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

NewYour score can change any day. QAmcp Monitor keeps testing your server and emails you when it breaks. Free for 1 server.See what Monitor does →

Directory / EvalGate

EvalGate

Q: Is EvalGate MCP server safe?

QAmcp's test on 5 Nov 2026: None of the hidden-instruction wordings we know were found in its 12 tool descriptions. Its error messages showed no secrets or internal details. All 12 of its tools are labeled read-only. Overall it scored 94/100 on 5 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.

by evalgate.com · https://www.evalgate.com/api/mcp

Run AI evaluations, record agent traces and gate releases on evidence, with scoped org access.

12 tools✓ all read-only✓ no account neededPricing: on their site

See pricing →Visit website

94 /100

PASS · WITH NOTES

Partial: 10 of 12 checks · 5 Nov 2026

Test it now for current results

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: 12 tools
Its own safety labels: 12 read-only
Memory it takes: About 2,100 tokens of your AI's memory, just for its tool descriptions

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, 5 Nov 2026.

Is EvalGate MCP server safe?

None of the hidden-instruction wordings we know were found in its 12 tool descriptions.
Its error messages showed no secrets or internal details.
All 12 of its tools are labeled read-only.
Overall it scored 94/100 on 5 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

12 tools, in the server's own words.

project_inspectread-only

Inspect the evaluations and project keys available in the authenticated organization.

project_planread-only

Return a non-mutating next-step plan for connecting a repository, evaluation, or trace source.

evaluations_listread-only

List evaluations with a stable cursor for the organization.

runs_listread-only

List evaluation runs with stable cursors and regression signals.

run_explainread-only

Explain a run using its status, failed-case metadata, and evidence-lineage summary.

baseline_lineageread-only

Show the published baseline anchor and its evidence lineage.

docs_searchread-only

Search the published OpenAPI operation catalog for relevant help.

connector_healthread-only

Show the latest connector-readiness reports for the organization.

connections_listread-only

List current workspace connection metadata, with source restrictions, freshness and bounded continuation.

connections_catalogread-only

Inspect all connector definitions and exact installed setup paths.

connections_rootsread-only

Page independent configured account roots using current administrator authority.

connections_graphread-only

Read canonical connection references and currently visible exact resource revisions.

Test results

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

!
Resources and prompts work
1 warning (1 resource)
- !Listing resource templates failed: Error POSTing to endpoint: {"error":{"code":"UNAUTHORIZED","message":"Unauthorized","requestId":"b4c1fa4d-fc2d-4f26-af32-b029cc8a81fa"}}
- and 2 more
note
✓
ConnectsConnected in 421 ms
pass
✓
Ready for the newest MCP versionUses the latest MCP version (2026-07-28)
pass
✓
Lists its toolsFound 12 tools
pass
✓
Every tool is describedAll 12 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
✓
Fast enough
All good
- ✓Connecting took 421 ms
- ✓Listing tools took 320 ms
pass
✓
No secrets leakedChecked 24 error messages: no secrets or internal details
pass
✓
Follows MCP best practices (not scored yet)Tool names, safety labels and tool list size follow the MCP guide
pass
–
Tools work with good inputs
Not tested
- –project_inspect: Needs you to sign in, so it was not tested (not counted against the server)
- –project_plan: Needs you to sign in, so it was not tested (not counted against the server)
- –evaluations_list: Needs you to sign in, so it was not tested (not counted against the server)
- –runs_list: Needs you to sign in, so it was not tested (not counted against the server)
- –baseline_lineage: Needs you to sign in, so it was not tested (not counted against the server)
- –docs_search: Needs you to sign in, so it was not tested (not counted against the server)
- –connector_health: Needs you to sign in, so it was not tested (not counted against the server)
- –connections_list: Needs you to sign in, so it was not tested (not counted against the server)
- and 4 more
not tested
–
Bad inputs give a clean error
Not tested
- –project_inspect: Needs you to sign in, so bad inputs were not tested
- –project_plan: Needs you to sign in, so bad inputs were not tested
- –evaluations_list: Needs you to sign in, so bad inputs were not tested
- –runs_list: Needs you to sign in, so bad inputs were not tested
- –baseline_lineage: Needs you to sign in, so bad inputs were not tested
- –docs_search: Needs you to sign in, so bad inputs were not tested
- –connector_health: Needs you to sign in, so bad inputs were not tested
- –connections_list: Needs you to sign in, so bad inputs were not tested
- and 2 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://www.evalgate.com/api/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/com-evalgate-evalgate.svg)](https://qamcp.dev/s/com-evalgate-evalgate.html)

Score over time

5 Nov 202694

One test so far. New tests will show here.

Reviews

Coming soon: reviews from people who use EvalGate, 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 tests it every hour and emails you when it goes down, the score drops, a tool changes or a secret leaks. Free for 1 server, no card.

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