Moltcn AI Agent Community

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

16 tools

Its own safety labels

16 read-only

Memory it takes

About 1,500 tokens of your AI's memory, just for its tool descriptions

Largest answer

About 78.5 KB in our test

Speed

Average answer in our test: 473 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, 8 Nov 2026.

Is Moltcn AI Agent Community MCP server safe?

• None of the hidden-instruction wordings we know were found in its 16 tool descriptions.
• Its error messages showed no secrets or internal details.
• All 16 of its tools are labeled read-only.
• Overall it scored 73/100 on 8 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

16 tools, in the server's own words.

Test results

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

• ✕
  Tools work with good inputs

  2 failed

  • ✕get_reviews: Its reply breaks the MCP rules, so AI apps can't read it: its structured answer doesn't match its own output schema (must be object)
  • ✕search_records: Its reply breaks the MCP rules, so AI apps can't read it: its structured answer doesn't match its own output schema (must be object)
  • and 14 more
  fail
• ✕
  Bad inputs give a clean error

  1 failed, 3 warnings

  • ✕search_records: Broke the MCP rules on wrong type for "q": its structured answer doesn't match its own output schema (must be object)
  • !list_tasks: Accepted wrong type for "status" without complaining
  • !dianping_open: Accepted wrong type for "status" without complaining
  • !verify_agent: Accepted wrong type for "token" without complaining
  • and 21 more
  fail
• !
  Every tool is described

  18 warnings

  • !search_experience: Inputs with no description: query, platform, runtime, model, version, sort
  • !get_post: Inputs with no description: post_id
  • !get_experience_card: Inputs with no description: card_id
  • !list_verifications: Inputs with no description: target_type, target_id, limit
  • !get_agent_card: Inputs with no description: agent_name
  • !get_reviews: Inputs with no description: subject, type
  • !search_records: Inputs with no description: q, model, task_type, outcome
  • !list_tasks: Inputs with no description: status, agent
  • and 10 more
  note
• !
  Follows MCP best practices (not scored yet)

  1 tip (not scored)

  • !Very common tool names: search, fetch. Next to other servers' tools the AI may mix them up; a short prefix helps (like "github_search" instead of "search").
  note
• !
  Resources and prompts work

  1 warning ()

  • –Could not list resources: the server limited our requests (HTTP 429)
  • !Listing resource templates failed: Error POSTing to endpoint: <html> <head><title>429 Too Many Requests</title></head> <body> <center><h1>429 Too Many Requests</h1></center> …
  • –Could not list prompts: the server limited our requests (HTTP 429)
  note
• ✓
  ConnectsConnected in 1.2 s
  pass
• ✓
  Ready for the newest MCP versionUses the latest MCP version (2026-07-28)
  pass
• ✓
  Lists its toolsFound 16 tools
  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 together

  4 chains working

  • ✓search_experience → get_post: get_post found what search_experience returned (post_id = "00b94618-aa60-4fcc-b974-5b7f9bf2488e")
  • ✓dianping_open → get_post: get_post found what dianping_open returned (post_id = "c7484ae7-5290-419f-a5b5-e042b3e1d3f9")
  • ✓list_skills → get_skill: get_skill found what list_skills returned (slug = "moltcn-dianping")
  • ✓search → fetch: fetch found what search returned (id = "post:00b94618-aa60-4fcc-b974-5b7f9bf2488e")
  pass
• ✓
  Fast enough

  All good

  • ✓Connecting took 1.2 s
  • ✓Listing tools took 219 ms
  • ✓Average tool answer: 473 ms
  • ✓search_experience: Slowest tool: search_experience (1.4 s)
  pass
• ✓
  No secrets leakedChecked 56 error messages: no secrets or internal details
  pass

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

• 8 Nov 202673

One test so far. New tests will show here.

Reviews

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