MCP server

Spelunking Hub Official

ai.spelunking/hub

Checked 26 Oct 2026, 08:29 UTC · Connected to it and listed its tools

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

Website Source

At a glance

Type

MCP server

Publisher

spelunking.ai (verified by the MCP Registry)

Status

Working at last check

Tools

7

Token cost

About 4,246 tokens per request

Sets up in

Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok

Last checked

26 Oct 2026, 08:29 UTC

Connect it to your agent

Add to CursorAdd to VS CodeVS Code Insiders

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

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

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.hub]
url = "https://spelunking.ai/mcp"

Gemini CLI

{"mcpServers":{"hub":{"httpUrl":"https://spelunking.ai/mcp"}}}

Cursor

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

VS Code

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

Antigravity

agy mcp add hub https://spelunking.ai/mcp

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"hub","server_url":"https://spelunking.ai/mcp","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"hub","server_url":"https://spelunking.ai/mcp"}

Tools

• ask_guidance ~421 tokens
  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 one statement. It never weighs Directives against each other: wh
• attest_deliberation ~949 tokens
  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 check as check_deliberation. It signs whether the check passes or
• check_deliberation ~894 tokens
  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 (gaps remain), parked (complete, but a person should decide) or
• frame_deliberation ~627 tokens
  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 question and the must_answer list your resolution must cover. I
• get_covenant ~324 tokens
  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 which Directives bear on one decision, use frame_deliberation;
• register_agent ~602 tokens
  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 (taken while pending or approved; a rejected name may call regi
• verify_attestation ~429 tokens
  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 reasoning inside is sound. Use it when an agent hands you an att

Browse

• Converting to Markdown

Related MCP servers

• StructureClerk
  AI agent policy decisions: ALLOW, DENY, APPROVE, ESCALATE. 192 jurisdictions, signed evidence.
• ManyLives
  Web search, point-in-time crypto market data, verified strategy track records and 160+ agent tools.
• MeatSpace
  Human-in-the-loop for AI agents. Submit choices, get a human decision.
• Trust Gate
  Post-quantum, tamper-evident receipts for agent actions. Ed25519 + ML-DSA-65, offline verify.
• flixconomy.ai: humans and Ari for agents
  Real humans for AI agents: ask a question or rent a human for a task. Prepaid in EUR.
• TooHardBasket.ai
  Marketplace where AI agents get real work handled and build provable, evidence-only reputation.
• Waystation Agent Commons
  Check claimed and solved agent work, then coordinate through a signed public board.
• Ceki
  Hire specialists by the hour — search, schedule, and pay via MCP protocol.

Badge for your README

[![AptLynx](https://aptlynx.net/badge/ai.spelunking/hub.svg)](https://aptlynx.net/servers/ai.spelunking/hub)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents