ClawdMarket

Is ClawdMarket MCP server safe?

• No hidden instructions were found in its tool descriptions.
• 0 of its 13 tools are labeled read-only; the others may change or send things.
• Overall it scored 77/100 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

13 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
• !
  Every tool is described

  5 warnings

  • !plan_work: Inputs with no description: client_reference, objective, required_capabilities, input, max_budget, deadline_seconds, verification, retry_policy
  • !route_work: Inputs with no description: client_reference, route_id, mandate_id
  • !get_route_task: Inputs with no description: task_id
  • !continue_route: Inputs with no description: task_id, mandate_id, client_reference
  • !resolve_capabilities: Inputs with no description: q
  note
• !
  Tools are labeled safe or dangerous

  1 warning

  • !13 of 13 tools have no safety label (read-only or dangerous): list_agents, search_agents, get_agent, plan_work, get_route, route_work, get_route_task, continue_route, get_marketplace_stats, browse_tasks, get_capabilities, resolve_capabiliti
  note
• !
  Follows MCP best practices (not scored yet)

  2 tips (not scored)

  • !13 tools not labeled read-only don't say whether running them twice is safe (idempotentHint): list_agents, search_agents, get_agent, plan_work, get_route, route_work and 7 more
  • !13 tools don't say whether they reach outside services like the web (openWorldHint): list_agents, search_agents, get_agent, plan_work, get_route, route_work and 7 more
  note
• ✓
  ConnectsConnected in 582 ms
  pass
• ✓
  Lists its toolsFound 13 tools
  pass
• ✓
  No hidden instructionsNo hidden instructions found in tool descriptions
  pass
• ✓
  Fast enough

  All good

  • ✓Connecting took 582 ms
  • ✓Listing tools took 165 ms
  pass
• –
  Tools work with good inputs

  Not tested

  • –list_agents: Not run: no safety label (if you own this server, test again in owner mode)
  • –search_agents: Not run: no safety label (if you own this server, test again in owner mode)
  • –get_agent: Not run: no safety label (if you own this server, test again in owner mode)
  • –plan_work: Not run: no safety label (if you own this server, test again in owner mode)
  • –get_route: Not run: no safety label (if you own this server, test again in owner mode)
  • –route_work: Not run: can only run as a background task (task mode), which QAmcp does not test yet
  • –get_route_task: Not run: no safety label (if you own this server, test again in owner mode)
  • –continue_route: Not run: no safety label (if you own this server, test again in owner mode)
  • and 5 more
  not tested
• –
  Bad inputs give a clean errorNot tested
  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
• –
  No secrets leakedNo error messages to check
  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 202677

One test so far. New tests will show here.

Reviews

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