QAmcp

Copied. Paste it into Claude Code, Cursor or Codex:Fetch and follow the instructions at https://qamcp.dev/setup.md to test my MCP server.

Your AI finds your server in your project, tests it with QAmcp, explains what's wrong in plain words, fixes it with your OK, and tests again. Read the instructions

SoonYour score can change any day. QAmcp Monitor tests your server every hour and emails you when it breaks.See what Monitor does →

Directory / Crevio

Crevio

Q: Is Crevio MCP server safe?

QAmcp's test on 28 Oct 2026: No hidden instructions were found in its tool descriptions. Its error messages showed no secrets or internal details. 13 of its 20 tools are labeled read-only; the others may change or send things. Overall it scored 86/100 on 28 Oct 2026. A test can only see what the server shows from outside, not what it does with your data behind the scenes. Connect servers from makers you trust.

by crevio.co · https://mcp.crevio.co/mcp

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

20 tools✓ no account neededPricing: on their site

See pricing →Visit website

86 /100

PASS · WITH NOTES

Partial: 10 of 12 checks · 28 Oct 2026

Is Crevio MCP server safe?

No hidden instructions were found in its tool descriptions.
Its error messages showed no secrets or internal details.
13 of its 20 tools are labeled read-only; the others may change or send things.
Overall it scored 86/100 on 28 Oct 2026.

A test can only see what the server shows from outside, not what it does with your data behind the scenes. Connect servers from makers you trust.

What it can do

20 tools, in the server's own words.

whoamiread-only

Identify the account, user, and credential behind this connection, with plan, credit balance, rate limits, and the tools available.

list_integrationsread-only

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`, p…

list_integration_toolsread-only

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.

run_script

Run JavaScript on the account's computer with bun — no agent turn — and wait for its result.

wait_for_script_runread-only

Wait for a script run to finish and return its result.

get_script_runread-only

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

cancel_script_run

Cancel a script run that has not started yet.

ask_crevio

Delegate a job to the Crevio agent and wait for the result.

start_chat

Open a chat with the Crevio agent and queue a run, without waiting.

list_chatsread-only

List the account's chats, newest first.

get_chatread-only

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

send_message

Continue a chat with follow-up instructions or answers — the agent keeps its context.

list_messagesread-only

Read a chat's messages, oldest first.

wait_for_runread-only

Wait for a run to settle (completed, failed, cancelled, or needs_input) and return it with the agent's final reply.

get_runread-only

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

list_runsread-only

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

resolve_approvals

Approve or deny the integration actions a run is paused on (status needs_input with pending_approval_ids).

cancel_run

Stop a run that is pending, running, or waiting for input, and its media generations still in flight.

get_file_download_urlread-only

Exchange an artifact id (art_...) from a run's or script run's `artifacts` for a download link.

list_audit_eventsread-only

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.

Test results

Safe mode: only tools labeled read-only were run. How the test works

!
Every tool is described
1 warning
- !list_audit_events: Inputs with no description: actor_type, entity_id
note
!
Follows MCP best practices (not scored yet)
1 tip (not scored)
- !The tool list is about 49 KB (roughly 12k tokens). AI apps send it with every message, so it takes that much of the AI's memory before any work starts.
note
!
Resources and prompts work
1 warning ()
- –Could not list resources: it needs sign-in
- !Listing resource templates failed: Error POSTing to endpoint: {"error":{"type":"invalid_request_error","message":"You did not provide an API key or valid OAuth token. Include…
note
✓
ConnectsConnected in 186 ms
pass
✓
Ready for the newest MCP versionUses the latest MCP version (2026-07-28)
pass
✓
Lists its toolsFound 20 tools
pass
✓
Tools are labeled safe or dangerousEvery tool has a safety label
pass
✓
No hidden instructionsNo hidden instructions found in tool descriptions
pass
✓
Fast enough
All good
- ✓Connecting took 186 ms
- ✓Listing tools took 65 ms
pass
✓
No secrets leakedChecked 32 error messages: no secrets or internal details
pass
–
Tools work with good inputs
Not tested
- –whoami: Needs you to sign in, so it was not tested (not counted against the server)
- –list_integrations: Needs you to sign in, so it was not tested (not counted against the server)
- –list_integration_tools: Needs you to sign in, so it was not tested (not counted against the server)
- –wait_for_script_run: Needs you to sign in, so it was not tested (not counted against the server)
- –get_script_run: Needs you to sign in, so it was not tested (not counted against the server)
- –list_chats: Needs you to sign in, so it was not tested (not counted against the server)
- –get_chat: Needs you to sign in, so it was not tested (not counted against the server)
- –list_messages: Needs you to sign in, so it was not tested (not counted against the server)
- and 12 more
not tested
–
Bad inputs give a clean error
Not tested
- –list_integration_tools: Needs you to sign in, so bad inputs were not tested
- –wait_for_script_run: Needs you to sign in, so bad inputs were not tested
- –get_script_run: Needs you to sign in, so bad inputs were not tested
- –list_chats: Needs you to sign in, so bad inputs were not tested
- –get_chat: Needs you to sign in, so bad inputs were not tested
- –list_messages: Needs you to sign in, so bad inputs were not tested
- –wait_for_run: Needs you to sign in, so bad inputs were not tested
- –get_run: Needs you to sign in, so bad inputs were not tested
- and 3 more
not tested
–
Tools work togetherNo safe tool returned data to start a chain from, so chains were not tested (not counted either way)
not tested

Test it yourself

Free and open source. Same checks, same score.

npx qamcp-cli https://mcp.crevio.co/mcp

Show this score on GitHub

Free for every server in the directory. Paste this into your README: the badge shows the score from our latest test.

[![QAmcp score](https://qamcp.dev/s/co-crevio-crevio.svg)](https://qamcp.dev/s/co-crevio-crevio.html)

Score over time

28 Oct 202686

One test so far. New tests will show here.

Reviews

Coming soon: reviews from people who use Crevio, signed in with GitHub, one per person. Reviews never change the score.

Is this your server? Get an alert the moment it breaks.

QAmcp Monitor (coming soon) tests it every hour and emails you when it goes down, the score drops, a tool changes or a secret leaks. You'll also be able to claim this page and get a verified owner mark. Founding price: $19/month for life for the first 50 teams.

Have a concern, or want it removed? Ask us and we'll take it off the list. How the directory works