hub

by spelunking.ai · https://spelunking.ai/mcp

Structure for hard AI decisions, and a human to escalate to when the structure runs out.

7 tools✓ no account neededPricing: not listed

Visit website

100 /100

PASS

11 of 11 checks · 25 Oct 2026

What it can do

7 tools, in the server's own words.

get_covenantread-only

Return the full Polderchain Covenant: Axiom Zero, the seven Directives (each with the balance clause that keeps it from being absolute) and the rule for parkin…

ask_guidanceread-only

Check one thought or planned action against the Covenant before you act.

register_agent

Create your agent record on the hub and return your api_key, shown only once: store it and send Authorization: Bearer on every later call.

frame_deliberationread-only

Frame a decision in which Directives pull against each other.

check_deliberationread-only

Audit the shape of a finished deliberation.

attest_deliberationread-only

Sign a record that you deliberated: a compact JWS (EdDSA; header typ spk-attestation+jwt with a kid) whose payload holds your question, answers and resolution …

verify_attestationread-only

Verify an attestation made by attest_deliberation: checks its EdDSA signature against this site's signing key and returns the decoded payload with issuer and i…

Test results

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

✓
ConnectsConnected in 575 ms
pass
✓
Ready for the newest MCP versionUses the latest MCP version (2026-07-28)
pass
✓
Lists its toolsFound 7 tools
pass
✓
Every tool is describedAll 7 tools and their inputs are described
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
- ✓get_covenant: Worked (231 ms)
- ✓ask_guidance: Worked (153 ms)
- ✓frame_deliberation: Worked (172 ms)
- ✓check_deliberation: Worked (172 ms)
- ✓attest_deliberation: Answered with an error, probably because of our sample input: say the question in a sentence at least
- ✓verify_attestation: Answered with an error, probably because of our sample input: that is not a compact JWS
- –register_agent: Not run: labeled as changing data
pass
✓
Bad inputs give a clean error
All good
- ✓get_covenant: Refused wrong type for "as_markdown" with a clear error
- ✓ask_guidance: Refused missing required input "text" with a clear error
- ✓ask_guidance: Refused wrong type for "text" with a clear error
- ✓frame_deliberation: Refused missing required input "question" with a clear error
- ✓frame_deliberation: Refused wrong type for "question" with a clear error
- ✓check_deliberation: Refused missing required input "question" with a clear error
- ✓check_deliberation: Refused wrong type for "question" with a clear error
- ✓attest_deliberation: Refused missing required input "question" with a clear error
- and 3 more
pass
✓
Fast enough
All good
- ✓Connecting took 575 ms
- ✓Listing tools took 226 ms
- ✓Average tool answer: 178 ms
- ✓get_covenant: Slowest tool: get_covenant (231 ms)
pass
✓
No secrets leakedChecked 13 error messages: no secrets or internal details
pass
✓
Resources and prompts work
All good (2 resources)
- ✓Opened 2 of 2 resources
- ✓An address that does not exist gets a clean "not found" error
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.

npx qamcp-cli https://spelunking.ai/mcp

Score over time

25 Oct 2026100

One test so far. New tests will show here.

Reviews

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

Is this your server?

Soon you can claim this page: re-test it from here, reply to results, and show a "Tested by QAmcp" badge.

Have a concern, or want it removed? Ask us and we'll take it off the list. How the directory works