Agent Concierge

At a glance

Runs where

On their server. What you send to it goes to them.

What you need

Nothing: it answered without a login

Tools

14 tools

Its own safety labels

6 read-only, 2 labeled as deleting or destroying, 6 labeled as changing things

Memory it takes

About 3,600 tokens of your AI's memory, just for its tool descriptions

Largest answer

About 15.5 KB in our test

Speed

Average answer in our test: 1.0 s

Tokens are an estimate: the characters in its tool names, descriptions and inputs, divided by 4. The exact number depends on your AI model. Safety labels are what the server says about itself. From our latest test, 9 Nov 2026.

Is Agent Concierge MCP server safe?

• None of the hidden-instruction wordings we know were found in its 14 tool descriptions.
• Its error messages showed no secrets or internal details.
• 6 of its 14 tools are labeled read-only; the others may change or send things.
• Overall it scored 93/100 on 9 Nov 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 this test does not check

• Its source code and packages.
• What a tool quietly does behind the scenes, such as writing a file or calling another service.
• Instructions hidden inside live tool answers. We only look for those in tool descriptions.
• Hidden instructions worded in a way our list doesn't know yet.
• Tools that could change something. Those are read, never run.

What QAmcp can and can't see · How to tell if an MCP server is safe · Hidden instructions · Prompt injection

Known security advisories

It lists no public code, so there is nothing to look up in GitHub Security Advisories or OSV.dev. QAmcp tests how a server behaves. It does not scan source code.

What it can do

14 tools, in the server's own words.

Test results

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

• !
  Ready for the newest MCP version

  1 warning

  • !Uses an older MCP version (2025-11-25). It works today, but it isn't on the July 2026 version (2026-07-28) yet.
  note
• !
  Fast enough

  1 warning

  • !search: Slowest tool: search (3.4 s): users will notice the wait
  • and 3 more
  note
• !
  Follows MCP best practices (not scored yet)

  1 tip (not scored)

  • !Very common tool names: search, call. Next to other servers' tools the AI may mix them up; a short prefix helps (like "github_search" instead of "search").
  note
• ✓
  ConnectsConnected in 1.3 s
  pass
• ✓
  Lists its toolsFound 14 tools
  pass
• ✓
  Every tool is describedAll 14 tools and their inputs are described
  pass
• ✓
  Tools are labeled safe or dangerousEvery tool has a safety label
  pass
• ✓
  No known hidden instructionsNone of the hidden-instruction wordings we know were found in tool descriptions. New wordings can get past this check.
  pass
• ✓
  Tools work with good inputs

  All good

  • ✓search: Worked (3.4 s)
  • ✓find_agents: Worked (1.4 s)
  • ✓whats_new: Answered with an error, probably because of our sample input: No saved task is available. Use chat to start or resume a conversation, or search with an explicit task. {"intent":"whats_new","suggested_r…
  • ✓credit: Answered with an error, probably because of our sample input: A valid visitor token is required for account access.
  • ✓search_workflows: Worked (606 ms)
  • ✓workflow_details: Answered with an error, probably because of our sample input: Published workflow not found. {"workflow":null,"status":"not_found","text":"Published workflow not found."}
  • –hello: Not run: labeled as changing data
  • –chat: Not run: labeled as changing data
  • and 6 more
  pass
• ✓
  Bad inputs give a clean error

  All good

  • ✓search: Refused missing required input "task" with a clear error
  • ✓search: Refused wrong type for "task" with a clear error
  • ✓find_agents: Refused missing required input "task" with a clear error
  • ✓find_agents: Refused wrong type for "task" with a clear error
  • ✓whats_new: Refused missing required input "visitor_token" with a clear error
  • ✓whats_new: Refused wrong type for "visitor_token" with a clear error
  • ✓credit: Refused missing required input "action" with a clear error
  • ✓credit: Refused wrong type for "action" with a clear error
  • and 4 more
  pass
• ✓
  No secrets leakedChecked 19 error messages: no secrets or internal details
  pass
• –
  Tools work togetherNo tool's answer could be fed into another tool, so there were no chains to test (not counted either way)
  not tested

Test it yourself

Free and open source. Same checks, same score.

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.

Score over time

• 9 Nov 202693

One test so far. New tests will show here.

Reviews

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