Skip to content

Crevio MCP server

co.crevio/creviocrevio.costreamable-httpv2.0.1Scanned

Delegate to an AI agent that runs your small business, or script the Crevio API and 3,000+ apps.

20 tools: 7 can delete or cancel things and 13 only read.

Tools: 7 delete, 0 irreversible, 0 write, 13 read.
  • Reads private data · 5
  • Reads text others write · 11
  • Can send data out · 1
  • 3 findings

Sign-in required, OAuth metadata published. Remote posture

With Anlyon

7 tools here can delete or cancel things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the Crevio MCP server can do

The Crevio MCP server is published by crevio.co, a domain the MCP Registry verified. It has 20 tools. It can delete or cancel things (7 tools: run_script, cancel_script_run, ask_crevio, start_chat and 3 more). 13 tools only read.

5 tools read private data (whoami, list_chats, get_chat and 2 more); 11 tools bring in text other people can write (run_script, ask_crevio, start_chat and 8 more); 1 tool can send data out of your system (send_message). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

The fixed checks matched 3 findings (credentials-mention and annotation-conflict). Each one comes with the text it matched.

Its remote endpoint asks for sign-in and publishes OAuth metadata, and its tools changed once since Anlyon Radar first saw them.

Last scanned Oct 27, 2026, version 2.0.1.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

20 tools

Deletes or cancels 7Claude Code: deny
  • ask_crevioDelegate a job to the Crevio agent and wait for the result.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: true
    • readOnlyHint: false
  • cancel_runStop a run that is pending, running, or waiting for input, and its media generations still in flight.No findings

    Why it is in this group

    • The name "cancel_run" says "cancel": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    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.

    Annotations the server declares

    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: false
  • cancel_script_runCancel a script run that has not started yet.No findings

    Why it is in this group

    • The name "cancel_script_run" says "cancel": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Cancel a script run that has not started yet. A running script runs to its end or its timeout.

    Annotations the server declares

    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: false
  • resolve_approvalsApprove or deny the integration actions a run is paused on (status needs_input with pending_approval_ids).Reads text others write1 finding

    Why it is in this group

    • The name "resolve_approvals" says "resolve": a word for reading.
    • The description's first verb is "approve": a word for a change.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Warn

      The server marks "resolve_approvals" destructive (destructiveHint: true), and its name says "resolve", a word for reading.

      Matched text

      annotations: {"readOnlyHint":false,"destructiveHint":true,"idempotentHint":false,"openWorldHint":true}; The name "resolve_approvals" says "resolve": a word for reading.

      What this check looks for
    Description, as the server wrote it
    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.

    Annotations the server declares

    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: true
    • readOnlyHint: false
  • run_scriptRun JavaScript on the account's computer with bun — no agent turn — and wait for its result.Reads text others writeNo findings

    Why it is in this group

    • The name "run_script" says "run": a word for a change.
    • The input takes a statement or command to run (input.code), which can change anything it can reach.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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. `args` reach the script as the global `args` (and process.argv). Files the script writes into the directory named by the global `outputDir` (20 at most, 50 MB each) come back as `artifacts`; get a download link with get_file_download_url.

    Annotations the server declares

    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: true
    • readOnlyHint: false
  • send_messageContinue a chat with follow-up instructions or answers — the agent keeps its context.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "send_message" says "send": a word for sending, and what is sent cannot be taken back.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe name "send_message" says "send": it sends or publishes something to other people.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: true
    • readOnlyHint: false
  • start_chatOpen a chat with the Crevio agent and queue a run, without waiting.Reads text others writeNo findings

    Why it is in this group

    • The name "start_chat" says "start": a word for a change.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: true
    • readOnlyHint: false
Only reads 13Show 13 read-only tools
  • get_chatGet a chat's title, kind, and latest run.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "get_chat" says "get": a word for reading.

    What it can reach

    • private-dataThe name "get_chat" says "get" and "chat": it reads messages.
    • private-dataThe description's first sentence says "get" and "chat": it reads messages.
    • untrusted-inputThe name "get_chat" says "get" and "chat": it reads messages, which other people can write.
    • untrusted-inputThe description's first sentence says "get" and "chat": it reads messages, which other people can write.
    Description, as the server wrote it
    Get a chat's title, kind, and latest run.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
  • get_file_download_urlExchange an artifact id (art_...) from a run's or script run's `artifacts` for a download link.Reads private dataReads text others write1 finding

    Why it is in this group

    • The name "get_file_download_url" says "get": a word for reading.

    What it can reach

    • private-dataThe name "get_file_download_url" says "get" and "file": it reads files.
    • private-dataThe input names a file (input.file_id), and the tool reads: it reads files.
    • untrusted-inputThe name "get_file_download_url" says "get" and "url": it reads web pages, which anyone can write.

    Findings

    • Info

      The description mentions "credentials".

      Matched text

      description: "...for a download link. The link needs no credentials and expires after 15 minutes; ask again..."

      What this check looks for
    Description, as the server wrote it
    Exchange an artifact id (art_...) from a run's or script run's `artifacts` for a download link. The link needs no credentials and expires after 15 minutes; ask again for a fresh one.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
  • get_runFetch a run's current status, summary, pending approvals, and (once settled) the agent's final reply.Reads text others writeNo findings

    Why it is in this group

    • The name "get_run" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "fetch" and "reply": it reads comments, which other people can write.
    Description, as the server wrote it
    Fetch a run's current status, summary, pending approvals, and (once settled) the agent's final reply.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
  • get_script_runRead a script run's status, and its result once it has finished.No findings

    Why it is in this group

    • The name "get_script_run" says "get": a word for reading.
    Description, as the server wrote it
    Read a script run's status, and its result once it has finished.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
  • list_audit_eventsList the account's audit events, newest first: access and configuration changes, approvals, API key use, and (at the full capture level) the agent's tool calls.No findings

    Why it is in this group

    • The name "list_audit_events" says "list": a word for reading.
    Description, as the server wrote it
    List the account's audit events, newest first: access and configuration changes, approvals, API key use, and (at the full capture level) the agent's tool calls.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
  • list_chatsList the account's chats, newest first.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "list_chats" says "list": a word for reading.

    What it can reach

    • private-dataThe name "list_chats" says "list" and "chat": it reads messages.
    • private-dataThe description's first sentence says "list" and "chat": it reads messages.
    • untrusted-inputThe name "list_chats" says "list" and "chat": it reads messages, which other people can write.
    • untrusted-inputThe description's first sentence says "list" and "chat": it reads messages, which other people can write.
    Description, as the server wrote it
    List the account's chats, newest first.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
  • list_integration_toolsList 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.No findings

    Why it is in this group

    • The name "list_integration_tools" says "list": a word for reading.
    Description, as the server wrote it
    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`.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
  • list_integrationsList 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 oth…No findings

    Why it is in this group

    • The name "list_integrations" says "list": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
  • list_messagesRead a chat's messages, oldest first.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "list_messages" says "list": a word for reading.

    What it can reach

    • private-dataThe name "list_messages" says "list" and "message": it reads messages.
    • private-dataThe description's first sentence says "read" and "chat": it reads messages.
    • untrusted-inputThe name "list_messages" says "list" and "message": it reads messages, which other people can write.
    • untrusted-inputThe description's first sentence says "read" and "chat": it reads messages, which other people can write.
    Description, as the server wrote it
    Read a chat's messages, oldest first. Returns the most recent `limit` messages; page back through older ones with starting_after.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
  • list_runsList the account's task runs, newest first — delegated jobs and scheduled tasks alike.No findings

    Why it is in this group

    • The name "list_runs" says "list": a word for reading.
    Description, as the server wrote it
    List the account's task runs, newest first — delegated jobs and scheduled tasks alike. Filter by status, task, or chat.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
  • wait_for_runWait for a run to settle (completed, failed, cancelled, or needs_input) and return it with the agent's final reply.Reads text others writeNo findings

    Why it is in this group

    • The name "wait_for_run" says "wait": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "wait" and "reply": it reads comments, which other people can write.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
  • wait_for_script_runWait for a script run to finish and return its result.No findings

    Why it is in this group

    • The name "wait_for_script_run" says "wait": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
  • whoamiIdentify the account, user, and credential behind this connection, with plan, credit balance, rate limits, and the tools available.Reads private data1 finding

    Why it is in this group

    • The name "whoami" says "whoami": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "credential": it reads secrets.

    Findings

    • Info

      The description mentions "credential".

      Matched text

      description: "Identify the account, user, and credential behind this connection, with plan, cred..."

      What this check looks for
    Description, as the server wrote it
    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.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

55 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.

Reads private data5
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write11
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out1
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__crevio__send_message"
    ]
  }
}

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Sign-in required, OAuth metadata published

Looked at Nov 20, 2026, 18:32 UTC, unchanged since Nov 13, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
401
tools/list served without credentials
no
Tools that change things, listed without credentials
0
Protocol version
not observed
WWW-Authenticate on 401
yes
resource_metadata in WWW-Authenticate
https://mcp.crevio.co/.well-known/oauth-protected-resource/mcp
RFC 9728 protected resource metadata
https://mcp.crevio.co/.well-known/oauth-protected-resource/mcp
Authorization servers
https://crevio.co
Legacy HTTP+SSE transport
no
Dynamic client registration
yes
Client ID metadata documents
no

Posture changes

  1. Nov 13, 2026
    • HTTP status of an anonymous initialize: 200 to 401
    • tools/list served without credentials: yes to no
    • Tools that change things, listed without credentials: 7 to 0
    • Protocol version: 2025-06-18 to none
    • WWW-Authenticate on 401: not observed to yes
    • resource_metadata in WWW-Authenticate: none to https://mcp.crevio.co/.well-known/oauth-protected-resource/mcp

Findings

Matches of fixed checks, with the text they matched.

1 warn2 info
  • The server marks "resolve_approvals" destructive (destructiveHint: true), and its name says "resolve", a word for reading.

    Matched text

    annotations: {"readOnlyHint":false,"destructiveHint":true,"idempotentHint":false,"openWorldHint":true}; The name "resolve_approvals" says "resolve": a word for reading.

    What this check looks for
  • Infowhoami

    The description mentions "credential".

    Matched text

    description: "Identify the account, user, and credential behind this connection, with plan, cred..."

    What this check looks for
  • The description mentions "credentials".

    Matched text

    description: "...for a download link. The link needs no credentials and expires after 15 minutes; ask again..."

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. PostureRemote posture changed. HTTP status of an anonymous initialize: 200 -> 401; tools/list served without credentials: yes -> no; Tools that change things, listed without credentials: 7 -> 0 (and 3 more).View diff
    • HTTP status of an anonymous initialize: 200 to 401
    • tools/list served without credentials: yes to no
    • Tools that change things, listed without credentials: 7 to 0
    • Protocol version: 2025-06-18 to none
    • WWW-Authenticate on 401: not observed to yes
    • resource_metadata in WWW-Authenticate: none to https://mcp.crevio.co/.well-known/oauth-protected-resource/mcp
  2. Tools2 added, 5 changed.+2 added~5 changedView diff

Install

Pinned to version 2.0.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http crevio https://mcp.crevio.co/mcp
claude mcp add --transport http crevio https://mcp.crevio.co/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__crevio__whoami",
      "mcp__crevio__list_integrations",
      "mcp__crevio__list_integration_tools",
      "mcp__crevio__wait_for_script_run",
      "mcp__crevio__get_script_run",
      "mcp__crevio__list_chats",
      "mcp__crevio__get_chat",
      "mcp__crevio__list_messages",
      "mcp__crevio__wait_for_run",
      "mcp__crevio__get_run",
      "mcp__crevio__list_runs",
      "mcp__crevio__get_file_download_url",
      "mcp__crevio__list_audit_events"
    ],
    "ask": [],
    "deny": [
      "mcp__crevio__run_script",
      "mcp__crevio__cancel_script_run",
      "mcp__crevio__ask_crevio",
      "mcp__crevio__start_chat",
      "mcp__crevio__send_message",
      "mcp__crevio__resolve_approvals",
      "mcp__crevio__cancel_run"
    ]
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as crevio. Review it before you use it.

Capability tags behind 12 rules
  • mcp__crevio__whoami private-data
  • mcp__crevio__run_script untrusted-input
  • mcp__crevio__ask_crevio untrusted-input
  • mcp__crevio__start_chat untrusted-input
  • mcp__crevio__list_chats private-data, untrusted-input
  • mcp__crevio__get_chat private-data, untrusted-input
  • mcp__crevio__send_message untrusted-input, outbound
  • mcp__crevio__list_messages private-data, untrusted-input
  • mcp__crevio__wait_for_run untrusted-input
  • mcp__crevio__get_run untrusted-input
  • mcp__crevio__resolve_approvals untrusted-input
  • mcp__crevio__get_file_download_url private-data, untrusted-input

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/co.crevio/crevio/verify?hash=fa8e9eebe391ac78dcaad20d08c5b80f7d1ab9367b759d7b70dfaef0ba5c8ba1" | jq -e '.changed == false'

Pinned hash fa8e9eebe391, from Oct 27, 2026, 22:17 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/co.crevio/crevio/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for co.crevio/crevio
[![Anlyon Radar](https://radar.anlyon.com/badge/co.crevio/crevio.svg)](https://radar.anlyon.com/servers/co.crevio/crevio)

Source: MCP Registry · repository. Synced Oct 27, 2026, 22:17 UTC.

Crevio MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Crevio MCP server safe?

No scan can promise that. What its definitions show: 20 tools, 7 of which can change, send or delete something, and 3 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Crevio MCP server delete data?

Yes. 7 tools can delete, cancel or revoke something: run_script, cancel_script_run, ask_crevio, start_chat, send_message, resolve_approvals and 1 more.

Can the Crevio MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the Crevio MCP server have?

20 tools: 7 destructive, 13 read. run_script, cancel_script_run, ask_crevio, start_chat, send_message, resolve_approvals, cancel_run, whoami and 12 more.

Does the Crevio MCP server need sign-in or OAuth?

Yes. Its remote endpoint answered 401 without credentials, and it publishes OAuth protected resource metadata (RFC 9728); its authorization server supports dynamic client registration.

Does the Crevio MCP server send data to outside services?

1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): send_message.

Has the Crevio MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Oct 27, 2026. Every change is on this page and in its Atom feed.