ai.mcpanalytics/analytics

Est-ce que ai.mcpanalytics/analytics est sûr ?

Au dernier audit MCP Hub, le serveur MCP « ai.mcpanalytics/analytics » 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 28 outils

• about≈ 96 tokens

  Platform documentation and info: how it works, tiers, usage.

  Paramètres, retour & exemple (1)

  Paramètres

  • topic · string · requis
    Topic: platform, manual, connectors, or a docs section

  Exemple d'appel

  {"name": "about", "arguments": {"topic": "texte"}}

  Exemple de retour

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

• account_link≈ 130 tokens

  Direct link to the right account page for anything not doable in chat: billing, browser upload, report management. Hand the user the link and guide them.

  Paramètres, retour & exemple (1)

  Paramètres

  • section · string · optionnel · home | billing | upgrade | create | upload | reports
    Where to send the user

  Exemple d'appel

  {"name": "account_link", "arguments": {"section": "home"}}

  Exemple de retour

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

• adjust_estimate≈ 132 tokens

  Apply the user's layout wishes to the estimate's page through the layout agent; a new named arrangement, nothing overwritten, no number changes.

  Paramètres, retour & exemple (2)

  Paramètres

  • estimate_id · string · requis
  • instructions · string · requis
    What to change, in the user's words

  Exemple d'appel

  {"name": "adjust_estimate", "arguments": {"estimate_id": "texte", "instructions": "texte"}}

  Exemple de retour

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

• agent_advisor≈ 101 tokens

  AI help desk: which analysis fits your question, interpreting results, fixing errors. Multi-turn.

  Paramètres, retour & exemple (1)

  Paramètres

  • message · string · requis
    Your question or request

  Exemple d'appel

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

  Exemple de retour

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

• answer_now≈ 129 tokens

  A read of the data (average, count, total, highest/lowest by group, a value in a month) answered in this response, in seconds. Not a read -> immediate=false with the reason; continue with decide_path.

  Paramètres, retour & exemple (2)

  Paramètres

  • objective · string · requis
  • dataset_ref · string · requis

  Exemple d'appel

  {"name": "answer_now", "arguments": {"objective": "texte", "dataset_ref": "texte"}}

  Exemple de retour

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

• ask_library≈ 113 tokens

  Ask a question across all your delivered analyses: a synthesized answer with citations back to specific reports.

  Paramètres, retour & exemple (1)

  Paramètres

  • question · string · requis
    Plain-language question to answer from your report library

  Exemple d'appel

  {"name": "ask_library", "arguments": {"question": "texte"}}

  Exemple de retour

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

• build_status≈ 141 tokens

  Check a commissioned build in-chat: stage progress, queue position, rejection reason if the data didn't match the objective, honest ETA, report link when delivered.

  Paramètres, retour & exemple (2)

  Paramètres

  • pipeline_id · integer · optionnel
    pipeline_id from a build (modify_analysis)
  • track_token · string · optionnel
    Token from the tracking URL

  Exemple d'appel

  {"name": "build_status", "arguments": {"pipeline_id": 1, "track_token": "texte"}}

  Exemple de retour

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

• check_tool_fit≈ 130 tokens

  Before naming a library tool: does it fit THIS dataset for THIS question? Column mapping, missing required inputs, method-fit verdict, the places it delivers. Read-only.

  Paramètres, retour & exemple (3)

  Paramètres

  • objective · string · optionnel
  • tool_name · string · requis
  • dataset_ref · string · requis

  Exemple d'appel

  {"name": "check_tool_fit", "arguments": {"tool_name": "texte", "dataset_ref": "texte"}}

  Exemple de retour

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

• create_analysis≈ 410 tokens

  Commission a NEW analysis built for your question. tier is REQUIRED. The user picks. Easiest: fuzzy_request (plain language) + dataset_ref + tier. Snapshot = instant automated report (~2-10 min). JSON = a fast computed answer, numbers + method, re-runnable tool you own (~5 min). Brief = the computed answer on a one-page report: chart, numbers, method (~7 min). Deck = commissioned deep analysis, a durable re-runnable module you own (30-45 min). Failed builds are never billed.

  Paramètres, retour & exemple (7)

  Paramètres

  • tier · string · optionnel · snapshot | json | brief | deck
    snapshot = instant report (~2-10 min); json = fast computed answer (~5 min, default); brief = one-page report of the answer (~7 min); deck = commissioned re-runnable module (30-45 min)
  • notes · string · optionnel
    Optional context for the build, constraints, definitions, or preferences the analyst agents should honor
  • dataset_ref · string · optionnel
    Single-dataset URI: 'uuid://UUID:KEY'
  • datasets_refs · object · optionnel
    Multi-dataset URIs keyed by role
  • fuzzy_request · string · optionnel
    Plain-language description of the analysis you want
  • specification · object · optionnel
    Full 11-field spec (legacy path, prefer fuzzy_request)
  • column_mapping · object · optionnel
    Optional semantic-to-real column map (hint only)

  Exemple d'appel

  {"name": "create_analysis", "arguments": {"tier": "snapshot", "notes": "texte", "dataset_ref": "texte", "datasets_refs": {}, "fuzzy_request": "texte", "specification": {}}}

  Exemple de retour

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

• datasets_list≈ 136 tokens

  List and search your uploaded datasets, with fuzzy matching on name, description, and tags. Returns each dataset's uuid:// reference for use in path_resolver and path_tool_run.

  Paramètres, retour & exemple (2)

  Paramètres

  • limit · integer · optionnel
    Max results
  • search · string · optionnel
    Search by name, description, or tags

  Exemple d'appel

  {"name": "datasets_list", "arguments": {"limit": 1, "search": "texte"}}

  Exemple de retour

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

• datasets_upload≈ 241 tokens

  Get your data in. Pass `data` as an array of row objects to create the dataset immediately and get a dataset_ref ready for path_resolver; omit it to get an upload link for a file only the user can reach. Add replace_ref (uuid://ID:KEY) with data to REFRESH an existing dataset in place; schedules and tools holding that reference read the new data on their next run.

  Paramètres, retour & exemple (3)

  Paramètres

  • data · array · optionnel
    Rows as an array of flat objects, creates the dataset in one call
  • expires_in · integer · optionnel
    Token expiration in seconds
  • replace_ref · string · optionnel
    uuid://ID:KEY of an existing dataset to overwrite in place with `data` (the push/refresh mode)

  Exemple d'appel

  {"name": "datasets_upload", "arguments": {"data": [], "expires_in": 1, "replace_ref": "texte"}}

  Exemple de retour

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

• decide_path≈ 174 tokens

  Step 0 for a new question: which path answers it on this data. One record: route (reuse | answer | package | ask | none), a score with its reason for each of answer, package, ask and none, the compiled read plan when it is a read, the method family and the library's tool fit when it is a package, and the one question to ask when something is missing. Deterministic, read-only.

  Paramètres, retour & exemple (2)

  Paramètres

  • objective · string · requis
  • dataset_ref · string · requis

  Exemple d'appel

  {"name": "decide_path", "arguments": {"objective": "texte", "dataset_ref": "texte"}}

  Exemple de retour

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

• discover_tools≈ 156 tokens

  Browse the analyses you can run: the ones you commissioned plus the platform Standard Library (prebuilt tools; each result tagged source:'own' or 'standard_library'). Plain-language match; no query lists everything, your own first. Nothing fits? Commission it with path_resolver.

  Paramètres, retour & exemple (1)

  Paramètres

  • query · string · optionnel
    Plain-language search over your library + the Standard Library; omit to list everything

  Exemple d'appel

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

  Exemple de retour

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

• find_precedent≈ 140 tokens

  Before estimating: how did we answer this objective before, on this data or any data? Prior packages and library runs with their tools, mappings, bespoke module names, method and verdicts. Platform-wide, read-only.

  Paramètres, retour & exemple (3)

  Paramètres

  • k · integer · optionnel
  • objective · string · requis
  • dataset_ref · string · optionnel

  Exemple d'appel

  {"name": "find_precedent", "arguments": {"objective": "texte"}}

  Exemple de retour

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

• modify_analysis≈ 262 tokens

  Modify an EXISTING analysis into a new version: reword the question, swap the method, or add a variable. Pass tool_name + changes (plain language). Rebuilds on the analysis's own dataset by default; the original stays put. Returns pipeline tracking. Follow with build_status.

  Paramètres, retour & exemple (4)

  Paramètres

  • tier · string · optionnel · snapshot | json | brief | deck
    Optional, change the depth of the new version
  • changes · string · requis
    What to change, in plain language, e.g. 'also break it down by region' or 'use a random forest instead'
  • tool_name · string · requis
    The analysis to modify (from discover_tools or your library)
  • dataset_ref · string · optionnel
    Optional, rebuild against a different dataset ('uuid://UUID:KEY')

  Exemple d'appel

  {"name": "modify_analysis", "arguments": {"changes": "texte", "tool_name": "texte"}}

  Exemple de retour

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

• my_objects≈ 121 tokens

  List and search the objects you own across every question: the curated charts, tables and figures of each delivered package, grouped by objective.

  Paramètres, retour & exemple (3)

  Paramètres

  • limit · integer · optionnel
  • query · string · optionnel
  • include_dropped · boolean · optionnel

  Exemple d'appel

  {"name": "my_objects", "arguments": {"limit": 1, "query": "texte", "include_dropped": true}}

  Exemple de retour

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

• order_analytics_package≈ 162 tokens

  Order what the estimate promised after reviewing it: library tools that fit, a bespoke build, or both, computed on the whole dataset; one reviewed page delivered. Credits per tool run; failed runs never billed.

  Paramètres, retour & exemple (4)

  Paramètres

  • bespoke · boolean · optionnel
  • tool_names · array · optionnel
  • estimate_id · string · requis
  • layout_objective · string · optionnel

  Exemple d'appel

  {"name": "order_analytics_package", "arguments": {"estimate_id": "texte"}}

  Exemple de retour

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

• package_status≈ 90 tokens

  Read an analytics package back: status, every run under it, the report link once delivered.

  Paramètres, retour & exemple (1)

  Paramètres

  • package_id · string · requis

  Exemple d'appel

  {"name": "package_status", "arguments": {"package_id": "texte"}}

  Exemple de retour

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

• report_cards≈ 112 tokens

  Browse a delivered report's individual cards (charts, tables, insights) inline in chat.

  Paramètres, retour & exemple (1)

  Paramètres

  • processing_id · string · requis
    The report's processing id, returned by path_tool_run or build_status

  Exemple d'appel

  {"name": "report_cards", "arguments": {"processing_id": "texte"}}

  Exemple de retour

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

• reports_list≈ 130 tokens

  Your report library: every analysis delivered, with status and links. Pass semantic_query to search report content in plain language.

  Paramètres, retour & exemple (2)

  Paramètres

  • limit · integer · optionnel
    Max results
  • semantic_query · string · optionnel
    Natural-language search over your reports' content

  Exemple d'appel

  {"name": "reports_list", "arguments": {"limit": 1, "semantic_query": "texte"}}

  Exemple de retour

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

• reports_view≈ 104 tokens

  Get a shareable browser link for a report, viewable without authentication.

  Paramètres, retour & exemple (1)

  Paramètres

  • processing_id · string · requis
    Processing ID from path_tool_run / reports_list

  Exemple d'appel

  {"name": "reports_view", "arguments": {"processing_id": "texte"}}

  Exemple de retour

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

• request_estimate≈ 216 tokens

  START HERE for a new question: free, ~30 s. A rough answer over a sample plus the layout of the complete package, every place named with the question it will answer, and a page link. Then review_estimate with the user.

  Paramètres, retour & exemple (4)

  Paramètres

  • objective · string · requis
    The user's question in their own words
  • tool_names · array · optionnel
    Optional library tools, each checked with check_tool_fit
  • dataset_ref · string · requis
    'uuid://UUID:KEY'
  • layout_objective · string · optionnel
    Optional: how the page should read

  Exemple d'appel

  {"name": "request_estimate", "arguments": {"objective": "texte", "dataset_ref": "texte"}}

  Exemple de retour

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

• rerun_package≈ 115 tokens

  Run a delivered package again, on its own data or new data: the same tools, the same curated objects, the same layout, as a new package with its own link.

  Paramètres, retour & exemple (2)

  Paramètres

  • package_id · string · requis
  • dataset_ref · string · optionnel

  Exemple d'appel

  {"name": "rerun_package", "arguments": {"package_id": "texte"}}

  Exemple de retour

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

• review_estimate≈ 118 tokens

  The estimate as you review it WITH the user: the question as understood, the estimated answer (sample, marked), every place and its question, the page link, a review checklist. Before path_bespoke.

  Paramètres, retour & exemple (1)

  Paramètres

  • estimate_id · string · requis

  Exemple d'appel

  {"name": "review_estimate", "arguments": {"estimate_id": "texte"}}

  Exemple de retour

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

• run_analysis≈ 327 tokens

  Run an analysis on your data. Returns a shareable interactive report URL with statistics you can cite, re-run and share, and the method named.

  Paramètres, retour & exemple (3)

  Paramètres

  • taskList · object · requis
    Execution inputs. Call tools_schema first for the analysis-specific fields.
  • tool_name · string · requis
    Name of the analysis to run
  • estimate_id · string · optionnel
    Optional. The estimate this run answers (from an estimate page); the run's objects are then written beside the estimate's for comparison.

  Exemple d'appel

  {"name": "run_analysis", "arguments": {"taskList": {}, "tool_name": "texte"}}

  Exemple de retour

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

• schedules≈ 224 tokens

  Standing re-runs of analyses you own: action='create' (weekly/monthly against a re-runnable data reference, connector:// or an https:// link; report emailed after each run), 'list', or 'cancel'.

  Paramètres, retour & exemple (6)

  Paramètres

  • action · string · requis · create | list | cancel
    What to do
  • cadence · string · optionnel · weekly | monthly
  • tool_name · string · optionnel
    create: the analysis to schedule
  • dataset_ref · string · optionnel
    create: re-runnable reference (connector:// or https://)
  • schedule_id · integer · optionnel
    cancel: from action='list'
  • column_mapping · object · optionnel

  Exemple d'appel

  {"name": "schedules", "arguments": {"action": "create"}}

  Exemple de retour

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

• tools_schema≈ 94 tokens

  Get an analysis's parameter schema. ALWAYS call before path_tool_run.

  Paramètres, retour & exemple (1)

  Paramètres

  • tool_name · string · requis
    Name of the analysis

  Exemple d'appel

  {"name": "tools_schema", "arguments": {"tool_name": "texte"}}

  Exemple de retour

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

• warehouse≈ 155 tokens

  Query your org's data warehouse free: browse the catalog (tables with column roles + computed metrics), semantically find data, plain-language ask, or named templates. Requires warehouse enablement (business plans).

  Paramètres, retour & exemple (4)

  Paramètres

  • query · string · optionnel
  • action · string · requis · ask | query | queries | catalog | find
  • params · object · optionnel
  • question · string · optionnel

  Exemple d'appel

  {"name": "warehouse", "arguments": {"action": "ask"}}

  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.mcpanalytics.ai/mcp/api-key