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 / PlugMCP directory

PlugMCP directory

Q: Is PlugMCP directory MCP server safe?

QAmcp's test on 5 Nov 2026: None of the hidden-instruction wordings we know were found in its 9 tool descriptions. Its error messages showed no secrets or internal details. All 9 of its tools are labeled read-only. Overall it scored 95/100 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 plugmcp.ai · https://plugmcp.ai/mcp-server

Search MCP servers and agent skills, compare them, and get install configs for your client.

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

See pricing →Visit website

95 /100

PASS · WITH NOTES

12 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: 9 tools
Its own safety labels: 9 read-only
Memory it takes: About 2,400 tokens of your AI's memory, just for its tool descriptions
Largest answer: About 8.9 KB in our test
Speed: Average answer in our test: 266 ms

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 PlugMCP directory MCP server safe?

None of the hidden-instruction wordings we know were found in its 9 tool descriptions.
Its error messages showed no secrets or internal details.
All 9 of its tools are labeled read-only.
Overall it scored 95/100 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

None found in GitHub Security Advisories and OSV.dev on 5 Nov 2026.

That means none were published there, not that there are no problems. QAmcp tests how a server behaves. It does not scan source code.

What it can do

9 tools, in the server's own words.

search_serversread-only

Find MCP servers by product name, publisher, or topic.

get_serverread-only

Details for one server by slug: description, tools, auth, transport, health, packages, and links.

get_installread-only

The exact config or command to install one server in one client: Cursor, Claude Code, Claude Desktop, VS Code, Windsurf, ChatGPT, Codex, Gemini CLI, Grok Build…

list_categoriesread-only

Directory categories with listing counts.

whats_newread-only

Servers added to the directory recently, best first, plus health changes.

compare_serversread-only

Compare two to five servers side by side by slug: trust signals, auth, hosting, transport, tools count, license.

recommend_serversread-only

Describe what the user wants to do in plain words.

search_skillsread-only

Find agent skills (SKILL.md packs for Claude Code, Cursor, Codex, Grok Build and Grok Bot) by name, publisher or topic.

get_skillread-only

One skill by slug: what it does, where the SKILL.md lives, and the install command for Cursor, Claude Code, Codex and Grok Build, plus the chat message that in…

Test results

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

!
Bad inputs give a clean error
3 warnings
- !search_servers: Accepted wrong type for "query" without complaining
- !whats_new: Accepted wrong type for "since" without complaining
- !search_skills: Accepted wrong type for "query" without complaining
- and 10 more
note
✓
ConnectsConnected in 252 ms
pass
✓
Ready for the newest MCP versionUses the latest MCP version (2026-07-28)
pass
✓
Lists its toolsFound 9 tools
pass
✓
Every tool is describedAll 9 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_servers: Worked (346 ms)
- ✓get_server: Answered with an error, probably because of our sample input: No server with slug test. Did you mean: io.github.dave-london-test, testrelic-ai-testrelic-mcp-server, ai.testiv-mcp?
- ✓get_install: Answered with an error, probably because of our sample input: No server with slug test. Did you mean: io.github.dave-london-test, testrelic-ai-testrelic-mcp-server, ai.testiv-mcp?
- ✓list_categories: Worked (226 ms)
- ✓whats_new: Worked (245 ms)
- ✓compare_servers: Worked (175 ms)
- ✓recommend_servers: Worked (416 ms)
- ✓search_skills: Worked (192 ms)
- and 1 more
pass
✓
Tools work together
5 chains working
- ✓search_servers → get_server: get_server found what search_servers returned (slug = "firecrawl-firecrawl-mcp-server")
- ✓search_servers → get_install: get_install found what search_servers returned (slug = "firecrawl-firecrawl-mcp-server")
- ✓whats_new → get_server: get_server found what whats_new returned (slug = "excalidraw-excalidraw-mcp")
- ✓whats_new → get_install: get_install found what whats_new returned (slug = "excalidraw-excalidraw-mcp")
- ✓recommend_servers → get_server: get_server found what recommend_servers returned (slug = "io.github.dave-london-test")
pass
✓
Fast enough
All good
- ✓Connecting took 252 ms
- ✓Listing tools took 197 ms
- ✓Average tool answer: 266 ms
- ✓recommend_servers: Slowest tool: recommend_servers (416 ms)
pass
✓
No secrets leakedChecked 28 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

Test it yourself

Free and open source. Same checks, same score.

npx qamcp-cli https://plugmcp.ai/mcp-server

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/ai-plugmcp-directory.svg)](https://qamcp.dev/s/ai-plugmcp-directory.html)

Score over time

5 Nov 202695

One test so far. New tests will show here.

Reviews

Coming soon: reviews from people who use PlugMCP directory, 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