Agent Provider Depot

Is Agent Provider Depot MCP server safe?

• No hidden instructions were found in its tool descriptions.
• Its error messages showed no secrets or internal details.
• All 4 of its tools are labeled read-only.
• Overall it scored 75/100 on 30 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

4 tools, in the server's own words.

Test results

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

• ✕
  Resources and prompts work

  1 failed, 9 warnings (11 resources, 9 prompts)

  • ✕11 listed resources are missing a valid address or name, so AI apps can't show or open them.
  • !Opening an address that doesn't exist (/api/hub://qamcp-does-not-exist-dddfe61c) returns content instead of a "not found" error, so AI apps can't tell a typo from real data.
  • !session-brief: Doesn't complain when the required input providers is missing.
  • !choose-stack: Doesn't complain when the required input task is missing.
  • !rescue-error: Doesn't complain when the required input error is missing.
  • !plan-eval: Doesn't complain when the required input task is missing.
  • !audit-stack: Doesn't complain when the required input deps is missing.
  • !choose_infra: Doesn't complain when the required input task is missing.
  • and 4 more
  fail
• !
  Ready for the newest MCP version

  1 warning

  • !Uses an older MCP version (2025-06-18). It works today, but it isn't on the July 2026 version (2026-07-28) yet.
  note
• !
  Every tool is described

  3 warnings

  • !session_brief: Inputs with no description: policies
  • !decide: Inputs with no description: full
  • !depot: Inputs with no description: op, args
  note
• !
  Bad inputs give a clean error

  2 warnings

  • !session_brief: Accepted wrong type for "providers" without complaining
  • !rescue: Accepted wrong type for "q" without complaining
  • and 3 more
  note
• ✓
  ConnectsConnected in 476 ms
  pass
• ✓
  Lists its toolsFound 4 tools
  pass
• ✓
  Tools are labeled safe or dangerousEvery tool has a safety label
  pass
• ✓
  No hidden instructionsNo hidden instructions found in tool descriptions
  pass
• ✓
  Tools work with good inputs

  All good

  • ✓session_brief: Worked (137 ms)
  • ✓rescue: Worked (114 ms)
  • ✓decide: Answered with an error, probably because of our sample input: error missing_query_param: task or jtbd is required (string) {"error":{"code":"missing_query_param","message":"task or jtbd is required (st…
  • ✓depot: Answered with an error, probably because of our sample input: error missing_query_param: task is required (string) {"error":{"code":"missing_query_param","message":"task is required (string)"}}
  pass
• ✓
  Fast enough

  All good

  • ✓Connecting took 476 ms
  • ✓Listing tools took 123 ms
  • ✓Average tool answer: 115 ms
  • ✓session_brief: Slowest tool: session_brief (137 ms)
  pass
• ✓
  No secrets leakedChecked 5 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 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

• 30 Oct 202675

One test so far. New tests will show here.

Reviews

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