ai.zerowidth/workbench

Est-ce que ai.zerowidth/workbench est sûr ?

Au dernier audit MCP Hub, le serveur MCP « ai.zerowidth/workbench » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 60 outils

• comments_create≈ 409 tokens

  Posts a comment on a workspace entity — a new thread, or a reply when rootId is given. Use it to leave findings where the discussion already lives (an eval result on the flow being debated, a summary on a long thread). Mention people via mentionedUserIds (from workspace member ids) to ring their notification bell; never mention someone who didn't ask to be pulled in.

  Paramètres, retour & exemple (7)

  Paramètres

  • body · string · requis
  • rootId · string · optionnel
    Reply into this thread; omit to start a new one.
  • entityId · string · requis
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.
  • approvalId · string · optionnel
  • entityKind · string · requis · workbench_flow | compass_page | compass_opportunity | caliper_review | caliper_dataset | caliper_rubric | caliper_eval | caliper_spec
    What the thread hangs on.
  • mentionedUserIds · array · optionnel

  Exemple d'appel

  {"name": "comments_create", "arguments": {"body": "texte", "entityId": "texte", "entityKind": "workbench_flow"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• comments_list≈ 306 tokens

  Lists the comment threads on one workspace entity (open first, then resolved) with authors and timestamps. Read this before weighing in on contested work — the threads are where disagreement lives before it becomes a decision.

  Paramètres, retour & exemple (3)

  Paramètres

  • entityId · string · requis
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.
  • entityKind · string · requis · workbench_flow | compass_page | compass_opportunity | caliper_review | caliper_dataset | caliper_rubric | caliper_eval | caliper_spec
    What the thread hangs on.

  Exemple d'appel

  {"name": "comments_list", "arguments": {"entityId": "texte", "entityKind": "workbench_flow"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• comments_resolve≈ 231 tokens

  Sets a comment thread's resolved state (rootId = the thread's root comment id). Resolve ONLY when the human asked or the thread's question is demonstrably settled — and say what settled it in a reply first. Reopening is for new evidence.

  Paramètres, retour & exemple (4)

  Paramètres

  • rootId · string · requis
  • resolved · boolean · requis
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.
  • approvalId · string · optionnel

  Exemple d'appel

  {"name": "comments_resolve", "arguments": {"rootId": "texte", "resolved": true}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• entity_tags_browse≈ 258 tokens

  Without a tag: every tag in use across the workspace with how many entities carry it, most-used first — the vocabulary the team already organizes by. With a tag: everything filed under it across every tool, each with its kind, id, title, and path. Use it to reuse existing labels instead of inventing near-duplicates, and to answer 'show me everything about X' when X is a label.

  Paramètres, retour & exemple (2)

  Paramètres

  • tag · string · optionnel
    A tag to expand into its items. Omit to list tags.
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.

  Exemple d'appel

  {"name": "entity_tags_browse", "arguments": {"tag": "texte", "workspace": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• entity_tags_get≈ 352 tokens

  Returns the tags on a batch of entities of one kind — the labels galleries organize by. Ids come from the kind's list/get tool or from search_workspace. Use it before entity_tags_set so you replace the full set knowingly, and to answer 'what is this filed under'. Entities the user can't see are omitted.

  Paramètres, retour & exemple (3)

  Paramètres

  • ids · array · requis
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.
  • entityKind · string · requis · workbench_flow | workbench_task | workbench_kb | compass_page | compass_opportunity | caliper_dataset | caliper_rubric | caliper_eval
    Which kind the ids belong to.

  Exemple d'appel

  {"name": "entity_tags_get", "arguments": {"ids": [], "entityKind": "workbench_flow"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• entity_tags_set≈ 413 tokens

  Replaces the FULL tag set on one entity (an empty list clears it). Read the current tags with entity_tags_get first and pass the merged list — this is not additive. Tags are lowercase letters, numbers, spaces, and hyphens; prefer labels already in use (entity_tags_browse) so the workspace's vocabulary stays small. The id comes from the kind's list/get tool or search_workspace.

  Paramètres, retour & exemple (5)

  Paramètres

  • tags · array · requis
  • entityId · string · requis
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.
  • approvalId · string · optionnel
    Approval id from a prior needs_confirmation response. Omit on the first call.
  • entityKind · string · requis · workbench_flow | workbench_task | workbench_kb | compass_page | compass_opportunity | caliper_dataset | caliper_rubric | caliper_eval

  Exemple d'appel

  {"name": "entity_tags_set", "arguments": {"tags": [], "entityId": "texte", "entityKind": "workbench_flow"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_doc≈ 161 tokens

  Fetch the full Markdown body of a specific docs page by its slug. Use this after `search_docs` when the user needs the complete content of a page. No authentication required.

  Paramètres, retour & exemple (1)

  Paramètres

  • slug · string · requis
    Page slug. Accepts 'compass/api', '/compass/api', or 'docs/compass/api'.

  Exemple d'appel

  {"name": "get_doc", "arguments": {"slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_docs≈ 156 tokens

  Enumerate all available docs pages, optionally filtered by product (e.g. 'compass', 'legal', 'overview'). Use this to discover what slugs exist before calling `get_doc`. No authentication required.

  Paramètres, retour & exemple (1)

  Paramètres

  • product · string · optionnel
    Optional product slug filter (e.g. 'compass', 'legal', 'overview').

  Exemple d'appel

  {"name": "list_docs", "arguments": {"product": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• search_docs≈ 226 tokens

  Search ZeroWidth product documentation. Returns matching pages with title, slug, public URL, and a query-relevant snippet. Use this when the user asks about a ZeroWidth product (Compass, Workbench, Caliper, Prism, Ledger, Napkin, zv1), an API behavior, or a policy. No authentication required — the docs corpus is public.

  Paramètres, retour & exemple (2)

  Paramètres

  • limit · integer · optionnel
    Max number of results. Defaults to 10.
  • query · string · requis
    Search query — keywords or natural-language phrase.

  Exemple d'appel

  {"name": "search_docs", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• search_workspace≈ 670 tokens

  Finds anything in the workspace in one call — uploaded files (searching the text inside them), folders, Workbench flows, shims, knowledge bases and tasks, Compass pages and changes, Caliper datasets, evals, rubrics, reviews, specs and sources, Ledger entries, Napkin sketches, decks, docs, sheets, diagrams and interfaces. The same search the person uses in Home. Use it FIRST whenever the user mentions something without saying where it lives ('the SOW', 'the dispatch interviews', 'that invoice'). The query is words in any order: each word must appear in the thing's name, its tags, the names of the folders it's filed under, or the text inside it — so 'northwind sow' finds the SOW filed in the Northwind folder, and 'dispatch interview' finds 'Dispatcher interview 1.md'. Results are ranked best first. Each hit carries its id, kind, path (for a link), folderPath (where it's filed, top-down), tags, and a snippet when the words were found inside it rather than in its name — say where a thing lives using folderPath. A file's id feeds workspace_files_read; other ids feed the kind's *_get tool. Pass folderId to search only inside one folder and everything under it. If nothing comes back, try fewer or different words before telling the user it doesn't exist. Results only include what the user can see, and only kinds this token may read.

  Paramètres, retour & exemple (5)

  Paramètres

  • q · string · requis
    Words, any order, case-insensitive. Fewer words find more.
  • kinds · array · optionnel
    Restrict to these kinds (file, folder, flow, page, doc, dataset, …). Omit to search everything.
  • limit · integer · optionnel
  • folderId · string · optionnel
    Only search inside this folder and the folders under it (ids from workspace_folders_browse or a folder hit).
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.

  Exemple d'appel

  {"name": "search_workspace", "arguments": {"q": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_executions_get≈ 362 tokens

  The flow's stack traces: recent executions with per-node timelines — what each node received, produced, how long it took, and the exact error when one failed. USE THIS when a run misbehaves instead of guessing: read the failing node's inputs/error, then propose a fix (workbench_flows_edit_text) grounded in what actually happened. Pass executionId to inspect one run, or just flowId for the most recent runs. Node inputs/outputs are truncated for transport — the full record is in the flow's dev drawer.

  Paramètres, retour & exemple (4)

  Paramètres

  • limit · integer · optionnel
    How many recent executions (default 3, max 10). Ignored when executionId is set.
  • flowId · string · requis
    Workbench flow id.
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys (workspace is intrinsic).
  • executionId · string · optionnel
    Specific execution to inspect. Omit for the latest runs.

  Exemple d'appel

  {"name": "workbench_executions_get", "arguments": {"flowId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_flow_authoring_guide≈ 165 tokens

  READ THIS FIRST before writing or editing any raw flow orchestration JSON. Covers the document shape, the settings-vs-input-ports rule (temperature, max_tokens, tools, response_format are PORTS, not settings — constants reach ports via value nodes), exact link format, plugin links, and three complete worked examples.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "workbench_flow_authoring_guide", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_flows_attach_knowledge_base≈ 434 tokens

  Attaches a knowledge base to an AGENT flow's draft, the same way picking it in the agent editor does: a docs knowledge base becomes a search tool the model calls when a question needs it; a tabular one also puts its tables in the prompt and adds a query tool. The flow needs a system prompt (scaffold it with one). Attaching one that's already there changes nothing. Do it BEFORE workbench_flows_publish: a published version is what interfaces and schedules run, so attach, try it with workbench_flows_run, then publish — and if something already pins an older version (an interface grant), re-grant the new version. Tell the model in its system prompt what the knowledge base holds and when to search it. May return `needs_confirmation`.

  Paramètres, retour & exemple (4)

  Paramètres

  • flowId · string · requis
    The agent flow, from workbench_flows_scaffold or workbench_flows_list.
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.
  • approvalId · string · optionnel
    Approval id from a prior needs_confirmation response. Omit on the first call.
  • knowledgeBaseId · string · requis
    The knowledge base id, from workbench_kb_create or workbench_kb_list.

  Exemple d'appel

  {"name": "workbench_flows_attach_knowledge_base", "arguments": {"flowId": "texte", "knowledgeBaseId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_flows_delete≈ 280 tokens

  Deletes a flow. Its schedules stop, guest share links die, and evals targeting it can no longer run (their binding shows flowOk: false) — check caliper_flow_performance for evals and workbench_flows_schedules_list before proposing, and prefer workbench_flows_update with archived: true when the user just wants it out of the way. May return `needs_confirmation`.

  Paramètres, retour & exemple (3)

  Paramètres

  • flowId · string · requis
    Flow id, from workbench_flows_list.
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.
  • approvalId · string · optionnel
    Approval id from a prior needs_confirmation response. Omit on the first call.

  Exemple d'appel

  {"name": "workbench_flows_delete", "arguments": {"flowId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_flows_edit_text≈ 550 tokens

  Applies ONE precise text replacement to a flow's DRAFT orchestration — Edit-tool semantics: `find` must be the EXACT current text, copied character-for-character from workbench_flows_get, and must occur exactly once anywhere in the flow (system prompts, node settings, metadata, a node's type). `find` is text inside ONE value, not JSON: to change a model, find the model slug alone (`anthropic-claude-haiku-4-5`) and replace it with another `llm` slug from workbench_node_catalog_get. It can't add or remove nodes or links. Zero or multiple matches return an error instead of guessing. This is the improvement primitive: check receipts first with caliper_flow_performance, cite the run id in `note`, apply the edit after approval, then re-run the eval with caliper_evals_run and report the score delta — never claim improvement without the before/after. Edits land on the draft only; the published version changes when someone publishes (workbench_flows_publish, after the user has seen the result). May return `needs_confirmation` — show the user the exact find/replace diff and wait.

  Paramètres, retour & exemple (6)

  Paramètres

  • find · string · requis
    EXACT current text (≥3 chars), copied verbatim — never reconstructed from memory.
  • note · string · requis
    Why this edit. Cite eval run ids when it follows a measurement (e.g. 'refund answers scored 1/5 on accuracy in run cer_abc — adds the manager-approval rule'). Lands in the audit log.
  • flowId · string · requis
    Flow to edit.
  • replace · string · requis
    Replacement text.
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this.
  • approvalId · string · optionnel
    Approval id from a prior needs_confirmation envelope.

  Exemple d'appel

  {"name": "workbench_flows_edit_text", "arguments": {"find": "texte", "note": "texte", "flowId": "texte", "replace": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_flows_fork≈ 384 tokens

  Copies a PUBLIC flow from another workspace (a template) into this one as a new draft the user owns. Identify it by its flowUuid (the id on Workbench's public template pages and in `workbench_flows_get` output); optionally pin which published version to copy. Flows already in this workspace can't be forked — open them instead. Counts toward the plan's flow cap. May return `needs_confirmation`.

  Paramètres, retour & exemple (4)

  Paramètres

  • flowUuid · string · requis
    The source flow's public uuid.
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.
  • approvalId · string · optionnel
    Approval id from a prior needs_confirmation response. Omit on the first call.
  • forkedFromVersion · string · optionnel
    Published version label to copy. Default: the latest published.

  Exemple d'appel

  {"name": "workbench_flows_fork", "arguments": {"flowUuid": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_flows_get≈ 350 tokens

  One flow. Default `view: summary` lists its nodes and links so you can pick one; `view: node` with a nodeId returns that node's full settings and prompt — read THAT before workbench_flows_edit_text, and copy `find` text from it character-for-character, never from memory. `view: full` returns the whole orchestration body.

  Paramètres, retour & exemple (4)

  Paramètres

  • view · string · optionnel · summary | node | full
    `summary` (default): the flow's fields plus one line per node (id, type, label, and how long its prompt is) and the links — enough to pick a node. `node`: the full settings of one node (pass nodeId) — what you need before workbench_flows_edit_text. `full`: the whole orchestration body; large.
  • flowId · string · requis
    Flow id.
  • nodeId · string · optionnel
    With view `node`: which node.
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys (workspace is intrinsic).

  Exemple d'appel

  {"name": "workbench_flows_get", "arguments": {"flowId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_flows_list≈ 180 tokens

  Lists every flow in the active workspace the caller can see. Returns summaries (id, name, visibility, updatedAt) — fetch one with `workbench_flows_get` for the full orchestration body.

  Paramètres, retour & exemple (1)

  Paramètres

  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys (workspace is intrinsic).

  Exemple d'appel

  {"name": "workbench_flows_list", "arguments": {"workspace": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_flows_publish≈ 403 tokens

  Snapshots the flow's current DRAFT as a named published version — the version schedules (workbench_flows_schedule), guest share links (workbench_flows_share_create), public-API runs, and 'published'-stage evals execute. The draft keeps evolving after this; runs on the published side don't change until the next publish. Publishing does NOT run the flow, but any eval set to runOnPublish starts a run (that spends credit — mention it when one exists). Publish only after the user has tested the draft (workbench_flows_run) or asked for it. May return `needs_confirmation`.

  Paramètres, retour & exemple (5)

  Paramètres

  • note · string · optionnel
    What changed — a commit message.
  • flowId · string · requis
    Flow to publish.
  • version · string · requis
    Version label, e.g. '1.0.0' or '2026-09-04'. Re-using a label retags it to this snapshot.
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.
  • approvalId · string · optionnel
    Approval id from a prior needs_confirmation response. Omit on the first call.

  Exemple d'appel

  {"name": "workbench_flows_publish", "arguments": {"flowId": "texte", "version": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_flows_revisions_list≈ 294 tokens

  The flow's revision history, newest first: published versions carry a `version` label and note; entries with version null are draft autosaves. Use it to answer 'is this published?' (any entry with a version), to find a revision id for caliper_evals_create's flowRevisionId, or to see when the draft last changed.

  Paramètres, retour & exemple (4)

  Paramètres

  • limit · integer · optionnel
    Entries to return, default 20.
  • flowId · string · requis
    Flow id.
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.
  • publishedOnly · boolean · optionnel
    true = only labeled published versions (default false).

  Exemple d'appel

  {"name": "workbench_flows_revisions_list", "arguments": {"flowId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_flows_run≈ 397 tokens

  Execute a flow and return its outputs synchronously. Runs the draft by default; pass source:"published" (optionally a version) to run the live published version. Spends workspace LLM budget, bounded by the token's cost cap. `input` is the flow's input envelope, e.g. {"kind":"chat","messages":[…]} or {"kind":"form","values":{…}}.

  Paramètres, retour & exemple (7)

  Paramètres

  • input · object · optionnel
    Flow input envelope (RunFlowInput). Omit for a flow that needs none.
  • flowId · string · requis
    Flow id to run.
  • source · string · optionnel · draft | published
    Which version to run. Default: draft.
  • version · string · optionnel
    Published version label (only with source:"published").
  • timeoutMs · integer · optionnel
    Max runtime in ms (also the hard cost ceiling).
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this. Ignored for workspace API keys.
  • approvalId · string · optionnel
    Re-call with the approvalId from a needs_confirmation response after the user approves.

  Exemple d'appel

  {"name": "workbench_flows_run", "arguments": {"flowId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_flows_scaffold≈ 1106 tokens

  Creates a runnable first-draft flow from a spec you author: pick the simplest pattern that fits (classifier for read-and-bucket, structurer for transform/extract/draft-for-review, agent for genuinely conversational), write a production-quality system prompt grounded in what the user told you, and mark anything stubbed with [STUB: ...] markers plus stubNotes. The draft opens in Workbench's simple editor at /w/<workspace>/flows/<id> — give the user that path. May return `needs_confirmation`; show the user what you're proposing and wait for their approval, then re-call with the approvalId. When the draft comes from a Compass change, pass its opportunityId so the flow and the change point at each other (Compass shows 'Open in Workbench'; the flow shows where it came from). Then: workbench_flows_run to try it, workbench_flows_publish when it's ready for schedules and share links.

  Paramètres, retour & exemple (13)

  Paramètres

  • mode · string · requis · agent | structurer | classifier | interviewer
    Pattern editor the draft opens in. Pick interviewer for conversations that LEARN something from a person (research calls, intake, retros) — pair it with workbench_flows_share_create so non-account humans can talk to it.
  • model · string · optionnel
    The model node slug the draft runs on, from workbench_node_catalog_get, that the workspace allows. For a classifier, a `decision` entry (Jev, Kev, Solar Decide); defaults to TypeSafe: Jev Latest. Otherwise an `llm` entry (e.g. an OpenAI, Anthropic, or Google model); defaults to Claude Haiku 4.5. Set it here rather than editing the flow afterwards.
  • flowName · string · requis
    Imperative + specific, ≤80 chars.
  • stubNotes · string · optionnel
    What's stubbed / missing / worth wiring next.
  • variables · array · optionnel
    agent / interviewer: types and descriptions for the {{tokens}} in systemPrompt. Every {{token}} becomes a variable on its own (the test pane and scenarios list it, the app fills it per user at run time); pass this only to set a type other than string or say what fills it.
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this.
  • approvalId · string · optionnel
    Approval id from a prior needs_confirmation response. Omit on the first call.
  • categories · array · optionnel
    classifier only: 2-12 buckets. The classifier asks the systemPrompt as one pick-one question with these as the options, and returns `values.category` plus `answers.category` (probabilities and confidence).
  • description · string · optionnel
    1-2 sentences: what it does, where it fits.
  • systemPrompt · string · optionnel
    The draft's behavior — production-quality first attempt with [STUB: ...] / [FILL IN: ...] markers where reality is missing. Required for structurer and classifier. Leave it out of an agent to get the bare model with no instructions (a 'promptless' agent).
  • opportunityId · string · optionnel
    Compass change (from compass_opportunities_list) this draft implements. Sets the flow ↔ change link; refused when the change already has a draft.
  • inputDescription · string · optionnel
    What the flow's single input carries.
  • responseSchemaJson · string · optionnel
    structurer only: the output JSON Schema, JSON-encoded as a string (object root, required fields, additionalProperties false).

  Exemple d'appel

  {"name": "workbench_flows_scaffold", "arguments": {"mode": "agent", "flowName": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_flows_scenarios_create≈ 384 tokens

  Saves a named scenario: values for the flow's variables, e.g. one demo customer. It shows in the test pane's Scenarios menu, and Caliper evals can run as it. Use the person's details from what the user shared (a CRM screenshot, a profile) and say which ones you made up. May return `needs_confirmation`.

  Paramètres, retour & exemple (5)

  Paramètres

  • flowId · string · requis
    Flow id.
  • values · object · optionnel
    Values by variable name, e.g. { member_first_name: "Lexi", plan_type: "Platinum" }. Names come from workbench_flows_scenarios_list's `variables`; a name the flow doesn't have is left out and reported back.
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.
  • approvalId · string · optionnel
    Approval id from a prior needs_confirmation response. Omit on the first call.
  • scenarioName · string · requis
    What it's called in the menu, e.g. 'Lexi Taylor, Platinum'.

  Exemple d'appel

  {"name": "workbench_flows_scenarios_create", "arguments": {"flowId": "texte", "scenarioName": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_flows_scenarios_delete≈ 243 tokens

  Deletes one scenario. A design session running as it goes back to no scenario. May return `needs_confirmation`.

  Paramètres, retour & exemple (4)

  Paramètres

  • flowId · string · requis
    Flow id.
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.
  • approvalId · string · optionnel
    Approval id from a prior needs_confirmation response. Omit on the first call.
  • scenarioId · string · requis
    Scenario id, from workbench_flows_scenarios_list.

  Exemple d'appel

  {"name": "workbench_flows_scenarios_delete", "arguments": {"flowId": "texte", "scenarioId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_flows_scenarios_list≈ 220 tokens

  A flow's variables (each {{token}} in an agent's prompt, with its type) and every saved scenario with its values. Read this before creating or updating a scenario, so the values use the flow's real variable names.

  Paramètres, retour & exemple (2)

  Paramètres

  • flowId · string · requis
    Flow id, from workbench_flows_list.
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.

  Exemple d'appel

  {"name": "workbench_flows_scenarios_list", "arguments": {"flowId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_flows_scenarios_update≈ 376 tokens

  Renames a scenario or changes its values. `values` MERGES into what's saved: pass only the variables that change, and null to clear one. Get the scenarioId from workbench_flows_scenarios_list. May return `needs_confirmation`.

  Paramètres, retour & exemple (6)

  Paramètres

  • flowId · string · requis
    Flow id.
  • values · object · optionnel
    Values by variable name, e.g. { member_first_name: "Lexi", plan_type: "Platinum" }. Names come from workbench_flows_scenarios_list's `variables`; a name the flow doesn't have is left out and reported back.
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.
  • approvalId · string · optionnel
    Approval id from a prior needs_confirmation response. Omit on the first call.
  • scenarioId · string · requis
    Scenario id, from workbench_flows_scenarios_list.
  • scenarioName · string · optionnel
    New name.

  Exemple d'appel

  {"name": "workbench_flows_scenarios_update", "arguments": {"flowId": "texte", "scenarioId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_flows_schedule≈ 837 tokens

  Set a specific built flow to run automatically on a cadence — the deterministic counterpart to a zv1 routine. Each run executes the flow's latest PUBLISHED revision with the fixed `input` envelope and routes the output per `delivery`. USE THIS when the user wants a flow they've built to run on a schedule ("run my digest flow every morning"). Do NOT create a routine for this — a routine runs a free-form instruction, not a built flow. The schedule runs the PUBLISHED flow, so the flow must be published (check workbench_flows_revisions_list; publish with workbench_flows_publish if it isn't). `input` is fixed for every run, so the flow itself should fetch anything time-varying at run time. Manage existing schedules with workbench_flows_schedules_list / workbench_flows_schedules_update.

  Paramètres, retour & exemple (10)

  Paramètres

  • input · ? · requis
    Fixed input envelope every run executes with — {"kind":"chat","messages":[…]} or {"kind":"form","values":{…}}, the same shape workbench_flows_run takes. Constant across runs.
  • label · ? · optionnel
  • flowId · string · requis
    Flow to schedule (id from workbench_flows_list).
  • delivery · string · optionnel · history | notification | email
  • interval · string · requis · hourly | daily | weekly
    Cadence: hourly, daily, or weekly.
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this. Ignored for workspace API keys.
  • approvalId · string · optionnel
    Approval id from a prior needs_confirmation response. Omit on the first call.
  • scheduleTime · ? · optionnel
  • scheduleTimezone · ? · optionnel
  • scheduleDayOfWeek · ? · optionnel

  Exemple d'appel

  {"name": "workbench_flows_schedule", "arguments": {"input": "texte", "flowId": "texte", "interval": "hourly"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_flows_schedules_delete≈ 258 tokens

  Removes a schedule for good. Prefer workbench_flows_schedules_update with enabled: false when the user might want it back. May return `needs_confirmation`.

  Paramètres, retour & exemple (4)

  Paramètres

  • flowId · string · requis
    Flow the schedule belongs to.
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.
  • approvalId · string · optionnel
    Approval id from a prior needs_confirmation response. Omit on the first call.
  • scheduleId · string · requis
    Schedule id, from workbench_flows_schedules_list.

  Exemple d'appel

  {"name": "workbench_flows_schedules_delete", "arguments": {"flowId": "texte", "scheduleId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_flows_schedules_list≈ 244 tokens

  Every schedule on one flow: cadence, whether it's paused (`enabled: false`), the next fire time, delivery, and the last run's status. Read this before workbench_flows_schedule (don't create a duplicate) and to get the scheduleId for workbench_flows_schedules_update / workbench_flows_schedules_delete / workbench_flows_schedules_run_now.

  Paramètres, retour & exemple (2)

  Paramètres

  • flowId · string · requis
    Flow id, from workbench_flows_list.
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.

  Exemple d'appel

  {"name": "workbench_flows_schedules_list", "arguments": {"flowId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_flows_schedules_run_now≈ 348 tokens

  Runs one iteration of a schedule immediately through the real scheduled pipeline (same input, same delivery — the email or channel it normally posts to) without moving its cadence. Works on paused schedules. Use it to test a schedule the user just set up. Spends workspace credit and delivers for real, so it sits behind the approval gate — may return `needs_confirmation`. The run is fire-and-forget: check workbench_flows_schedules_list for lastStatus, or workbench_executions_get for the trace.

  Paramètres, retour & exemple (4)

  Paramètres

  • flowId · string · requis
    Flow the schedule belongs to.
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.
  • approvalId · string · optionnel
    Approval id from a prior needs_confirmation response. Omit on the first call.
  • scheduleId · string · requis
    Schedule id, from workbench_flows_schedules_list.

  Exemple d'appel

  {"name": "workbench_flows_schedules_run_now", "arguments": {"flowId": "texte", "scheduleId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_flows_schedules_update≈ 775 tokens

  Changes one schedule: `enabled: false` pauses it (configuration kept), `enabled: true` resumes and recomputes the next fire time from now; `interval` / `scheduleTime` / `scheduleTimezone` / `scheduleDayOfWeek` change the cadence; `label`, `delivery`, and `input` can change too. Pass only what changes. Get the scheduleId from workbench_flows_schedules_list. May return `needs_confirmation`.

  Paramètres, retour & exemple (12)

  Paramètres

  • input · ? · optionnel
    New fixed input envelope — {"kind":"chat","messages":[…]} or {"kind":"form","values":{…}}.
  • label · ? · optionnel
  • flowId · string · requis
    Flow the schedule belongs to.
  • enabled · boolean · optionnel
    false pauses, true resumes.
  • delivery · string · optionnel · history | notification | email
  • interval · string · optionnel · hourly | daily | weekly
    New cadence: hourly, daily, or weekly.
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.
  • approvalId · string · optionnel
    Approval id from a prior needs_confirmation response. Omit on the first call.
  • scheduleId · string · requis
    Schedule id, from workbench_flows_schedules_list.
  • scheduleTime · ? · optionnel
  • scheduleTimezone · ? · optionnel
  • scheduleDayOfWeek · ? · optionnel

  Exemple d'appel

  {"name": "workbench_flows_schedules_update", "arguments": {"flowId": "texte", "scheduleId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_flows_share_create≈ 365 tokens

  Creates a no-account guest link where anyone can chat with the flow's latest PUBLISHED revision at workbench's /s/<token> page — the fastest way to put a working flow in a stakeholder's hands ('here, try it'). The flow must have a published version (workbench_flows_revisions_list shows it; publish with workbench_flows_publish if not). Conversations are capped per guest; the link can expire, and you can list links with workbench_flows_shares_list and kill one with workbench_flows_shares_revoke. May return `needs_confirmation` — say who the link is for and wait.

  Paramètres, retour & exemple (5)

  Paramètres

  • label · string · optionnel
    Who/what this link is for, e.g. 'support pilot'.
  • flowId · string · requis
    Flow to share.
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this.
  • approvalId · string · optionnel
    Approval id from a prior needs_confirmation envelope.
  • expiresInDays · integer · optionnel
    Days until the link dies. Omit = revoke-only.

  Exemple d'appel

  {"name": "workbench_flows_share_create", "arguments": {"flowId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_flows_shares_list≈ 240 tokens

  Every guest link on one flow, newest first: label, whether it's still live, the shareUrl (live links only — dead ones have no URL), expiry, and how many guests and messages it has seen. Use it to answer 'who has access', to recover a link the user lost, and to get the shareId for workbench_flows_shares_revoke.

  Paramètres, retour & exemple (2)

  Paramètres

  • flowId · string · requis
    Flow id, from workbench_flows_list.
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.

  Exemple d'appel

  {"name": "workbench_flows_shares_list", "arguments": {"flowId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_flows_shares_revoke≈ 275 tokens

  Kills one guest link immediately — anyone holding it gets a closed page from then on. Conversations already had stay in the flow's history. Get the shareId from workbench_flows_shares_list. May return `needs_confirmation`.

  Paramètres, retour & exemple (4)

  Paramètres

  • flowId · string · requis
    Flow the link belongs to.
  • shareId · string · requis
    Share id, from workbench_flows_shares_list.
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.
  • approvalId · string · optionnel
    Approval id from a prior needs_confirmation response. Omit on the first call.

  Exemple d'appel

  {"name": "workbench_flows_shares_revoke", "arguments": {"flowId": "texte", "shareId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_flows_update≈ 481 tokens

  Changes a flow's name, description, visibility, tags, or archived state — the metadata around the flow, NOT its orchestration (prompts and nodes change through workbench_flows_edit_text). Pass only what changes. Archiving hides the flow from the default gallery but leaves it runnable, scheduled, and shared; pass archived: false to restore. May return `needs_confirmation`.

  Paramètres, retour & exemple (8)

  Paramètres

  • tags · array · optionnel
    Replacement tag set (lowercase labels). The whole set, not a diff.
  • flowId · string · requis
    Flow id, from workbench_flows_list.
  • archived · boolean · optionnel
    true archives, false restores.
  • flowName · string · optionnel
    New name.
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.
  • approvalId · string · optionnel
    Approval id from a prior needs_confirmation response. Omit on the first call.
  • visibility · string · optionnel · PRIVATE | WORKSPACE | SHARED
    Who can see it: PRIVATE (only the user), WORKSPACE (every member, the default), or SHARED (specific people, granted afterwards). Say 'make it private' → PRIVATE.
  • description · ? · optionnel
    New description; null clears it.

  Exemple d'appel

  {"name": "workbench_flows_update", "arguments": {"flowId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_kb_add_documents≈ 574 tokens

  Adds documents to a knowledge base and starts ingestion (chunk + embed; graph KBs also extract entities; tabular KBs load CSV as tables). Text goes inline (Markdown, plain text, CSV — encoding utf8); binary files (PDF, .docx) go base64-encoded with their mimeType. Up to 50 sources per call, ~10 MB each. Ingestion runs in the BACKGROUND — the result carries a runId; check it with workbench_kb_ingestion_status when the user asks, don't poll. workbench_kb_search works once it finishes. Content from <attached-file> blocks is ideal source material. Check workbench_kb_documents_list first so you don't add a document twice. Embedding spends workspace inference credit, so this sits behind the approval gate: may return `needs_confirmation`.

  Paramètres, retour & exemple (4)

  Paramètres

  • kbId · string · requis
    Knowledge base id (from workbench_kb_list or workbench_kb_create).
  • sources · array · requis
    Documents to ingest (1-50).
  • workspace · string · optionnel
    Workspace slug override.
  • approvalId · string · optionnel
    Approval id from a prior needs_confirmation envelope.

  Exemple d'appel

  {"name": "workbench_kb_add_documents", "arguments": {"kbId": "texte", "sources": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_kb_create≈ 354 tokens

  Creates an empty knowledge base. Recipe 'docs' (default) for reference material an agent searches at runtime; 'tabular' for spreadsheet-style data queried with SQL; 'graph' for entity/relationship extraction. After creating, add content with workbench_kb_add_documents, then give an agent flow a search tool over it with workbench_flows_attach_knowledge_base (before publishing the flow). May return `needs_confirmation`.

  Paramètres, retour & exemple (6)

  Paramètres

  • name · string · requis
    Knowledge base name (1-200 chars).
  • recipe · string · optionnel · docs | tabular | graph
    Default 'docs'.
  • workspace · string · optionnel
    Workspace slug override.
  • approvalId · string · optionnel
    Approval id from a prior needs_confirmation envelope.
  • visibility · string · optionnel · PRIVATE | WORKSPACE | SHARED
    Who can see it: PRIVATE (only the user), WORKSPACE (every member, the default), or SHARED (specific people, granted afterwards). Say 'make it private' → PRIVATE.
  • description · string · optionnel

  Exemple d'appel

  {"name": "workbench_kb_create", "arguments": {"name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_kb_delete≈ 247 tokens

  Deletes a knowledge base and everything in it. Flows that search it will find nothing — check which agents use it (the user knows; the KB page in Workbench lists them) and say so before proposing. May return `needs_confirmation`.

  Paramètres, retour & exemple (3)

  Paramètres

  • kbId · string · requis
    Knowledge base id, from workbench_kb_list.
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.
  • approvalId · string · optionnel
    Approval id from a prior needs_confirmation response. Omit on the first call.

  Exemple d'appel

  {"name": "workbench_kb_delete", "arguments": {"kbId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_kb_document_delete≈ 286 tokens

  Removes one ingested document and all its chunks; searches stop returning it at once. Get the documentId from workbench_kb_documents_list. To replace a document, remove it then workbench_kb_add_documents the new version. May return `needs_confirmation`.

  Paramètres, retour & exemple (4)

  Paramètres

  • kbId · string · requis
    Knowledge base id.
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.
  • approvalId · string · optionnel
    Approval id from a prior needs_confirmation response. Omit on the first call.
  • documentId · string · requis
    Document id, from workbench_kb_documents_list.

  Exemple d'appel

  {"name": "workbench_kb_document_delete", "arguments": {"kbId": "texte", "documentId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_kb_documents_list≈ 252 tokens

  Every document ingested into the KB's current content: id, name, type, size, chunk count. Empty for a KB with nothing ingested yet (or one whose ingestion is still running — check workbench_kb_ingestion_status). Use it before workbench_kb_add_documents to avoid re-adding a document, and to get the documentId for workbench_kb_document_delete.

  Paramètres, retour & exemple (2)

  Paramètres

  • kbId · string · requis
    Knowledge base id, from workbench_kb_list.
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.

  Exemple d'appel

  {"name": "workbench_kb_documents_list", "arguments": {"kbId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_kb_get≈ 210 tokens

  One knowledge base: name, recipe (docs / tabular / graph), status, document and chunk counts, embedding model, and ingestion settings. Read it to confirm a KB has content before pointing a flow at it. Get the kbId from workbench_kb_list.

  Paramètres, retour & exemple (2)

  Paramètres

  • kbId · string · requis
    Knowledge base id.
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.

  Exemple d'appel

  {"name": "workbench_kb_get", "arguments": {"kbId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_kb_ingestion_status≈ 273 tokens

  The state of one ingestion run started by workbench_kb_add_documents: PENDING / RUNNING / DONE / FAILED, chunks written, and the error when it failed. Read it when the user asks whether their documents are in yet, or before a search that needs them — don't poll in a loop; ingestion of a few documents takes under a minute. Pass the runId the add-documents call returned.

  Paramètres, retour & exemple (3)

  Paramètres

  • kbId · string · requis
    Knowledge base id.
  • runId · string · requis
    Ingestion run id, from workbench_kb_add_documents.
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.

  Exemple d'appel

  {"name": "workbench_kb_ingestion_status", "arguments": {"kbId": "texte", "runId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_kb_list≈ 187 tokens

  Lists every knowledge base in the active workspace the caller can see. Returns summaries (id, name, description, status, doc/chunk counts, embedding model). Use an id with `workbench_kb_search` to retrieve content.

  Paramètres, retour & exemple (1)

  Paramètres

  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys (workspace is intrinsic).

  Exemple d'appel

  {"name": "workbench_kb_list", "arguments": {"workspace": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_kb_search≈ 344 tokens

  Retrieves the most relevant chunks from one knowledge base — the core RAG primitive. `mode:"semantic"` (default) embeds the query and ranks by meaning (spends a small amount of workspace credit); `mode:"keyword"` is a free case-insensitive substring match. Each hit carries the chunk text, its document, and a score (cosine similarity 0-1 for semantic, match count for keyword). Get a kbId from `workbench_kb_list`.

  Paramètres, retour & exemple (5)

  Paramètres

  • kbId · string · requis
    Knowledge base id (from workbench_kb_list).
  • mode · string · optionnel · semantic | keyword
    semantic (embed + rank by meaning, default) or keyword (free substring match).
  • limit · integer · optionnel
    Max hits to return, 1-50. Default 10.
  • query · string · requis
    What to search for.
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this. Ignored for workspace API keys.

  Exemple d'appel

  {"name": "workbench_kb_search", "arguments": {"kbId": "texte", "query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_node_catalog_get≈ 433 tokens

  The ground truth for what nodes exist and what their ports actually are — verify against this instead of recalling. Search by keyword/category for summaries; pass `slug` for one node's full detail (inputs, outputs, settings). Inputs are PORTS fed by links; settings live on the node — see `workbench_flow_authoring_guide`. The catalog is the WORKSPACE'S: model nodes the workspace's inference policy forbids come back with `allowed: false` — never author with those; pick an allowed model. Pass `flowId` to include the flow's pinned imports as nodes.

  Paramètres, retour & exemple (7)

  Paramètres

  • q · string · optionnel
    Keyword over slug / name / tagline / description.
  • slug · string · optionnel
    Exact node slug → full detail for that one node (ports + settings).
  • limit · integer · optionnel
    Results per page, 1-50. Default 20.
  • flowId · string · optionnel
    A flow whose pinned imports should appear as `imported-<uuid>` nodes.
  • offset · integer · optionnel
    Pagination offset.
  • category · string · optionnel
    Filter by category.
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; the catalog's policy annotation is per workspace.

  Exemple d'appel

  {"name": "workbench_node_catalog_get", "arguments": {"q": "texte", "slug": "texte", "limit": 1, "flowId": "texte", "offset": 1, "category": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_shim_add_answer≈ 276 tokens

  Adds one answer (a label and, optionally, when it applies). The shim needs three examples of it before it builds again with the new answer. May return `needs_confirmation`.

  Paramètres, retour & exemple (5)

  Paramètres

  • answer · string · requis
  • shimId · string · requis
    Shim id, from workbench_shim_list.
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.
  • approvalId · string · optionnel
    Approval id from a prior needs_confirmation response. Omit on the first call.
  • description · string · optionnel
    When this answer applies.

  Exemple d'appel

  {"name": "workbench_shim_add_answer", "arguments": {"answer": "texte", "shimId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_shim_add_examples≈ 373 tokens

  Adds example inputs to one answer. Write inputs a real person would actually type in the shim's setting — varied in length, register and specifics, each one clearly this answer and not another — never paraphrases of the answer's name. Read the shim first so new examples fit alongside the existing ones and land where recall is low. Exact duplicates are skipped. The shim rebuilds on its own afterwards; read it again for the new report. May return `needs_confirmation`.

  Paramètres, retour & exemple (5)

  Paramètres

  • answer · string · requis
    The answer these examples belong to, exactly as labelled.
  • shimId · string · requis
    Shim id, from workbench_shim_list.
  • examples · array · requis
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.
  • approvalId · string · optionnel
    Approval id from a prior needs_confirmation response. Omit on the first call.

  Exemple d'appel

  {"name": "workbench_shim_add_examples", "arguments": {"answer": "texte", "shimId": "texte", "examples": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_shim_create≈ 394 tokens

  Creates a shim from a name, the question it answers, and its answers. Add examples afterwards with workbench_shim_add_examples — three or more per answer and it builds on its own. May return `needs_confirmation`.

  Paramètres, retour & exemple (6)

  Paramètres

  • name · string · requis
    A short name, e.g. "Support triage".
  • answers · array · requis
  • question · string · requis
    The question, e.g. "Which team should read this message?"
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.
  • approvalId · string · optionnel
    Approval id from a prior needs_confirmation response. Omit on the first call.
  • inputsComeFrom · string · optionnel
    One line on where the inputs come from, in the user's words.

  Exemple d'appel

  {"name": "workbench_shim_create", "arguments": {"name": "texte", "answers": [], "question": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_shim_get≈ 265 tokens

  One shim in full: the question, where its inputs come from, every answer with its description and examples, what the shim still needs before it can build, and the newest build's report — held-out accuracy, recall per answer, which answers get mistaken for which, and the compiler's notes. Read it before writing examples: match the setting and the existing examples' register, and put new examples where recall is low or the compiler says an answer is thin.

  Paramètres, retour & exemple (2)

  Paramètres

  • shimId · string · requis
    Shim id, from workbench_shim_list.
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.

  Exemple d'appel

  {"name": "workbench_shim_get", "arguments": {"shimId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_shim_list≈ 195 tokens

  Every shim the user can see: id, name, the question it answers, how many answers and examples it has, and the published version's held-out accuracy (null until something is published). A shim is a small decision model that runs inside an app with no model call. Start here to get a shimId.

  Paramètres, retour & exemple (1)

  Paramètres

  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.

  Exemple d'appel

  {"name": "workbench_shim_list", "arguments": {"workspace": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_tasks_act≈ 337 tokens

  Records THIS user's verdict on a run that is waiting on them — the labels come from the gate (workbench_tasks_run_view shows them via the plan; a wrong label errors listing the real options). Echo the verdict + note back to the user in one line BEFORE calling; that echo is the confirmation. Refuses when the gate is assigned to someone else.

  Paramètres, retour & exemple (5)

  Paramètres

  • note · string · optionnel
    The user's reasoning, attached to the verdict.
  • runId · string · requis
    Task run id that is waiting_human.
  • verdict · string · requis
    One of the gate's verdict labels, e.g. "confirmed".
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.
  • approvalId · string · optionnel
    Approval id from a prior needs_confirmation response. Omit on the first call.

  Exemple d'appel

  {"name": "workbench_tasks_act", "arguments": {"runId": "texte", "verdict": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_tasks_compile≈ 330 tokens

  Runs the compiler over a sentence and returns the PROPOSED plan (or repair-grade problems — fix by refining the sentence with the user, not by guessing). Nothing persists. Present the proposal in plain terms: which clauses run flows, which you (zv1) will handle, who decides, what the compiler noted. Then iterate or freeze. Compile may take ~15s.

  Paramètres, retour & exemple (4)

  Paramètres

  • taskId · string · optionnel
    The task this sentence belongs to, when compiling an edit — keeps it out of the child-task candidates.
  • sentence · string · requis
    The sentence to compile.
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.
  • approvalId · string · optionnel
    Re-call with the approvalId from a needs_confirmation response after the user approves.

  Exemple d'appel

  {"name": "workbench_tasks_compile", "arguments": {"sentence": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_tasks_create≈ 294 tokens

  Creates a DRAFT Task from a name + sentence. Use this once the user's sentence feels settled after you've refined it together — then compile it. The sentence should be THEIR words: trigger first ('When a claim arrives…'), then steps, branches, and who decides what.

  Paramètres, retour & exemple (4)

  Paramètres

  • sentence · string · requis
    The process sentence, in the user's words.
  • taskName · string · requis
    Short task name.
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.
  • approvalId · string · optionnel
    Approval id from a prior needs_confirmation response. Omit on the first call.

  Exemple d'appel

  {"name": "workbench_tasks_create", "arguments": {"sentence": "texte", "taskName": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_tasks_delete≈ 254 tokens

  Deletes a task. Runs still in flight are stopped (a gate waiting on someone is closed), and its schedule trigger stops firing; past runs stay in history. Check workbench_tasks_get for live runs and say so before proposing. May return `needs_confirmation`.

  Paramètres, retour & exemple (3)

  Paramètres

  • taskId · string · requis
    Task id, from workbench_tasks_list.
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.
  • approvalId · string · optionnel
    Approval id from a prior needs_confirmation response. Omit on the first call.

  Exemple d'appel

  {"name": "workbench_tasks_delete", "arguments": {"taskId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_tasks_freeze≈ 352 tokens

  Freezes a reviewed plan as the Task's next version and activates it. Pass the EXACT plan object a compile returned — never hand-edit it (change the sentence and recompile instead). Freeze ONLY after the user has seen the proposal and said go; echo what you're freezing in one line first. In-flight runs keep their pinned versions. After freezing, offer to start a first run.

  Paramètres, retour & exemple (5)

  Paramètres

  • plan · ? · requis
    The plan object from workbench_tasks_compile, verbatim.
  • taskId · string · requis
    The task id (create a draft first if none).
  • sentence · string · requis
    The sentence this plan was compiled from.
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.
  • approvalId · string · optionnel
    Approval id from a prior needs_confirmation response. Omit on the first call.

  Exemple d'appel

  {"name": "workbench_tasks_freeze", "arguments": {"plan": "texte", "taskId": "texte", "sentence": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_tasks_get≈ 257 tokens

  One Task in full: its sentence, status, the latest saved plan (the clauses — which run flows, which zv1 handles, who decides at each gate) with the flow and people names the plan refers to, and its recent runs. Read this before editing a task's sentence (workbench_tasks_compile with taskId) and when the user asks what a task does. Get the taskId from workbench_tasks_list.

  Paramètres, retour & exemple (2)

  Paramètres

  • taskId · string · requis
    Task id.
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.

  Exemple d'appel

  {"name": "workbench_tasks_get", "arguments": {"taskId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_tasks_list≈ 196 tokens

  Lists the workspace's Tasks — sentence-orchestrated processes — with their sentence, status, and recent runs (id, status, who a waiting run is on). Use this to find a task the user names ('claims intake') and to see what's in flight; workbench_tasks_get reads one in full.

  Paramètres, retour & exemple (1)

  Paramètres

  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.

  Exemple d'appel

  {"name": "workbench_tasks_list", "arguments": {"workspace": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_tasks_run_view≈ 217 tokens

  The run's current state rendered as its sentence: what ran (with timings), which path each gate took, what's waiting on whom and for how long, what's coming up. Use whenever the user asks where something stands, and after acting on a gate.

  Paramètres, retour & exemple (2)

  Paramètres

  • runId · string · requis
    Task run id.
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.

  Exemple d'appel

  {"name": "workbench_tasks_run_view", "arguments": {"runId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_tasks_start≈ 282 tokens

  Kicks off a run of a Task. When the task expects an input document (its trigger has an input), pass the user's material as `input` — pasted text, extracted attachment text, or JSON. Cite the run id back and tell the user what happens next (the run may immediately be waiting on someone).

  Paramètres, retour & exemple (4)

  Paramètres

  • input · ? · optionnel
    Trigger payload — the document text / JSON the task starts from.
  • taskId · string · requis
    Task id (from workbench_tasks_list).
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.
  • approvalId · string · optionnel
    Approval id from a prior needs_confirmation response. Omit on the first call.

  Exemple d'appel

  {"name": "workbench_tasks_start", "arguments": {"taskId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workbench_tasks_update≈ 266 tokens

  Changes a task's name — the gallery label only. The sentence and plan are versioned and change through workbench_tasks_compile + workbench_tasks_freeze, never here. May return `needs_confirmation`.

  Paramètres, retour & exemple (4)

  Paramètres

  • taskId · string · requis
    Task id, from workbench_tasks_list.
  • taskName · string · requis
    New name.
  • workspace · string · optionnel
    Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.
  • approvalId · string · optionnel
    Approval id from a prior needs_confirmation response. Omit on the first call.

  Exemple d'appel

  {"name": "workbench_tasks_update", "arguments": {"taskId": "texte", "taskName": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://api.zerowidth.ai/mcp/x/workbench