ai.letsship/ship

Est-ce que ai.letsship/ship est sûr ?

Au dernier audit MCP Hub, le serveur MCP « ai.letsship/ship » 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 72 outils

• activate_sandbox_template_version≈ 180 tokens

  Make a version the one missions use from their next dispatch. It is rebuilt only if its snapshot is gone; the response says which.

  Paramètres, retour & exemple (2)

  Paramètres

  • versionId · string · requis
    Version id (stv_...)
  • templateId · string · requis
    Sandbox id (sbt_...)

  Exemple d'appel

  {"name": "activate_sandbox_template_version", "arguments": {"versionId": "texte", "templateId": "texte"}}

  Exemple de retour

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

• approve_mission_ceiling≈ 246 tokens

  A mission that reached its credit limit pauses until a member lets it continue. This raises the mission's limit by one step and runs the stage that stopped again, so it spends credits: ask the person first. Returns the new limit. Answers 409 when the mission is not at its limit. Requires the missions:run scope.

  Paramètres, retour & exemple (2)

  Paramètres

  • issueId · string · requis
    The mission's issue id: a Linear key or a GitHub Issues id, e.g. SHIP-412
  • projectId · string · requis
    Project id the mission belongs to (get_mission's summary.projectId)

  Exemple d'appel

  {"name": "approve_mission_ceiling", "arguments": {"issueId": "texte", "projectId": "texte"}}

  Exemple de retour

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

• archive_mission≈ 170 tokens

  Hide a finished mission from list_missions and the board. Nothing else changes: unarchive_mission shows it again. Requires the missions:write scope and the config:write capability (an owner or admin).

  Paramètres, retour & exemple (1)

  Paramètres

  • issueId · string · requis
    The mission's issue id: a Linear key or a GitHub Issues id, e.g. SHIP-412

  Exemple d'appel

  {"name": "archive_mission", "arguments": {"issueId": "texte"}}

  Exemple de retour

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

• bind_mcp_server≈ 962 tokens

  Create or update the binding for a server the repository declares. roles is the full set of pipeline roles that may use it (reviewer and qa only ever receive read-only tools, and cannot use a server that runs inside the sandbox). transport: 'remote' (the gateway proxies to the server's URL), 'isolate' (the gateway runs the server's npm package in isolation, for a command that needs a secret) or 'local' (the command runs inside the sandbox, no credential). Omit transport and remoteUrl on an update to keep the server the binding is pinned to, with its credential (a roles, tools or credential edit); set them only to bind or re-point the server. Requires the config:write capability.

  Paramètres, retour & exemple (7)

  Paramètres

  • roles · array · requis
    Every role that may use the server ([] disables it)
  • projectId · string · requis
    Project id, e.g. from list_projects
  • remoteUrl · string · optionnel
    A fixed https URL: a hosted endpoint for a command server, or an override for a URL server
  • transport · string · optionnel · remote | isolate | local
    How the gateway reaches the server: 'remote' proxies to remoteUrl, 'isolate' runs the server's npm package away from the sandbox so a secret stays out of it, and 'local' runs the command inside the sandbox with no credential. Omit it on an update to keep the server the binding is pinned to.
  • credential · ? · optionnel
    Write-only credential the gateway attaches; agents never receive it. Omit to keep the stored one. OAuth credentials are not set here: bind as remote with kind 'none', then start_mcp_server_oauth.
  • serverName · string · requis
    Server name as the repository's MCP file declares it (see list_mcp_servers)
  • approvedTools · array · optionnel
    The approved subset of the tool snapshot (refresh_mcp_server_tools first). Omit to keep it.

  Exemple d'appel

  {"name": "bind_mcp_server", "arguments": {"roles": [], "projectId": "texte", "serverName": "texte"}}

  Exemple de retour

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

• build_sandbox_template≈ 130 tokens

  Build the sandbox's active version, or return the build already running for it.

  Paramètres, retour & exemple (1)

  Paramètres

  • templateId · string · requis
    Sandbox id (sbt_...)

  Exemple d'appel

  {"name": "build_sandbox_template", "arguments": {"templateId": "texte"}}

  Exemple de retour

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

• clear_agents_override≈ 178 tokens

  Delete the per-issue agents/baseBranch override — the mission resolves from ship.yml again.

  Paramètres, retour & exemple (2)

  Paramètres

  • issueId · string · requis
    The mission's issue id: a Linear key or a GitHub Issues id, e.g. SHIP-353 or WEB-42
  • projectId · string · requis
    Project id the mission belongs to

  Exemple d'appel

  {"name": "clear_agents_override", "arguments": {"issueId": "texte", "projectId": "texte"}}

  Exemple de retour

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

• create_mission≈ 715 tokens

  Create the tracker issue AND start the run in one call, for work that has no issue yet. Pass entryStartAt='builder' with an entryPlan to hand over a plan you already wrote; pass entryStartAt='reviewer'/'qa' with entryPrNumber to hand over an existing build — in which case title may be omitted and the pull request's own title names the mission. This tool calls the SHIP API, documented at https://letsship.ai/docs/api. Requires the missions:run token scope.

  Paramètres, retour & exemple (8)

  Paramètres

  • title · string · optionnel
    Issue title. Omit ONLY with entryPrNumber — the pull request's own title is then used
  • agents · object · optionnel
    Per-role harness/model override for THIS mission only; overrides ship.yml without changing it
  • labels · array · optionnel
    Tracker labels to apply
  • entryPlan · string · optionnel
    Hand-off plan markdown, for entryStartAt='builder'
  • projectId · string · requis
    Project id the mission belongs to
  • description · string · optionnel
    Issue body; acceptance criteria written here are parsed as they would be on any issue
  • entryStartAt · string · optionnel · builder | reviewer | qa
    Pipeline stage to enter at; omit for the default full run starting at the planner
  • entryPrNumber · integer · optionnel
    Existing open PR number, required for entryStartAt='reviewer' or 'qa'

  Exemple d'appel

  {"name": "create_mission", "arguments": {"projectId": "texte"}}

  Exemple de retour

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

• create_scheduled_task≈ 702 tokens

  Create a recurring agent mission. Firing it — on schedule, or immediately via run_scheduled_task — creates an ordinary tracker issue assigned to the agent, which drives a normal pipeline run: a scheduled task is a stored mission request, not a new execution mode. This tool calls the SHIP API, documented at https://letsship.ai/docs/api. Requires the config:write capability.

  Paramètres, retour & exemple (12)

  Paramètres

  • name · string · requis
    Scheduled task name, shown in the console and used in the issue title
  • time · string · requis
    24-hour wall-clock time in `timezone`, e.g. '09:00'.
  • labels · array · optionnel
    Tracker label names put on every issue this scheduled task files (default none). The label must ALREADY exist in the project's tracker team — the platform attaches labels but cannot create them, so a name the workspace does not have is dropped.
  • prompt · string · requis
    Becomes the created issue's description verbatim on every fire
  • enabled · boolean · optionnel
    Whether the schedule is armed (default true)
  • weekday · string · optionnel · monday | tuesday | wednesday | thursday | friday | saturday | sunday
    Day of week — required when interval is 'weekly'.
  • interval · string · requis · daily | weekly | monthly
    Fire cadence. 'weekly' requires weekday; 'monthly' requires dayOfMonth.
  • timezone · string · requis
    IANA timezone id, e.g. 'Europe/Amsterdam'.
  • projectId · string · requis
    Project id the scheduled task belongs to
  • dayOfMonth · integer · optionnel
    Day of month, 1-28 — required when interval is 'monthly' (capped at 28 so every month has the day).
  • templateKey · string · optionnel
    Attribution only, when authored from a template — see list_scheduled_task_templates
  • skipIfPreviousOpen · boolean · optionnel
    Skip a scheduled fire while the previous fire's mission is still open (default true — the guardrail is opt-out, not opt-in)

  Exemple d'appel

  {"name": "create_scheduled_task", "arguments": {"name": "texte", "time": "texte", "prompt": "texte", "interval": "daily", "timezone": "texte", "projectId": "texte"}}

  Exemple de retour

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

• decline_mission≈ 167 tokens

  Close the mission's open pull request on GitHub without merging it; the mission becomes declined, and no call here reopens it. Requires the missions:write scope.

  Paramètres, retour & exemple (1)

  Paramètres

  • issueId · string · requis
    The mission's issue id: a Linear key or a GitHub Issues id, e.g. SHIP-412

  Exemple d'appel

  {"name": "decline_mission", "arguments": {"issueId": "texte"}}

  Exemple de retour

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

• delete_sandbox_registry≈ 184 tokens

  Delete the stored credential of a private registry (an id from list_sandbox_registries). A sandbox build that installs from that host then gets no credential. Requires the connectors:write scope and the config:write capability.

  Paramètres, retour & exemple (1)

  Paramètres

  • registryId · string · requis
    Registry credential id, from list_sandbox_registries

  Exemple d'appel

  {"name": "delete_sandbox_registry", "arguments": {"registryId": "texte"}}

  Exemple de retour

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

• delete_sandbox_template≈ 185 tokens

  Delete a sandbox with all its versions and builds. Answers 409 while an agent or a project's default sandbox uses it: point those at another sandbox first (update_project with defaultSandboxTemplateId). Missions that run in it now finish. Requires the agents:write scope and the config:write capability.

  Paramètres, retour & exemple (1)

  Paramètres

  • templateId · string · requis
    Sandbox id (sbt_...)

  Exemple d'appel

  {"name": "delete_sandbox_template", "arguments": {"templateId": "texte"}}

  Exemple de retour

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

• delete_scheduled_task≈ 182 tokens

  Delete a scheduled task and its run history, which no call can bring back. Missions it already started continue. Setting enabled to false stops new runs and keeps the task and its history. Requires the scheduled-tasks:write scope and the config:write capability.

  Paramètres, retour & exemple (1)

  Paramètres

  • scheduledTaskId · string · requis
    Scheduled task id to delete

  Exemple d'appel

  {"name": "delete_scheduled_task", "arguments": {"scheduledTaskId": "texte"}}

  Exemple de retour

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

• destroy_environment≈ 158 tokens

  Request teardown of a preview environment (its deployed Worker(s) + every provisioned datastore). Enqueues to the orchestrator; requires project write capability.

  Paramètres, retour & exemple (1)

  Paramètres

  • environmentId · string · requis
    Environment id to tear down

  Exemple d'appel

  {"name": "destroy_environment", "arguments": {"environmentId": "texte"}}

  Exemple de retour

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

• dismiss_notice≈ 200 tokens

  Close a notice for the person this token acts for, as the console's close button does. Only a notice with dismissible: true can be closed (a low balance). It stays closed while its id lasts: a low balance that a top-up ends and a later spend brings back has a new id and shows again. Critical notices cannot be closed.

  Paramètres, retour & exemple (1)

  Paramètres

  • noticeId · string · requis
    The notice's id from get_notices, e.g. credits_low:<grant>

  Exemple d'appel

  {"name": "dismiss_notice", "arguments": {"noticeId": "texte"}}

  Exemple de retour

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

• get_agent_run≈ 187 tokens

  Fetch one agent run: its run record, metric series (CPU/mem/disk over time), and the agent session summaries (role, outcome, cost, sessionId). sessions lists every session of the run's role on the mission; runSessionId names this run's own, so read its log and cost from that one.

  Paramètres, retour & exemple (1)

  Paramètres

  • sandboxId · string · requis
    Agent run id: the run's sandbox id, from list_agent_runs

  Exemple d'appel

  {"name": "get_agent_run", "arguments": {"sandboxId": "texte"}}

  Exemple de retour

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

• get_agent_run_logs≈ 300 tokens

  Fetch a session's log content from one agent run. part=session is the agent stream-json (reasoning + tool calls); part=system is the container/runner stdout (clone, dependency install, validation gate, git, callback); part=prompt is the assembled input prompt. The role and sessionId are fields of the agent run's own record. A log longer than 40,000 characters returns its end, from a whole line, with a note.

  Paramètres, retour & exemple (4)

  Paramètres

  • part · string · optionnel · session | system | prompt
    Which log stream to read
  • role · string · requis
    Agent role: planner | builder | reviewer | qa
  • sandboxId · string · requis
    Agent run id: the run's sandbox id
  • sessionId · string · requis
    Session id from get_agent_run's sessions list

  Exemple d'appel

  {"name": "get_agent_run_logs", "arguments": {"role": "texte", "sandboxId": "texte", "sessionId": "texte"}}

  Exemple de retour

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

• get_agents_override≈ 177 tokens

  Read the per-issue agents/baseBranch override record for one mission, or null when unset.

  Paramètres, retour & exemple (2)

  Paramètres

  • issueId · string · requis
    The mission's issue id: a Linear key or a GitHub Issues id, e.g. SHIP-353 or WEB-42
  • projectId · string · requis
    Project id the mission belongs to

  Exemple d'appel

  {"name": "get_agents_override", "arguments": {"issueId": "texte", "projectId": "texte"}}

  Exemple de retour

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

• get_artifact≈ 353 tokens

  Fetch one artifact's metadata + a long-lived signed serving url (open it to view the screenshot/video).

  Paramètres, retour & exemple (1)

  Paramètres

  • id · string · requis
    Artifact id (from list_artifacts)

  Exemple d'appel

  {"name": "get_artifact", "arguments": {"id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "url": "texte", "kind": "screenshot", "role": "texte", "caption": "texte", "issueId": "texte", "createdAt": "texte", "criterion": "texte", "expiresAt": "texte", "projectId": "texte", "sandboxId": "texte", "sessionId": "texte"}}

• get_billing≈ 134 tokens

  Read the workspace's credit balance by source and expiry, whether a new mission would start now, the per-mission credit ceiling, the project allowance and recent usage. Check it before dispatching work.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_billing", "arguments": {}}

  Exemple de retour

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

• get_environment≈ 307 tokens

  Fetch one preview environment's registry row (status, worker name, timestamps).

  Paramètres, retour & exemple (1)

  Paramètres

  • environmentId · string · requis
    Environment id (from list_environments)

  Exemple d'appel

  {"name": "get_environment", "arguments": {"environmentId": "texte"}}

  Exemple de retour

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

• get_mission≈ 338 tokens

  Fetch one mission. view='summary' (the default, small enough to poll) returns its summary (activity, stage, review/check/test state, PR, paused and pauseSource, cost), its agent runs (sandboxId, role, status, harness, model, cost) and proofRunSandboxId (pass it to list_artifacts as sandboxId for the proof). view='full' adds its stages, events, stats and the plan/review/QA outcomes. pauseSource 'checkpoint:<role>' means a checkpoint holds it: resume_mission approves that stage. Requires the missions:read scope.

  Paramètres, retour & exemple (4)

  Paramètres

  • view · string · optionnel · summary | full
    summary (default) for the state, runs and proof run; full for every stage, event and outcome
  • issueId · string · requis
    The mission's issue id: a Linear key or a GitHub Issues id, e.g. SHIP-412
  • orgSlug · string · optionnel
    Narrow an issue id to one org
  • projectId · string · optionnel
    Narrow an issue id that two projects share

  Exemple d'appel

  {"name": "get_mission", "arguments": {"issueId": "texte"}}

  Exemple de retour

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

• get_notices≈ 182 tokens

  Read what needs attention in the workspace, critical first: a tracker connection its vendor no longer accepts (missions cannot start or report back until someone reconnects it), or credits running out. Each notice has a stable id and kind, a message and, when the caller can act, an action URL to hand to a person. A notice the caller dismissed is left out. Check it before dispatching work.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_notices", "arguments": {}}

  Exemple de retour

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

• get_project≈ 455 tokens

  Fetch a single project by its UUID. Returns 404 if the project is not in the caller's org.

  Paramètres, retour & exemple (1)

  Paramètres

  • projectId · string · requis
    Project UUID

  Exemple d'appel

  {"name": "get_project", "arguments": {"projectId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "name": "texte", "slug": "texte", "orgId": "texte", "status": "active", "scmRepo": "texte", "tracker": "linear", "scmOwner": "texte", "autoMerge": true, "createdAt": 1, "issueCode": "texte", "trackerTeamId": "texte"}}

• get_sandbox_build_log≈ 196 tokens

  A page of a build's log after sequence number `after`. Call again with after = nextAfter until done is true.

  Paramètres, retour & exemple (3)

  Paramètres

  • after · integer · optionnel
    Return chunks after this sequence number (default 0)
  • buildId · string · requis
    Build id (tbd_...)
  • templateId · string · requis
    Sandbox id (sbt_...)

  Exemple d'appel

  {"name": "get_sandbox_build_log", "arguments": {"buildId": "texte", "templateId": "texte"}}

  Exemple de retour

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

• get_sandbox_capacity≈ 179 tokens

  How many agents the org's missions are running at once against its limit (null while the org is unclassified), which missions wait for an agent slot and why, and whether every slot on the platform is taken. Read from the platform's once-a-minute capacity check.

  Paramètres, retour & exemple (1)

  Paramètres

  • orgId · string · optionnel
    Required only for a caller in several orgs

  Exemple d'appel

  {"name": "get_sandbox_capacity", "arguments": {"orgId": "texte"}}

  Exemple de retour

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

• get_scheduled_task≈ 193 tokens

  Fetch one scheduled task by id: its project, name, prompt, triggers (schedule), labels, template key, skip-if-previous-open setting, enabled state, and next/last run times. An id outside the caller's accessible projects returns not found. For what each fire produced, use list_scheduled_task_runs.

  Paramètres, retour & exemple (1)

  Paramètres

  • scheduledTaskId · string · requis
    Scheduled task id, e.g. from list_scheduled_tasks

  Exemple d'appel

  {"name": "get_scheduled_task", "arguments": {"scheduledTaskId": "texte"}}

  Exemple de retour

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

• get_setup_progress≈ 906 tokens

  Read what the workspace has set up with SHIP so far, as the console's setup checklist shows it: up to 13 milestones in three groups, taken in order (get started, make it yours, make it autonomous). `activeGroup` names the group to work on now, and each group carries its own count. Each milestone says whether it is reached and, when a console page takes it and the caller's role can, the page that does it. `next` names the first milestone not reached yet. Use it to suggest the next step to a person.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_setup_progress", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"next": "workspace", "orgId": "texte", "groups": [], "guides": [], "complete": true, "totalCount": 1, "activeGroup": "first_mission", "firstMission": {}, "reachedCount": 1, "activeGroupProgress": {}}}

• healthz≈ 95 tokens

  Returns the upstream API status, environment, and version.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "healthz", "arguments": {}}

  Exemple de retour

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

• inspect_mission≈ 270 tokens

  Fetch the typed platform-inspection report for a mission, by its issue id. Returns per-section KV/D1/R2 state: task state, retry reason, dispatch error, latest review + QA verdicts, run index, per-attempt provenance, running sandboxes, and session-log heads. Requires the inspect:read scope.

  Paramètres, retour & exemple (4)

  Paramètres

  • issueId · string · requis
    The mission's issue id: a Linear key or a GitHub Issues id, e.g. SHIP-199 or WEB-42
  • orgSlug · string · optionnel
    Narrow an ambiguous issue code to one org
  • sections · string · optionnel
    Comma-separated section filter (default all): taskState,retryReason,provenance,…
  • projectId · string · optionnel
    Scope to a specific project id

  Exemple d'appel

  {"name": "inspect_mission", "arguments": {"issueId": "texte"}}

  Exemple de retour

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

• list_agent_runs≈ 858 tokens

  List the agent runs, live and finished, in the caller's accessible projects, newest first. Each run is one agent in its own sandbox. Returns id (the run's sandbox id), issueId, role, harness, status, instance type, and latest CPU/memory/disk metrics. When more runs match, nextCursor is set: pass it back as cursor, with the same filters, for the next page.

  Paramètres, retour & exemple (6)

  Paramètres

  • role · string · optionnel · planner | builder | reviewer | qa
    Only the runs of this agent role
  • limit · integer · optionnel
    Max results (default 50). Narrow with projectId, issueId, role or status before raising it.
  • cursor · string · optionnel
    nextCursor from the previous page; omit for the newest runs
  • status · string · optionnel · running | stale | completed | stopped | failed
    Filter by how the run stands: running, completed (finished), stopped (ended on purpose before it finished), failed, or stale (closed without a report)
  • issueId · string · optionnel
    Only the runs of this mission, by its issue id, e.g. SHIP-412
  • projectId · string · optionnel
    Filter to one project id

  Exemple d'appel

  {"name": "list_agent_runs", "arguments": {"role": "planner", "limit": 1, "cursor": "texte", "status": "running", "issueId": "texte", "projectId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"data": [], "nextCursor": "texte"}}

• list_artifacts≈ 591 tokens

  List proof-of-work artifacts (QA screenshots/video/traces) for the caller's accessible projects. Each row carries kind, content type, caption, the acceptance criterion it proves, the sandboxId of the agent run that produced it, and a long-lived signed serving url. Filter by issueId to get one ticket's evidence: the artifacts of every run, superseded QA attempts included, up to limit; a note says when more exist. For the mission's proof of work specifically, read proofRunSandboxId from GET /v1/missions/{id} and pass it as sandboxId.

  Paramètres, retour & exemple (4)

  Paramètres

  • limit · integer · optionnel
    Max results (default 50). Narrow with issueId or sandboxId before raising it.
  • issueId · string · optionnel
    Filter to one issue (e.g. SHIP-133)
  • projectId · string · optionnel
    Filter to one project id
  • sandboxId · string · optionnel
    Filter to ONE agent run's artifacts (e.g. the mission's proofRunSandboxId)

  Exemple d'appel

  {"name": "list_artifacts", "arguments": {"limit": 1, "issueId": "texte", "projectId": "texte", "sandboxId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"data": [], "nextCursor": "texte"}}

• list_billing_ledger≈ 216 tokens

  List where the workspace's credits went, newest first: one entry per mission (its start, each further 3 agent-hours, and messages charged before messages became free), per grant, per adjustment and per expiry. Pass nextCursor back as cursor for the next page. Owners and admins only.

  Paramètres, retour & exemple (2)

  Paramètres

  • limit · integer · optionnel
    Entries per page, 1-100 (default 50).
  • cursor · string · optionnel
    nextCursor from the previous page; omit for the newest entries.

  Exemple d'appel

  {"name": "list_billing_ledger", "arguments": {"limit": 1, "cursor": "texte"}}

  Exemple de retour

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

• list_credit_offers≈ 274 tokens

  List what SHIP sells: the credit packs (credits, the price in US dollars before tax, which checkout adds for the buyer's location, and the price per credit), the monthly plans under `team.plans` (Starter and Scale: each its credits a month, monthly price, price per credit, which credits added on top also cost, and agents at once), the range of credits a workspace on a plan can add at once, Enterprise under `enterprise` (the minimum yearly credit commitment, the highest and lowest price per credit, and the agents at once at the minimum; contracts are sold by SHIP, not through checkout), what Free and the packs allow (`limits`), plus the trial size. The same catalog the pricing page shows.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_credit_offers", "arguments": {}}

  Exemple de retour

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

• list_environments≈ 428 tokens

  List per-mission preview environments for the caller's accessible projects. Returns id, issueId, projectId, prNumber, workerName, and lifecycle status.

  Paramètres, retour & exemple (4)

  Paramètres

  • limit · integer · optionnel
    Max results (default 50). Narrow with issueId, projectId or status before raising it.
  • status · string · optionnel · provisioning | active | destroying | destroyed | failed
    Filter by lifecycle status
  • issueId · string · optionnel
    Filter to one issue id
  • projectId · string · optionnel
    Filter to one project id

  Exemple d'appel

  {"name": "list_environments", "arguments": {"limit": 1, "status": "provisioning", "issueId": "texte", "projectId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"data": [], "nextCursor": "texte"}}

• list_mcp_bindings≈ 162 tokens

  Every MCP server binding across the projects you can see in your org: project, server, transport, status, enabled roles, how it authenticates, and the NAMES of the credential fields set (never values). Use it to find where a credential is used; use list_mcp_servers for one project's full detail.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_mcp_bindings", "arguments": {}}

  Exemple de retour

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

• list_mcp_servers≈ 220 tokens

  The MCP servers a project's repository declares in its MCP file (.mcp.json by default), each with its binding: enabled roles, transport, status, approved tools, per-role effective tool counts (null when the server runs inside the sandbox and the role gets every tool it exposes), and the NAMES of the credential fields set (never values). Also reports whether the file could be read (configStatus).

  Paramètres, retour & exemple (1)

  Paramètres

  • projectId · string · requis
    Project id, e.g. from list_projects

  Exemple d'appel

  {"name": "list_mcp_servers", "arguments": {"projectId": "texte"}}

  Exemple de retour

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

• list_missions≈ 368 tokens

  List missions in the caller's accessible projects, newest activity first, with total for paging. Each has issueId, title, activity (what it does now), pipelineProgress, review/check/test state, PR, cost and paused. Archived missions are left out. Requires the missions:read scope.

  Paramètres, retour & exemple (5)

  Paramètres

  • limit · integer · optionnel
    Page size (default 25). Narrow with projectId, activity or search before raising it.
  • offset · integer · optionnel
    Rows to skip, for the next page
  • search · string · optionnel
    Match the issue id, title, owner or repository
  • activity · string · optionnel · queued | planning | building | fixing_ci | addressing_review | addressing_qa | ci_running | ci_failed
    Filter by what the mission does now
  • projectId · string · optionnel
    Filter to one project id

  Exemple d'appel

  {"name": "list_missions", "arguments": {"limit": 1, "offset": 1, "search": "texte", "activity": "queued", "projectId": "texte"}}

  Exemple de retour

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

• list_orgs≈ 222 tokens

  List every organization on the platform with its owner email, member count, and pending invite status. Requires platform-admin (cross_org) access. Cursor-paginated (default page size 50) — feed the response's nextCursor back as the cursor input to reach the next page; a null nextCursor means there are no more pages.

  Paramètres, retour & exemple (2)

  Paramètres

  • limit · integer · optionnel
    Page size, 1-100 (API default 50)
  • cursor · string · optionnel
    Opaque page cursor, echoed back as nextCursor by a prior call

  Exemple d'appel

  {"name": "list_orgs", "arguments": {"limit": 1, "cursor": "texte"}}

  Exemple de retour

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

• list_projects≈ 475 tokens

  List the projects accessible to the calling principal. Returns id, slug, name, status, createdAt for each.

  Paramètres, retour & exemple (2)

  Paramètres

  • limit · integer · optionnel
    Max results (default 20)
  • cursor · string · optionnel
    Opaque pagination cursor from a previous call

  Exemple d'appel

  {"name": "list_projects", "arguments": {"limit": 1, "cursor": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"data": [], "nextCursor": "texte"}}

• list_sandbox_registries≈ 114 tokens

  The org's private package registries sandboxes install from: host, auth scheme, username. Never the secret.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_sandbox_registries", "arguments": {}}

  Exemple de retour

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

• list_sandbox_starters≈ 108 tokens

  Ready-made sandbox definitions (Python, Java, Go, Rust, Ruby) to create a sandbox from.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_sandbox_starters", "arguments": {}}

  Exemple de retour

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

• list_sandbox_template_versions≈ 141 tokens

  Every saved version of a sandbox, newest first, with the active one marked and each one's latest build.

  Paramètres, retour & exemple (1)

  Paramètres

  • templateId · string · requis
    Sandbox id (sbt_...)

  Exemple d'appel

  {"name": "list_sandbox_template_versions", "arguments": {"templateId": "texte"}}

  Exemple de retour

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

• list_sandbox_templates≈ 116 tokens

  List the org's sandboxes (definitions agents start in), with each one's active version, size and latest build status.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_sandbox_templates", "arguments": {}}

  Exemple de retour

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

• list_scheduled_task_runs≈ 273 tokens

  Run history for one scheduled task, each row's status (dispatching/dispatched/skipped/failed) and, once its issue exists, the joined mission progress/cost. A 'dispatched' status means the issue was created and the mission started — never that the work succeeded; read the joined mission state for that. Newest first; when older runs exist, pass nextCursor back as cursor for the next page.

  Paramètres, retour & exemple (3)

  Paramètres

  • limit · integer · optionnel
    Runs per page, 1-200 (default 50)
  • cursor · string · optionnel
    nextCursor from the previous page; omit for the newest runs
  • scheduledTaskId · string · requis
    Scheduled task id

  Exemple d'appel

  {"name": "list_scheduled_task_runs", "arguments": {"scheduledTaskId": "texte"}}

  Exemple de retour

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

• list_scheduled_task_templates≈ 160 tokens

  Read-only gallery of curated scheduled task templates — a prepared prompt plus a suggested cadence. A template is content, not a code path: pass its key as templateKey on create_scheduled_task for attribution, or copy its prompt/schedule into a hand-written scheduled task.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_scheduled_task_templates", "arguments": {}}

  Exemple de retour

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

• list_scheduled_tasks≈ 160 tokens

  List recurring agent missions (scheduled tasks) across the caller's accessible projects — schedule, enabled state, and next/last fire time for each. Pass projectId for the tasks of one project.

  Paramètres, retour & exemple (1)

  Paramètres

  • projectId · string · optionnel
    Only the scheduled tasks of this project

  Exemple d'appel

  {"name": "list_scheduled_tasks", "arguments": {"projectId": "texte"}}

  Exemple de retour

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

• mark_setup_step≈ 358 tokens

  Mark a step of the setup checklist completed or skipped for the person this token acts for, as the console's Mark as complete and Skip controls do; open removes the mark. Give step for one milestone, or group to mark every open step of that group (the console's Skip all). A marked step counts as done on that person's checklist and its status says how; reached stays false until SHIP sees the step done. Returns the checklist as it now stands. A token that acts for no person is refused.

  Paramètres, retour & exemple (3)

  Paramètres

  • mark · string · requis · completed | skipped | open
    open removes the caller's mark.
  • step · string · optionnel · workspace | first_mission | first_review | first_merge | preview_deployment | agent_instructions | mcp_servers | custom_sandbox
    The milestone id from get_setup_progress. Give step or group.
  • group · string · optionnel · first_mission | team | explore
    A group id: marks every open step of the group.

  Exemple d'appel

  {"name": "mark_setup_step", "arguments": {"mark": "completed"}}

  Exemple de retour

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

• merge_mission≈ 276 tokens

  Merge the mission's open pull request on GitHub with the repository's own merge method; the mission then becomes done, and the merge cannot be undone from here. When the branch is out of date with its base, answers 202 with status 'updating_branch' and a message: SHIP updates the branch and merges once CI passes, with no further call. Answers 409 with the reason for any other blocker (missing reviews, failing checks, another branch protection). On a merge conflict SHIP starts the builder to fix it and merges once the mission is ready again, with no further call. Requires the missions:write scope.

  Paramètres, retour & exemple (1)

  Paramètres

  • issueId · string · requis
    The mission's issue id: a Linear key or a GitHub Issues id, e.g. SHIP-412

  Exemple d'appel

  {"name": "merge_mission", "arguments": {"issueId": "texte"}}

  Exemple de retour

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

• pause_mission≈ 167 tokens

  Hold a mission before its next stage. The stage that runs now finishes; no agent is stopped. Use resume_mission to continue. Requires the missions:write scope and a role that can control missions.

  Paramètres, retour & exemple (1)

  Paramètres

  • issueId · string · requis
    The mission's issue id: a Linear key or a GitHub Issues id, e.g. SHIP-412

  Exemple d'appel

  {"name": "pause_mission", "arguments": {"issueId": "texte"}}

  Exemple de retour

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

• refresh_mcp_server_tools≈ 239 tokens

  Snapshot the bound server's current tools (with their readOnlyHint / destructiveHint annotations) for approval. Approvals of tools that no longer exist are dropped. The binding must be ready; a server inside the sandbox has no gateway tool list. Requires config:write.

  Paramètres, retour & exemple (2)

  Paramètres

  • projectId · string · requis
    Project id, e.g. from list_projects
  • serverName · string · requis
    Server name as the repository's MCP file declares it (see list_mcp_servers)

  Exemple d'appel

  {"name": "refresh_mcp_server_tools", "arguments": {"projectId": "texte", "serverName": "texte"}}

  Exemple de retour

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

• request_more_credits≈ 182 tokens

  Ask for more credits for the workspace, saying what they are for. Any member may ask. The answer says who has the request: SHIP for a sponsored or Enterprise workspace, its owners and admins otherwise. A message sent while a request is open joins it.

  Paramètres, retour & exemple (1)

  Paramètres

  • message · string · requis
    What the credits are for.

  Exemple d'appel

  {"name": "request_more_credits", "arguments": {"message": "texte"}}

  Exemple de retour

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

• resume_mission≈ 187 tokens

  Continue a paused mission. When a checkpoint holds it (get_mission shows pauseSource 'checkpoint:<role>'), this approves that stage's result and starts the next stage. To ask for changes to the result instead, use send_mission_instruction. Requires the missions:write scope.

  Paramètres, retour & exemple (1)

  Paramètres

  • issueId · string · requis
    The mission's issue id: a Linear key or a GitHub Issues id, e.g. SHIP-412

  Exemple d'appel

  {"name": "resume_mission", "arguments": {"issueId": "texte"}}

  Exemple de retour

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

• run_scheduled_task≈ 208 tokens

  Fire a scheduled task immediately, bypassing both its schedule and the skip-if-previous-open guard — an explicit run always creates a new issue even while a prior fire's mission is still open. Requires the pipeline:control capability and, for a token caller, the missions:run scope — the same authorization starting a mission by hand requires, because it is the same act.

  Paramètres, retour & exemple (1)

  Paramètres

  • scheduledTaskId · string · requis
    Scheduled task id to fire

  Exemple d'appel

  {"name": "run_scheduled_task", "arguments": {"scheduledTaskId": "texte"}}

  Exemple de retour

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

• save_sandbox_registry≈ 260 tokens

  Store (or replace) the credential for a registry host. The platform attaches it to sandbox requests for that host only; it never enters a sandbox and is never returned.

  Paramètres, retour & exemple (4)

  Paramètres

  • host · string · requis
    Registry host or URL, e.g. npm.pkg.github.com
  • scheme · string · requis · bearer | basic
    How the registry takes the credential: 'bearer' sends secret as a token, 'basic' sends username and secret
  • secret · string · requis
    Token or password
  • username · string · optionnel
    Required for basic

  Exemple d'appel

  {"name": "save_sandbox_registry", "arguments": {"host": "texte", "scheme": "bearer", "secret": "texte"}}

  Exemple de retour

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

• save_sandbox_template≈ 420 tokens

  Create a sandbox (omit templateId) or change one. A definition is Dockerfile steps on the platform base (RUN, ENV, ARG, WORKDIR, USER; no FROM). A changed definition or size becomes a new version and is built at once; the response carries that build. Refusals name the line or the size bound.

  Paramètres, retour & exemple (5)

  Paramètres

  • name · string · optionnel
    Required when creating
  • size · ? · optionnel
    A tier, or { vcpu, memoryMib, diskMb } within 1-4 vCPU, >=3072 MiB per vCPU, <=12288 MiB, 8000-20000 MB
  • starterId · string · optionnel
    Create from a starter's definition and size
  • dockerfile · string · optionnel
    The Dockerfile that builds the sandbox image. Give this or starterId to create; it replaces the file on an update
  • templateId · string · optionnel
    Sandbox id (sbt_...)

  Exemple d'appel

  {"name": "save_sandbox_template", "arguments": {"name": "texte", "size": "texte", "starterId": "texte", "dockerfile": "texte", "templateId": "texte"}}

  Exemple de retour

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

• send_mission_instruction≈ 366 tokens

  Tell a mission what to change. Use kind='follow_up' (the default) to ask for a change: the instruction reaches the agents AND dispatches the builder against the mission's open pull request, overriding cached review and QA verdicts. Use kind='note' to record context for whatever runs next without starting any work. A restart is a different thing: it re-evaluates an unchanged pull request against its cached verdicts, and so changes nothing. Returns a receipt saying what was recorded and what it will cause. This tool calls the SHIP API, documented at https://letsship.ai/docs/api. Requires the missions:write token scope.

  Paramètres, retour & exemple (3)

  Paramètres

  • body · string · requis
    What the agents should do. Travels verbatim into the prompt
  • kind · string · optionnel · follow_up | note
    follow_up (default) dispatches the builder; note records context and dispatches nothing
  • issueId · string · requis
    Issue id the mission is tracked under, e.g. SHIP-244 or GH-1280

  Exemple d'appel

  {"name": "send_mission_instruction", "arguments": {"body": "texte", "issueId": "texte"}}

  Exemple de retour

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

• set_agents_override≈ 1077 tokens

  Patch one role's harness/model/effort/prompt for a single mission, layered over ship.yml per-field (a role or field this call omits keeps resolving from ship.yml — SHIP-337). Use promptContent or promptPath(+promptRef) to run an ephemeral prompt experiment (spec D9) without committing to the target repo. Read-modify-write: this call is merged onto the previously stored override record (via get_agents_override), so a prior set for a DIFFERENT role — or a different field on this same role, e.g. an earlier harness pin — survives; the underlying PUT is a full-record replace and would otherwise silently drop it. This tool calls the SHIP API, documented at https://letsship.ai/docs/api.

  Paramètres, retour & exemple (15)

  Paramètres

  • role · string · requis · planner | builder | reviewer | qa
    The role this override entry patches
  • size · ? · optionnel
    Container size for this role on this mission
  • model · string · optionnel
    The model id this role uses for this mission. The harness must support it
  • effort · string · optionnel
    Reasoning effort for this role, mapped to the harness's own control at dispatch: low, medium, high or xhigh, and also max on claude-code. A value the harness does not take is refused at dispatch.
  • harness · string · optionnel · claude-code | codex | pi | kilo-code | open-code
    The code harness this role runs on for this mission
  • issueId · string · requis
    The mission's issue id: a Linear key or a GitHub Issues id, e.g. SHIP-353 or WEB-42
  • sandbox · string · optionnel
    Sandbox name or id this role starts in for this mission (beats ship.yml and the project default)
  • rejectOn · string · optionnel · critical | suggestion | trivial
    Review rejection threshold — only meaningful on the reviewer role
  • projectId · string · requis
    Project id the mission belongs to
  • promptRef · string · optionnel
    Git ref for promptPath — only meaningful alongside promptPath.
  • baseBranch · string · optionnel
    Override the pipeline's fork/target branch for this mission
  • checkpoint · boolean · optionnel
    Pause the pipeline after this role's stage completes
  • promptMode · string · optionnel · replace | extend
    How this prompt relates to the repo's own .ship/agents/<role>.md (or ship.yml-pointed) layer. replace (default) makes this the role's only role-prompt layer; extend resolves the repo's layer first and appends this content after it, as a separately attributed span. Only meaningful with promptContent or promptPath. NOTE: the merge is per FIELD, and prompt is one field — a later call that sets a new promptContent/promptPath without repeating promptMode replaces the whole stored prompt, reverting to replace.
  • promptPath · string · optionnel
    Repo-relative path to an L2 prompt file. Without promptRef this is the SHIP-347 pointer form (resolved at the pinned base branch); with promptRef it's a path+ref experiment resolved at that ref.
  • promptContent · string · optionnel
    Inline prompt-experiment body, capped at 30,000 characters. Mutually exclusive with promptPath.

  Exemple d'appel

  {"name": "set_agents_override", "arguments": {"role": "planner", "issueId": "texte", "projectId": "texte"}}

  Exemple de retour

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

• set_mcp_config_path≈ 258 tokens

  Point the project at the repository file that declares its MCP servers, e.g. .cursor/mcp.json or .vscode/mcp.json. null restores the default (.mcp.json). The file is read, never edited. When the repository's ship.yml sets mcp.config, that wins and this call is refused (409); list_mcp_servers reports which one applies as configPathSource. Requires the config:write capability.

  Paramètres, retour & exemple (2)

  Paramètres

  • projectId · string · requis
    Project id, e.g. from list_projects
  • configPath · ? · requis
    Repository-relative path, or null

  Exemple d'appel

  {"name": "set_mcp_config_path", "arguments": {"projectId": "texte", "configPath": "texte"}}

  Exemple de retour

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

• set_mission_auto_merge≈ 246 tokens

  Set whether SHIP merges this mission's pull request by itself once the checks, the review and the test pass. The setting is for this mission only and replaces the project's auto-merge for it; get_project shows the project's. While it is on, SHIP merges without asking again. Requires the missions:write scope.

  Paramètres, retour & exemple (2)

  Paramètres

  • enabled · boolean · requis
    true merges the pull request once it is ready; false leaves the merge to a person
  • issueId · string · requis
    The mission's issue id: a Linear key or a GitHub Issues id, e.g. SHIP-412

  Exemple d'appel

  {"name": "set_mission_auto_merge", "arguments": {"enabled": true, "issueId": "texte"}}

  Exemple de retour

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

• set_mission_disposition≈ 328 tokens

  Record a person's reason for how a mission ended, which the delivery statistics use: product (real work, judged on its merits), probe (a test on purpose), superseded (another mission replaced it: give supersededBy) or takeover (a person finished the work outside SHIP); null clears it. Set it only with the person's answer, never from your own guess. Requires the missions:write scope and the config:write capability.

  Paramètres, retour & exemple (3)

  Paramètres

  • issueId · string · requis
    The mission's issue id: a Linear key or a GitHub Issues id, e.g. SHIP-412
  • disposition · ? · requis
    product, probe, superseded or takeover; null clears a disposition set by mistake
  • supersededBy · string · optionnel
    The issue id of the mission that replaced this one, for disposition superseded only

  Exemple d'appel

  {"name": "set_mission_disposition", "arguments": {"issueId": "texte", "disposition": "texte"}}

  Exemple de retour

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

• start_credit_checkout≈ 526 tokens

  Opens a payment page and returns its URL. Nothing is charged until the buyer pays on that page. It sells one credit pack, a monthly plan (offer team, with teamPlan starter or scale, a subscription that renews until cancelled), or extra credits for a workspace already on a plan (offer team_credits, for quantity credits at that plan's own price per credit, paid once, expiring with the plan month). Only a workspace on a plan can use team_credits. Only owners and admins can open a page. The server refuses the request while startNow is false, and the same idempotencyKey returns the same page.

  Paramètres, retour & exemple (5)

  Paramètres

  • offer · string · requis · credit_pack_10 | credit_pack_50 | credit_pack_100 | team | team_credits
    A pack, team or team_credits, from list_credit_offers.
  • quantity · integer · optionnel
    Credits for team_credits, within the range list_credit_offers gives; omit for a pack or a plan.
  • startNow · boolean · requis
    Records the buyer's own consent to start the credits at once, during the withdrawal period, against this text: "Start my credits now, so they can be used during the 14-day withdrawal period. If I withdraw, I pay for the credits I used; I lose the right to withdraw once all the credits I am buying are used." The server refuses the request while it is false.
  • teamPlan · string · optionnel · starter | scale
    The plan to start, for offer team only: starter or scale, from list_credit_offers.
  • idempotencyKey · string · optionnel
    Reuse on retry to get the same page back.

  Exemple d'appel

  {"name": "start_credit_checkout", "arguments": {"offer": "credit_pack_10", "startNow": true}}

  Exemple de retour

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

• start_mcp_server_oauth≈ 329 tokens

  Begin the OAuth consent for a server bound as remote. Returns an authorizeUrl that a HUMAN must open in a browser signed in to the SHIP console as the same user this token acts for; the provider returns to the console, which stores the credential. The link is single-use and expires (expiresAt). An agent cannot complete the consent itself. Requires config:write.

  Paramètres, retour & exemple (4)

  Paramètres

  • scope · string · optionnel
    Requested scope; defaults to the server's own hint
  • returnTo · string · optionnel
    Console path to land on after consent, e.g. /projects/<id>
  • projectId · string · requis
    Project id, e.g. from list_projects
  • serverName · string · requis
    Server name as the repository's MCP file declares it (see list_mcp_servers)

  Exemple d'appel

  {"name": "start_mcp_server_oauth", "arguments": {"projectId": "texte", "serverName": "texte"}}

  Exemple de retour

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

• start_mission≈ 594 tokens

  Hand a mission off to the AI agent team. Omit startAt for the default full run (planner first); pass startAt='builder' with a plan to skip straight to coding; pass startAt='reviewer' or startAt='qa' with an existing prNumber to hand off an existing build. Requires the missions:run token scope.

  Paramètres, retour & exemple (6)

  Paramètres

  • plan · string · optionnel
    Hand-off plan markdown, for startAt='builder'
  • agents · object · optionnel
    Per-role harness/model override for THIS mission only; overrides ship.yml without changing it
  • issueId · string · requis
    The mission's issue id: a Linear key or a GitHub Issues id, e.g. SHIP-244 or WEB-42
  • startAt · string · optionnel · builder | reviewer | qa
    Pipeline stage to enter at; omit for the default full run starting at the planner
  • prNumber · integer · optionnel
    Existing open PR number, required for startAt='reviewer' or startAt='qa'
  • projectId · string · requis
    Project id the mission belongs to

  Exemple d'appel

  {"name": "start_mission", "arguments": {"issueId": "texte", "projectId": "texte"}}

  Exemple de retour

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

• stop_agent_run≈ 188 tokens

  Stop the agent in one run before it finishes. Its work in progress is lost, and the run's status becomes stopped a few seconds later. Needs an org admin and the sandboxes:stop scope. This stops one agent run, not the mission: to stop the whole mission, use POST /v1/missions/{issueId}/stop.

  Paramètres, retour & exemple (1)

  Paramètres

  • sandboxId · string · requis
    Agent run id: the run's sandbox id, from list_agent_runs

  Exemple d'appel

  {"name": "stop_agent_run", "arguments": {"sandboxId": "texte"}}

  Exemple de retour

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

• stop_mission≈ 176 tokens

  Hard-stop a mission: every agent run of it stops and its work in progress is lost. The pull request stays open, and start_mission starts the mission again. To stop one agent run only, use stop_agent_run. Requires the missions:write scope.

  Paramètres, retour & exemple (1)

  Paramètres

  • issueId · string · requis
    The mission's issue id: a Linear key or a GitHub Issues id, e.g. SHIP-412

  Exemple d'appel

  {"name": "stop_mission", "arguments": {"issueId": "texte"}}

  Exemple de retour

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

• unarchive_mission≈ 154 tokens

  Show an archived mission in list_missions and on the board again. Requires the missions:write scope and the config:write capability.

  Paramètres, retour & exemple (1)

  Paramètres

  • issueId · string · requis
    The mission's issue id: a Linear key or a GitHub Issues id, e.g. SHIP-412

  Exemple d'appel

  {"name": "unarchive_mission", "arguments": {"issueId": "texte"}}

  Exemple de retour

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

• unbind_mcp_server≈ 215 tokens

  Delete a binding and its stored credential: no role receives the server from its next run. The repository's MCP file is not changed, so the server can be bound again. Requires config:write.

  Paramètres, retour & exemple (2)

  Paramètres

  • projectId · string · requis
    Project id, e.g. from list_projects
  • serverName · string · requis
    Server name as the repository's MCP file declares it (see list_mcp_servers)

  Exemple d'appel

  {"name": "unbind_mcp_server", "arguments": {"projectId": "texte", "serverName": "texte"}}

  Exemple de retour

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

• update_project≈ 508 tokens

  Change the settings of one project; a field you leave out keeps its value. status paused or archived stops new missions in the project, and active starts them again. autoMerge sets whether SHIP merges a ready pull request by itself. defaultSandboxTemplateId sets the sandbox the agents start in (null for the platform base). repoFullName and linearTeamKey connect the project to another repository or Linear team through the organization's existing connections. Change only what a person asked for. Answers the project as it now stands. Requires the projects:admin scope and the config:write capability.

  Paramètres, retour & exemple (8)

  Paramètres

  • name · string · optionnel
    A new name
  • status · string · optionnel · active | paused | archived
    active, paused or archived
  • autoMerge · boolean · optionnel
    true merges a ready pull request without a person
  • issueCode · string · optionnel
    A GitHub Issues project's issue id prefix, 2-5 characters; only new ids use it
  • projectId · string · requis
    Project id, from list_projects
  • repoFullName · string · optionnel
    owner/repo of the repository to connect, through the organization's GitHub connection
  • linearTeamKey · string · optionnel
    The key of the Linear team to connect, e.g. ENG
  • defaultSandboxTemplateId · ? · optionnel
    A sandbox id (sbt_...) from list_sandbox_templates, or null for the platform base

  Exemple d'appel

  {"name": "update_project", "arguments": {"projectId": "texte"}}

  Exemple de retour

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

• update_scheduled_task≈ 639 tokens

  Patch a scheduled task's name, prompt, schedule, skip-guard, or enabled state — only the fields passed are changed. To change the schedule, set interval/time/timezone together (plus weekday or dayOfMonth as the interval requires). This tool calls the SHIP API, documented at https://letsship.ai/docs/api. Requires the config:write capability.

  Paramètres, retour & exemple (11)

  Paramètres

  • name · string · optionnel
    Scheduled task name, shown in the console and used in the issue title
  • time · string · optionnel
    24-hour wall-clock time in `timezone`, e.g. '09:00'.
  • labels · array · optionnel
    Tracker label names put on every issue this scheduled task files (replaces the list; [] clears it). The label must ALREADY exist in the project's tracker team — the platform attaches labels but cannot create them, so a name the workspace does not have is dropped.
  • prompt · string · optionnel
    Replaces the issue description verbatim
  • enabled · boolean · optionnel
    Set false to pause the schedule without deleting the scheduled task
  • weekday · string · optionnel · monday | tuesday | wednesday | thursday | friday | saturday | sunday
    Day of week — required when interval is 'weekly'.
  • interval · string · optionnel · daily | weekly | monthly
    Fire cadence. 'weekly' requires weekday; 'monthly' requires dayOfMonth.
  • timezone · string · optionnel
    IANA timezone id, e.g. 'Europe/Amsterdam'.
  • dayOfMonth · integer · optionnel
    Day of month, 1-28 — required when interval is 'monthly' (capped at 28 so every month has the day).
  • scheduledTaskId · string · requis
    Scheduled task id to update
  • skipIfPreviousOpen · boolean · optionnel
    Skip a scheduled fire while the previous fire's mission is still open (default true — the guardrail is opt-out, not opt-in)

  Exemple d'appel

  {"name": "update_scheduled_task", "arguments": {"scheduledTaskId": "texte"}}

  Exemple de retour

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

• update_team_subscription≈ 279 tokens

  Change the workspace's monthly plan subscription: plan switches between starter and scale from the next renewal on (nothing is charged or refunded for the current month; passing the current plan drops a waiting switch), or cancelAtPeriodEnd true ends it when the month already paid for ends, false resumes it before then. Pass at least one. Owners and admins only. The answer is the subscription as it now stands, with any waiting switch under nextPlan.

  Paramètres, retour & exemple (2)

  Paramètres

  • plan · string · optionnel · starter | scale
    The plan from the next renewal on: starter or scale, from list_credit_offers.
  • cancelAtPeriodEnd · boolean · optionnel
    true ends the subscription at the end of the paid month; false resumes it.

  Exemple d'appel

  {"name": "update_team_subscription", "arguments": {"plan": "starter", "cancelAtPeriodEnd": true}}

  Exemple de retour

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

• watch_agent_run≈ 803 tokens

  Wait on one agent run and follow what its agent does, instead of polling get_agent_run. The call returns when the run ends, when its mission moves to another stage, or after maxSeconds. While it waits, each agent event (a thought, a tool call, a plan update, an error) is sent as a progress notification when the request has a progress token. The result has the status of the run, the stage of its mission, ended, the reason it returned, the last 20 events and a cursor. When the run is still running, call it again with since set to the cursor. A run that already ended returns at once. If your client ends a call after 60 seconds, set maxSeconds below that.

  Paramètres, retour & exemple (3)

  Paramètres

  • since · integer · optionnel
    The cursor from an earlier result. Only the events after it are sent
  • sandboxId · string · requis
    Agent run id: the run's sandbox id, from list_agent_runs or get_mission
  • maxSeconds · integer · optionnel
    The longest time to wait, in seconds (default 300, at most 600)

  Exemple d'appel

  {"name": "watch_agent_run", "arguments": {"sandboxId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"hint": "texte", "ended": true, "stage": "texte", "cursor": "texte", "events": [], "reason": "run_ended", "status": "running", "sandboxId": "texte"}}

• whoami≈ 410 tokens

  Returns the caller's identity, org, role, role-derived RBAC capabilities, and token scopes. Use this to check whether the current token may perform an action (e.g. config:write) before attempting it.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "whoami", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"role": "owner", "orgId": "texte", "scopes": [], "userId": "texte", "projectId": "texte", "capabilities": [], "principalType": "cookie"}}

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://mcp.letsship.ai/mcp