co.crevio/crevio

Est-ce que co.crevio/crevio est sûr ?

Au dernier audit MCP Hub, le serveur MCP « co.crevio/crevio » 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 18 outils

• ask_crevio≈ 894 tokens

  Delegate a job to the Crevio agent and wait for the result. The agent works your account through the Crevio API and every connected integration (products, customers, orders, email, socials, sites, research) and replies in `result`. Each job is a full agent run that takes from half a minute to several minutes, so use it for work that needs judgement or writing. If the run is still going when the wait ends, the reply has wait_timed_out: true — then call wait_for_run with its id and never call ask_crevio again, which would do the job twice. Run ids do not expire, and only the user who started a run can read it.

  Paramètres, retour & exemple (5)

  Paramètres

  • speed · string · optionnel · faster | smarter
    faster thinks less, for simple jobs where latency matters more than depth; smarter (default) thinks it through.
  • message · string · requis
    What you want done, in natural language, with all the context needed — the agent does not see your conversation.
  • approval_mode · string · optionnel · autonomous | supervised | read_only
    autonomous (default) acts without review; supervised pauses in needs_input for your approval before each gated write (pending_approval_ids) and otherwise finishes with its proposal; read_only forbids writes.
  • idempotency_key · string · optionnel
    Always pass one, unique to this request. Retrying with the same key within an hour returns the run the first call started instead of doing the job twice.
  • timeout_seconds · integer · optionnel
    How long to wait for the run to finish before returning. Defaults to, and is capped at, 300 s when your client accepts a streamed reply (text/event-stream), 90 s otherwise. The run keeps going when the wait ends first.

  Exemple d'appel

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

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "object": "texte", "result": "texte", "reused": true, "status": "pending", "chat_id": "texte", "summary": "texte", "task_id": "texte", "next_step": "texte", "task_name": "texte", "created_at": "texte", "started_at": "texte"}}

• cancel_run≈ 520 tokens

  Stop a run that is pending, running, or waiting for input, and its media generations still in flight. A run mid-step finishes that step first: it returns with cancel_requested_at set and settles as cancelled moments later (wait_for_run to confirm). Repeating it is harmless.

  Paramètres, retour & exemple (1)

  Paramètres

  • run_id · string · requis
    A run id (trun_...).

  Exemple d'appel

  {"name": "cancel_run", "arguments": {"run_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "object": "texte", "result": "texte", "reused": true, "status": "pending", "chat_id": "texte", "summary": "texte", "task_id": "texte", "next_step": "texte", "task_name": "texte", "created_at": "texte", "started_at": "texte"}}

• cancel_script_run≈ 470 tokens

  Cancel a script run that has not started yet. A running script runs to its end or its timeout.

  Paramètres, retour & exemple (1)

  Paramètres

  • run_id · string · requis
    A script run id (srun_...).

  Exemple d'appel

  {"name": "cancel_script_run", "arguments": {"run_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "calls": [], "error": "texte", "object": "texte", "output": "texte", "result": "texte", "reused": true, "status": "queued", "next_step": "texte", "created_at": "texte", "started_at": "texte", "completed_at": "texte"}}

• get_chat≈ 274 tokens

  Get a chat's title, kind, and latest run.

  Paramètres, retour & exemple (1)

  Paramètres

  • chat_id · string · requis
    A chat id (aichat_...). A run id works too — it resolves to that run's chat.

  Exemple d'appel

  {"name": "get_chat", "arguments": {"chat_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "title": "texte", "object": "texte", "created_at": "texte", "updated_at": "texte", "context_type": "general", "latest_run_id": "texte"}}

• get_run≈ 476 tokens

  Fetch a run's current status, summary, pending approvals, and (once settled) the agent's final reply.

  Paramètres, retour & exemple (1)

  Paramètres

  • run_id · string · requis
    A run id (trun_...).

  Exemple d'appel

  {"name": "get_run", "arguments": {"run_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "object": "texte", "result": "texte", "reused": true, "status": "pending", "chat_id": "texte", "summary": "texte", "task_id": "texte", "next_step": "texte", "task_name": "texte", "created_at": "texte", "started_at": "texte"}}

• get_script_run≈ 462 tokens

  Read a script run's status, and its result once it has finished.

  Paramètres, retour & exemple (1)

  Paramètres

  • run_id · string · requis
    A script run id (srun_...).

  Exemple d'appel

  {"name": "get_script_run", "arguments": {"run_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "calls": [], "error": "texte", "object": "texte", "output": "texte", "result": "texte", "reused": true, "status": "queued", "next_step": "texte", "created_at": "texte", "started_at": "texte", "completed_at": "texte"}}

• list_chats≈ 402 tokens

  List the account's chats, newest first.

  Paramètres, retour & exemple (4)

  Paramètres

  • limit · integer · optionnel
    Default 20.
  • search · string · optionnel
    Only chats whose title matches.
  • ending_before · string · optionnel
    Return the page before this id — the first id from the previous page.
  • starting_after · string · optionnel
    Return the page after this id — the last id from the previous page.

  Exemple d'appel

  {"name": "list_chats", "arguments": {"limit": 1, "search": "texte", "ending_before": "texte", "starting_after": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"data": [], "object": "texte", "has_more": true}}

• list_integration_tools≈ 533 tokens

  List one namespace's functions — the name a script calls, its parameters, whether it only reads, whether it needs approval, and a snippet run_script accepts. crevioApi has hundreds of operations: narrow it with `search`.

  Paramètres, retour & exemple (4)

  Paramètres

  • limit · integer · optionnel
    Default 10.
  • offset · integer · optionnel
    Skip this many matches — the count already seen.
  • search · string · optionnel
    Keywords, best match first — ranked over name, description and parameters, so not every word has to match.
  • namespace · string · requis
    A namespace from list_integrations, e.g. crevioApi or pdGmail.

  Exemple d'appel

  {"name": "list_integration_tools", "arguments": {"namespace": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"data": [], "object": "texte", "has_more": true}}

• list_integrations≈ 424 tokens

  List what a script can call: the Crevio API (crevioApi), Crevio's own tools (platform), and every integration you can use, each as a namespace under `tools`, plus the account's other connected apps and their status. Then list a namespace's functions with list_integration_tools.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_integrations", "arguments": {}}

  Exemple de retour

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

• list_messages≈ 374 tokens

  Read a chat's messages, oldest first. Returns the most recent `limit` messages; page back through older ones with starting_after.

  Paramètres, retour & exemple (3)

  Paramètres

  • limit · integer · optionnel
    Default 50.
  • chat_id · string · requis
    A chat id (aichat_...). A run id works too — it resolves to that run's chat.
  • ending_before · string · optionnel
    Return the messages older than this id — the first id of the previous page. Paging walks backwards through history, since the default page is the tail.

  Exemple d'appel

  {"name": "list_messages", "arguments": {"chat_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"data": [], "object": "texte", "has_more": true}}

• list_runs≈ 672 tokens

  List the account's task runs, newest first — delegated jobs and scheduled tasks alike. Filter by status or task.

  Paramètres, retour & exemple (5)

  Paramètres

  • limit · integer · optionnel
    Default 20.
  • status · string · optionnel · pending | running | completed | failed | needs_input | timed_out | unknown | skipped
    Only runs in this state.
  • task_id · string · optionnel
    Only runs of this task (task_...).
  • ending_before · string · optionnel
    Return the page before this id — the first id from the previous page.
  • starting_after · string · optionnel
    Return the page after this id — the last id from the previous page.

  Exemple d'appel

  {"name": "list_runs", "arguments": {"limit": 1, "status": "pending", "task_id": "texte", "ending_before": "texte", "starting_after": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"data": [], "object": "texte", "has_more": true}}

• resolve_approvals≈ 632 tokens

  Approve or deny the integration actions a run is paused on (status needs_input with pending_approval_ids). Submit a decision for every pending id at once; the run resumes in the background.

  Paramètres, retour & exemple (2)

  Paramètres

  • run_id · string · requis
    A run id (trun_...).
  • approvals · array · requis
    One decision per pending approval id — the run stays paused until every one is answered.

  Exemple d'appel

  {"name": "resolve_approvals", "arguments": {"run_id": "texte", "approvals": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "object": "texte", "result": "texte", "reused": true, "status": "pending", "chat_id": "texte", "summary": "texte", "task_id": "texte", "next_step": "texte", "task_name": "texte", "created_at": "texte", "started_at": "texte"}}

• run_script≈ 809 tokens

  Run JavaScript on the account's computer with bun — no agent turn — and wait for its result. `tools.<namespace>.<function>(args)` calls anything list_integration_tools shows (every call returns its result and throws on failure; top-level await works), and the script's last expression is its result. Chain calls and transform data in one run, e.g. `const { data } = await tools.crevioApi.listOrders({ status: "succeeded" }); data.length`. Runs as you, and only for account admins. If the wait ends first the reply has wait_timed_out: true and the run id: continue with wait_for_script_run — calling run_script again runs it twice unless you reuse the idempotency_key. Run ids do not expire, and only the user who started a run can read it. At most 4 runs in flight per user.

  Paramètres, retour & exemple (4)

  Paramètres

  • code · string · requis
    The JavaScript to run.
  • wait_seconds · integer · optionnel
    How long to wait for the script to finish before returning. Defaults to, and is capped at, 300 s when your client accepts a streamed reply (text/event-stream), 90 s otherwise. The script keeps going when the wait ends first.
  • idempotency_key · string · optionnel
    Always pass one, unique to this request. Retrying with the same key within an hour returns the run the first call started instead of doing the job twice.
  • timeout_seconds · integer · optionnel
    How long the script may run (default 300).

  Exemple d'appel

  {"name": "run_script", "arguments": {"code": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "calls": [], "error": "texte", "object": "texte", "output": "texte", "result": "texte", "reused": true, "status": "queued", "next_step": "texte", "created_at": "texte", "started_at": "texte", "completed_at": "texte"}}

• send_message≈ 614 tokens

  Continue a chat with follow-up instructions or answers — the agent keeps its context. Resumes a run waiting in needs_input, or queues a new run when the last one finished. Returns run_busy while a run is still in progress. Optionally waits for the reply.

  Paramètres, retour & exemple (3)

  Paramètres

  • chat_id · string · requis
    A chat id (aichat_...). A run id works too — it resolves to that run's chat.
  • message · string · requis
    The follow-up to send into the conversation.
  • timeout_seconds · integer · optionnel
    Seconds to wait for the reply before returning (default 0: return the new run immediately). Capped like ask_crevio's wait.

  Exemple d'appel

  {"name": "send_message", "arguments": {"chat_id": "texte", "message": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "object": "texte", "result": "texte", "reused": true, "status": "pending", "chat_id": "texte", "summary": "texte", "task_id": "texte", "next_step": "texte", "task_name": "texte", "created_at": "texte", "started_at": "texte"}}

• start_chat≈ 716 tokens

  Open a chat with the Crevio agent and queue a run, without waiting. Returns the run immediately — its `chat_id` is the conversation to continue with send_message. Follow the run with wait_for_run or get_run.

  Paramètres, retour & exemple (4)

  Paramètres

  • speed · string · optionnel · faster | smarter
    faster thinks less, for simple jobs where latency matters more than depth; smarter (default) thinks it through.
  • message · string · requis
    What you want done, in natural language, with all the context needed — the agent does not see your conversation.
  • approval_mode · string · optionnel · autonomous | supervised | read_only
    autonomous (default) acts without review; supervised pauses in needs_input for your approval before each gated write (pending_approval_ids) and otherwise finishes with its proposal; read_only forbids writes.
  • idempotency_key · string · optionnel
    Always pass one, unique to this request. Retrying with the same key within an hour returns the run the first call started instead of doing the job twice.

  Exemple d'appel

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

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "object": "texte", "result": "texte", "reused": true, "status": "pending", "chat_id": "texte", "summary": "texte", "task_id": "texte", "next_step": "texte", "task_name": "texte", "created_at": "texte", "started_at": "texte"}}

• wait_for_run≈ 584 tokens

  Wait for a run to settle (completed, failed, cancelled, or needs_input) and return it with the agent's final reply. If it is still running when the wait ends, the reply has wait_timed_out: true — call wait_for_run again.

  Paramètres, retour & exemple (2)

  Paramètres

  • run_id · string · requis
    A run id (trun_...).
  • timeout_seconds · integer · optionnel
    How long to wait for the run to finish before returning. Defaults to, and is capped at, 300 s when your client accepts a streamed reply (text/event-stream), 90 s otherwise. The run keeps going when the wait ends first.

  Exemple d'appel

  {"name": "wait_for_run", "arguments": {"run_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "object": "texte", "result": "texte", "reused": true, "status": "pending", "chat_id": "texte", "summary": "texte", "task_id": "texte", "next_step": "texte", "task_name": "texte", "created_at": "texte", "started_at": "texte"}}

• wait_for_script_run≈ 561 tokens

  Wait for a script run to finish and return its result. If it is still running when the wait ends, the reply has wait_timed_out: true — call again.

  Paramètres, retour & exemple (2)

  Paramètres

  • run_id · string · requis
    A script run id (srun_...).
  • wait_seconds · integer · optionnel
    How long to wait for the script to finish before returning. Defaults to, and is capped at, 300 s when your client accepts a streamed reply (text/event-stream), 90 s otherwise. The script keeps going when the wait ends first.

  Exemple d'appel

  {"name": "wait_for_script_run", "arguments": {"run_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "calls": [], "error": "texte", "object": "texte", "output": "texte", "result": "texte", "reused": true, "status": "queued", "next_step": "texte", "created_at": "texte", "started_at": "texte", "completed_at": "texte"}}

• whoami≈ 581 tokens

  Identify the account, user, and credential behind this connection, with plan, credit balance, rate limits, and the tools available. Only needed to troubleshoot the connection or check credits and limits — other tools already act on this account.

  Paramètres, retour & exemple (0)

  Exemple d'appel

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

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"plan": "texte", "user": {}, "tools": [], "limits": {}, "object": "texte", "account": {}, "credits": 1, "credential": {}, "rate_limit": {}}}

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.crevio.co/mcp