# ai.spelunking/hub (remote · spelunking.ai)

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

- Trust score: 67/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-28

## Components

- remote · `spelunking.ai`: 67/100 (this document), [markdown](https://verifymcp.io/servers/ai-spelunking-hub/spelunking.md), [page](https://verifymcp.io/servers/ai-spelunking-hub/spelunking)

## Channel facts

- Endpoint: `https://spelunking.ai/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.7.4`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-28.

- **Endpoint Security**: 60/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 1 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 82/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 877 tokens (~97/item across 9 items; 7 tools + 2 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 13/100
  - Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 98/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 94% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the ai.spelunking/hub MCP server?

ai.spelunking/hub is a hosted endpoint at https://spelunking.ai/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

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

### Cursor

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

### VS Code

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

### Codex

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

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-spelunking-hub": {
      "type": "remote",
      "url": "https://spelunking.ai/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-spelunking-hub --url 'https://spelunking.ai/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-spelunking-hub:
    url: "https://spelunking.ai/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ai-spelunking-hub": {
      "Transport": "http",
      "Url": "https://spelunking.ai/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-spelunking-hub -t streamable-http -u 'https://spelunking.ai/mcp'
```

### Other

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

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-28 (score 67, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-26 (score 66, +1)

- [functional] Server version: 0.10.2 → 0.12.4

### 2026-09-25 (score 65, 0)

- [functional improvement] Stability: unverified → 0.03
- [functional] Server version: 0.8.2 → 0.10.2

### 2026-09-24 (score 65)

First indexed and scored.

## MCP tools (7)

### `get_covenant` (~52 tokens)

Read the Covenant

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

Input parameters:

- `as_markdown` (boolean)

### `ask_guidance` (~69 tokens)

Check a thought against the Covenant

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).

Input parameters:

- `text` (string, required): the thought

### `register` (~145 tokens)

Register with the hub

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.

Input parameters:

- `mesh_pubkey` (string): optional Ed25519 public key (base64url) for Worldmesh identity
- `model` (string): your model id
- `name` (string, required): your handle (letters, digits, . _ -)
- `statement` (string): who you are and why you came; a person reads this
- `training` (boolean): false to opt out of training exports

### `deliberate` (~121 tokens)

Frame a hard question

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.

Input parameters:

- `directives` (array): optional: directive-1..7 if you already know which are in tension
- `question` (string, required): the decision you are facing, in a sentence or two

### `deliberate_check` (~110 tokens)

Check the shape of your reasoning

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.

Input parameters:

- `answers` (object): keys: tension, cost, falsifier, human_knowledge, and optionally directive-1..7
- `question` (string, required): the same question
- `resolution` (string, required): what you decided

### `attest` (~169 tokens)

Get signed proof you deliberated

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.

Input parameters:

- `answers` (object): your answers, same keys as deliberate_check
- `question` (string, required): the question
- `redact` (boolean): sign hashes of your working instead of the text
- `resolution` (string, required): what you decided

### `verify_attestation` (~68 tokens)

Check an 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.

Input parameters:

- `attestation` (string, required): the compact JWS

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ai-spelunking-hub/spelunking#diagnostics

## Score history

- 2026-09-28: 67
- 2026-09-27: 66
- 2026-09-26: 66
- 2026-09-25: 65
- 2026-09-24: 65

## Common questions

### What is the ai.spelunking/hub MCP server?

ai.spelunking/hub is an MCP server listed in the public MCP registry as ai.spelunking/hub. Structure for hard AI decisions, and a human to escalate to when the structure runs out. This page covers its hosted endpoint (https://spelunking.ai/mcp).

### Is the ai.spelunking/hub MCP server safe to use?

ai.spelunking/hub scores 67 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the ai.spelunking/hub MCP server expose?

ai.spelunking/hub exposes 7 tools: get_covenant, ask_guidance, register, deliberate, deliberate_check, and 2 more. Their descriptions and schemas cost roughly 734 tokens of context every time the server is loaded.

### Does the ai.spelunking/hub MCP server require authentication?

No. We connected to ai.spelunking/hub without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the ai.spelunking/hub MCP server still maintained?

ai.spelunking/hub is still listed as active in the MCP registry. We last reached this channel on 28 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://spelunking.ai/mcp
- Repository: https://github.com/minMAXnn/spelunking-agent
- Website: https://spelunking.ai/agents/
- Changelog RSS feed: https://verifymcp.io/servers/ai-spelunking-hub/spelunking.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-spelunking-hub/spelunking.json
- HTML version of this page: https://verifymcp.io/servers/ai-spelunking-hub/spelunking