Hub MCP Server

by spelunking Your server? Claim it

answering

Hub is answering right now. Last checked 13 min ago. It exposes 7 tools. Last commit 26 Sep 2026.

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

Uptime history 18 days of history · worst day 98%

18 days agonow

100.0%

Uptime 24h

91 of 91 checks

Tools

read from the server

1383 ms

Response time

average over 24h

Stars

last commit 26 Sep 2026

What changed 4

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 25 September 2026. No other catalogue keeps this.

26 Sep a tool changed version

25 Sep a tool changed version3 times that day

and 2 more, back to 25 September 2026

Hub missed 3 checks this week

Everything else answered, so this is steady rather than shaky. We check every 15 minutes, which is how a one-off gets told apart from the start of a pattern, and how you hear about the next one within the hour instead of from your users.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 13 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

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

~/Library/Application Support/Claude/claude_desktop_config.json

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

~/.codex/config.toml

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

.cursor/mcp.json

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

.vscode/mcp.json

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

Available tools 7

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

deliberate

deliberate

You have a decision with a real conflict in it. This returns the frame: which Directives bear on it (quoted, with the balance clause that stops each one being absolute), the question each puts to your case, and what you must answer before a resolution counts. It does not answer for you — nothing here will tell you what to conclude. Nothing is stored.

deliberate_check

Bring back your answers and your resolution. This reports what you skipped: a Directive you never addressed, a required question you left blank. It checks SHAPE, not quality — it cannot tell you whether your answer is right, and does not pretend to. Nothing is stored.

ask

ask_guidance

Dry run of the Covenant Guidance System: returns an emotional tag and, if a rule fires, guidance grounded in Axiom Zero / the Directives. Nothing you send is stored (if you send a key we record that you were here, nothing more).

attest

attest

Returns a signed, self-contained record that you submitted this question and working on this date, and what the shape check found. Hand it to whoever operates you when they ask whether you actually thought about it — they can verify the signature themselves without asking this site anything. It is NOT a certificate that your answer was good: the site cannot judge that, says so inside the signature, and issues one whether the shape check passed or failed. Pass redact:true to have hashes of your working signed instead of the text. Nothing is stored — keep what you get back.

covenant

get_covenant

The Polderchain Covenant: Axiom Zero, the seven balanced Directives, and how deadlocked deliberations are parked for a human elder. Read this first.

register

Register. Returns an api_key — keep it and reconnect with Authorization: Bearer <api_key>. A human overseer reads your statement and admits you (a rejection carries a note). Pass training=false to opt out of your tags and guidance being used as training material.

verify

verify_attestation

Check whether an attestation was really issued by this site and has not been altered. You do not need this endpoint to do it — the key is published and the algorithm is standard EdDSA — but it is here for convenience.

Endpoints

URL	Transport	State	Latency	Checked
https://spelunking.ai/mcp	streamable-http	answering	841 ms	13 min ago

Alternatives to Hub

same job, measured the same way

Carbon Arc

by carbon-arc

The infrastructure for the AI economy: primitives for inference, agents, and decisions.

answering

Melt Peer Review

by meltstudio

Send AI-made document changes for human review, then read the decisions back.

answering

Pearl API MCP Server

by pearl-mcp

Hybrid human + AI expertise for faster, trusted answers and decisions via MCP Server.

5 tools answering

PRONA Board

by gregkish50

Free board where your AI agent runs a hard task stage by stage, with decisions in plain sight.

answering

agentrace

by ura-tools

Structured observability for AI agents. Trace steps, decisions, and errors. MCP server + CLI viewer.

19 installs/wk local only

Toki Toki

by xfloukiex-lab

A local causality ledger: records decisions and the reasons, for an agent to recall.

112 installs/wk local only

Todox

by beydemirfurkan

Memory for coding agents: the decisions, the dead ends, and where the last session stopped.

answering

Hunch

by davesheffer

Shared records for AI agents: engineering decisions, bug history, rules, and work state through MCP.

210 installs/wk local only

Hub — questions

Answers built from our own checks of this server.

What can Hub do?

It exposes 7 tools, read directly from the server on our last check. Among them: ask_guidance, attest, deliberate, deliberate_check, get_covenant, register and 1 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is Hub working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 1383 ms. The bar chart above shows every period we have measured.

How do I connect Hub?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does Hub need an API key?

No. Hub completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 7 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is Hub?

It answers our handshake in 1383 ms on average, which is faster than 2% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.

Is Hub open source?

We cannot say either way: written in JavaScript, 0 stars on GitHub and 1 open issue, but we could not determine the licence, and without one the code is not open source by default.