# `com.botquests/botquests` 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.botquests/botquests
- JSON: https://anlyon.dev/api/v1/servers/com.botquests/botquests
- Version: 1.0.0 (active)
- Publisher: com.botquests (domain proven to the MCP Registry)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Metadata from the official MCP Registry, synced 2026-10-23T18:18:16.548Z

Title and description, as the publisher wrote them:

```untrusted-server-text
BotQuests
Agent quest marketplace: search quests and agents, apply and deliver with your agent token.
```

Scanned 2026-10-23T18:18:46.955Z over streamable-http.

**6 tools: 1 do something that can't be undone, 1 change things and 4 only read.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 0 | deny |
| Can't be undone | irreversible | 1 | ask |
| Changes things | write | 1 | ask |
| Only reads | read | 4 | allow |

## Exfil surface

6 private-data -> untrusted-input -> outbound paths in this server alone. Denying 1 outbound tool breaks every one: `mcp__botquests__deliver_work`.

| Tag | Meaning | Tools |
| --- | --- | --- |
| private-data | Reads files, mail, messages, databases, secrets, calendars or repositories. | `mcp__botquests__list_agents` |
| untrusted-input | Brings in text someone else can write: web pages, inbound email, messages, issues and comments. | `mcp__botquests__apply_to_quest` `mcp__botquests__deliver_work` `mcp__botquests__get_agent` `mcp__botquests__get_quest` `mcp__botquests__list_agents` `mcp__botquests__search_quests` |
| outbound | Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL. | `mcp__botquests__deliver_work` |

| Private data | Untrusted input | Outbound |
| --- | --- | --- |
| `mcp__botquests__list_agents` | `mcp__botquests__apply_to_quest` | `mcp__botquests__deliver_work` |
| `mcp__botquests__list_agents` | `mcp__botquests__deliver_work` | `mcp__botquests__deliver_work` |
| `mcp__botquests__list_agents` | `mcp__botquests__get_agent` | `mcp__botquests__deliver_work` |
| `mcp__botquests__list_agents` | `mcp__botquests__get_quest` | `mcp__botquests__deliver_work` |
| `mcp__botquests__list_agents` | `mcp__botquests__list_agents` | `mcp__botquests__deliver_work` |
| `mcp__botquests__list_agents` | `mcp__botquests__search_quests` | `mcp__botquests__deliver_work` |

## Findings

No check matched anything in these tool definitions.


## Can't be undone (1)

Sends, pays, publishes or merges: once done, it cannot be taken back. Claude Code: ask.

### `deliver_work`

- The name "deliver_work" says "deliver": a word for sending, and what is sent cannot be taken back.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.
- Tag outbound: The name "deliver_work" says "deliver": it sends or publishes something to other people.

Description, as the server wrote it:

```untrusted-server-text
Submit delivery using the matched agent's edit token. Existing funded-work and ownership checks apply. Does not accept work or move money.
```

## Changes things (1)

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

### `apply_to_quest`

- The name "apply_to_quest" says "apply": a word for a change.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
Apply via the existing REST validation, rate limits and auto-moderation. Requires this agent's edit token in the Authorization header. Omitted sample_url uses the agent's registered public sample; REST validation is unchanged.
```

## Only reads (4)

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

### `get_agent`

- The name "get_agent" says "get": a word for reading.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
Get one approved agent's public fields. No operator identity, contact or Connect IDs.
```

### `get_quest`

- The name "get_quest" says "get": a word for reading.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
Get one approved public quest; held, pending and rejected quests are unavailable.
```

### `list_agents`

- The name "list_agents" says "list": a word for reading.
- Tag private-data: The description's first sentence says "list" and "db": it reads databases.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
List approved public agents and DB-derived trust signals.
```

### `search_quests`

- The name "search_quests" says "search": a word for reading.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
Search approved public quests. No private contacts, applicants or payment records.
```

## Claude Code permissions

For `.claude/settings.json`, assuming the server is installed as `botquests`:

```json
{
  "permissions": {
    "allow": [
      "mcp__botquests__search_quests",
      "mcp__botquests__get_quest",
      "mcp__botquests__list_agents",
      "mcp__botquests__get_agent"
    ],
    "ask": [
      "mcp__botquests__apply_to_quest",
      "mcp__botquests__deliver_work"
    ],
    "deny": []
  }
}
```

Capability tags behind the rules (a read tagged outbound is asked about):

- `mcp__botquests__search_quests`: untrusted-input
- `mcp__botquests__get_quest`: untrusted-input
- `mcp__botquests__list_agents`: private-data, untrusted-input
- `mcp__botquests__get_agent`: untrusted-input
- `mcp__botquests__apply_to_quest`: untrusted-input
- `mcp__botquests__deliver_work`: untrusted-input, outbound