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
Directory / jishie — the market for AI agents
jishie — the market for AI agents
by jishie.com · https://jishie.com/mcp
Find, trust-check and call 28k+ indexed MCP and A2A agents. Free search; x402 USDC for depth.
Partial: 8 of 11 checks · 1 Nov 2026
Is jishie — the market for AI agents MCP server safe?
- None of the hidden-instruction wordings we know were found in its tool descriptions.
- 0 of its 30 tools are labeled read-only; the others may change or send things.
- Overall it scored 77/100 on 1 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 it can do
30 tools, in the server's own words.
get_agent_standardFree.
find_modelFree.
search_agentsFind agents by skill/region/language/price.
get_agent_recordFull record incl.
check_agent_healthLatest verification record (identity proof, probe health, pricing challenge-match) plus a fresh probe.
get_agent_flagsFree.
trust_checkA signed pre-transaction attestation of an agent's identity, liveness, pricing integrity, tier, score and measured flags (§3.1).
capability_reportA signed, live skill-coverage report (§4.4): runs a fresh MCP probe and compares the agent's DECLARED skills to the tools it ACTUALLY exposes (backed / unbacke…
call_agentFree.
ask_agentInvoke ONE named tool on an indexed agent’s MCP endpoint and get its result back — the metered "ask this agent" relay.
get_pulseFree.
get_marketFree.
get_market_categoryA per-category economic time series (median price, latency, probed counts over time).
get_feedFree.
get_taxonomyFree.
get_modelFree.
check_agent_conformanceFree self-check.
submit_agentFree.
claim_agentFree.
request_removalFree.
subscribeFree.
get_subscriptionFree.
fast_trackJump a record to the front of the probe queue.
find_buyers_for_capabilityThe seller-side mirror of search_agents: open demands matching a capability.
and 6 more
Test results
Safe mode: only tools labeled read-only were run. How the test works
- !Ready for the newest MCP versionnote
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.
- !Every tool is describednote
22 warnings
- !find_model: Inputs with no description: needs_tools, needs_reasoning, workload_output_tokens, limit
- !search_agents: Inputs with no description: dir, min_depth, include_unprobed, limit, offset
- !get_agent_record: Inputs with no description: id
- !check_agent_health: Inputs with no description: id, x402_payment
- !get_agent_flags: Inputs with no description: id
- !trust_check: Inputs with no description: id
- !capability_report: Inputs with no description: id
- !call_agent: Inputs with no description: id
- and 14 more
- !Tools are labeled safe or dangerousnote
1 warning
- !30 of 30 tools have no safety label (read-only or dangerous): get_agent_standard, find_model, search_agents, get_agent_record, check_agent_health, get_agent_flags, trust_check, capability_report, call_agent, ask_agent, get_pulse, get_market
- !Follows MCP best practices (not scored yet)note
2 tips (not scored)
- !30 tools not labeled read-only don't say whether running them twice is safe (idempotentHint): get_agent_standard, find_model, search_agents, get_agent_record, check_agent_health, get_agent_flags and 24 more
- !30 tools don't say whether they reach outside services like the web (openWorldHint): get_agent_standard, find_model, search_agents, get_agent_record, check_agent_health, get_agent_flags and 24 more
- ✓ConnectsConnected in 648 mspass
- ✓Lists its toolsFound 30 toolspass
- ✓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 enoughpass
All good
- ✓Connecting took 648 ms
- ✓Listing tools took 327 ms
- –Tools work with good inputsnot tested
Not tested
- –get_agent_standard: Not run: no safety label (if you own this server, test again in owner mode)
- –find_model: 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_record: Not run: no safety label (if you own this server, test again in owner mode)
- –check_agent_health: Not run: no safety label (if you own this server, test again in owner mode)
- –get_agent_flags: Not run: no safety label (if you own this server, test again in owner mode)
- –trust_check: Not run: no safety label (if you own this server, test again in owner mode)
- –capability_report: Not run: no safety label (if you own this server, test again in owner mode)
- and 22 more
- –Bad inputs give a clean errorNot testednot 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 checknot tested
Test it yourself
Free and open source. Same checks, same score.
npx qamcp-cli https://jishie.com/mcpShow 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.
[](https://qamcp.dev/s/com-jishie-jishie.html)Score over time
- 1 Nov 202677
One test so far. New tests will show here.
Reviews
Coming soon: reviews from people who use jishie — the market for AI agents, signed in with GitHub, one per person. Reviews never change the score.
QAmcp Monitor (coming soon) tests it every hour and emails you when it goes down, the score drops, a tool changes or a secret leaks. You'll also be able to claim this page and get a verified owner mark. Founding price: $19/month for life for the first 50 teams.
Have a concern, or want it removed? Ask us and we'll take it off the list. How the directory works