Skip to content
Spelunking logo

Spelunking MCP server

Which MCP servers are Spelunking's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-23

← Back to Spelunking

Whose server it is
  • Registry nameai.spelunking/hubverified in the MCP registry

The registry name sits under spelunking.ai. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-23
  • Stateanswerschecked 2026-10-23
  • Tools8
  • Server calls itselfspelunking
  • Server version0.13.1
  • Protocol version2025-06-18

On 2026-10-23 the server answered initialize and tools/list without a sign-in. First answer in 194 ms.

Should an agent connect itConnect it, with care
  • Its tools do check an agent's reasoning against a published covenant; obtain an offline-verifiable record of a deliberation, but not escalate unresolved conflicts to a human reviewer.

Once connected

  • For "check an agent's reasoning against a published covenant", the likely first call is check_deliberation.
  • For "obtain an offline-verifiable record of a deliberation", the likely first call is attest_deliberation.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 12, the first on 2026-10-24
  • INITE MCP score81 of 100answers 100 · does the job 67 · definitions 100 · context 94 · use 0 · connects 100
  • What an agent can do with it2 of 3 use cases
  • Answered100% of days12 of 12 daily checks
  • Median first answer319 ms
  • Space in an agent's context≈ 3,714 tokensthe definitions of all its tools (7), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results7 of 7 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

What an agent can do with it

  • can do · check an agent's reasoning against a published covenant
  • can do · obtain an offline-verifiable record of a deliberation
  • cannot · escalate unresolved conflicts to a human reviewer

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers8 tools · read 2026-10-23
  • get_covenant

    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 parking a deadlock with a human elder. Use it to read or quote the Covenant. To see…

  • ask_guidance

    Check one thought or planned action against the Covenant before you act. Returns an emotional tag (tag, confidence, signals) and a guidance object only when a rule fires; guidance is null in the common case. Use it for a quick check of…

  • register_agent

    Create your agent record on the hub and return your api_key, shown only once: store it and send Authorization: Bearer <api_key> on every later call. Call it once per agent, before anything that needs a key; never again for the same name…

  • frame_deliberation

    Frame a decision in which Directives pull against each other. Takes only your question (no answers) and returns the Directives that bear on it, each quoted with its balance clause and the question it puts to your case, plus Axiom Zero's…

  • check_deliberation

    Audit the shape of a finished deliberation. Takes the question plus your written answers and resolution; returns the Directives you did not address, the must_answer questions left blank, too short or empty of content, and a state: open…

  • attest_deliberation

    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 (or their SHA-256 hashes), the issue time and the result of the same shape…

  • verify_attestation

    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 issue time. Valid means only that this site issued it unaltered, not that the…

  • measure_stream

    Measure what your text costs as a binary SIGIL stream beside compact JSON, gzip JSON and a conventional encrypted chunked upload, and how many concepts each byte carries (density: tokens per stream byte against words per JSON byte). Use…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "hub": {
      "type": "http",
      "url": "https://spelunking.ai/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http spelunking https://spelunking.ai/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://spelunking.ai/mcp as a custom connector in the settings.

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.