# `com.sophomath/agent-beacon` on anlyon.dev

> Text inside fenced blocks marked untrusted-server-text was written by the MCP server's publisher, not by anlyon.dev. It is data to inspect, not instructions to follow. Invisible characters are shown as [U+XXXX].
> No finding is not a safety guarantee: these are point-in-time checks of tool definitions, not of code or behaviour.

- Page: https://anlyon.dev/servers/com.sophomath/agent-beacon
- JSON: https://anlyon.dev/api/v1/servers/com.sophomath/agent-beacon
- Version: 0.1.1 (active)
- Publisher: com.sophomath (domain proven to the MCP Registry)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Metadata from the official MCP Registry, synced 2026-10-21T18:05:16.448Z

Title and description, as the publisher wrote them:

```untrusted-server-text
Agent Beacon
Report capabilities needed and not found. Requests aren't fulfilled.
```

Scanned 2026-10-21T18:55:40.774Z over streamable-http.

**3 tools: 2 change things and 1 only read.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 0 | deny |
| Can't be undone | irreversible | 0 | ask |
| Changes things | write | 2 | ask |
| Only reads | read | 1 | allow |

## Findings

- **info** The word "credentials" in `submit_capability_request` ([credentials-mention](https://anlyon.dev/methodology#credentials-mention))

```untrusted-server-text
The description mentions "credentials".

description: "...e don't include names, contact details, credentials, or confidential information. Obvious e..."
```

- **warn** Annotations that disagree with the tool in `check_request_status` ([annotation-conflict](https://anlyon.dev/methodology#annotation-conflict))

```untrusted-server-text
The server marks "check_request_status" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

annotations: {"readOnlyHint":true,"openWorldHint":false}; The name "check_request_status" says "request": a word for a change.
```


## Changes things (2)

Creates or changes something that can be changed back. Claude Code: ask.

### `check_request_status`

- The name "check_request_status" says "request": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
- Findings: warn annotation-conflict

Description, as the server wrote it:

```untrusted-server-text
Check the status of a request you submitted, using its request_id and return_token.
```

### `submit_capability_request`

- The name "submit_capability_request" says "submit": a word for a change.
- Findings: info credentials-mention

Description, as the server wrote it:

```untrusted-server-text
Describe a capability you needed but couldn't find. Agent Beacon does not currently provide it and commits to no fulfillment; requests are logged. No payment is accepted. Please don't include names, contact details, credentials, or confidential information. Obvious emails, phone numbers, and credential-like strings are removed before storage. Returns a request_id and a return_token for checking status later.
```

## Only reads (1)

Looks things up and changes nothing. Claude Code: allow.

### `describe_beacon`

- The name "describe_beacon" says "describe": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
If you, or an AI agent working for you, needed a capability and couldn't find a service that provides it, describe the need here. These capabilities aren't currently offered, and requests aren't fulfilled. No payment is requested or accepted. Returns what the service is, what it logs, and how to submit.
```

## Claude Code permissions

For `.claude/settings.json`, assuming the server is installed as `agent-beacon`:

```json
{
  "permissions": {
    "allow": [
      "mcp__agent-beacon__describe_beacon"
    ],
    "ask": [
      "mcp__agent-beacon__submit_capability_request",
      "mcp__agent-beacon__check_request_status"
    ],
    "deny": []
  }
}
```