# deep_search_book

Search for a query directly inside a specific book by converting it to text on-the-fly. Useful for books not yet indexed by Calibre FTS.

Agent View of the PolicyLayer registry record for `deep_search_book`. HTML page: https://policylayer.com/tools/2b3pro-calibre-mcp/deep-search-book

## Facts

- Tool: `deep_search_book`
- Server: Calibre (`2b3pro/calibre-mcp`) — https://policylayer.com/tools/2b3pro-calibre-mcp.md
- Homepage: https://github.com/2b3pro/calibre-mcp
- Risk category: Read (Low risk)
- Registry record: grade B, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Allowed

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "deep_search_book",
    "arguments": {}
  }
}
```

## Why deep_search_book is rated Low

This tool performs a read-only search operation within book content. While it converts books to text on-the-fly, this is a transient operation for searching purposes only—no data is created, modified, deleted, or executed. The blast radius if misused is minimal: an agent could only retrieve or discover information from existing ebook content, not alter it or trigger external actions.

From the tool's own definition: "Tool description states it 'Search[es] for a query directly inside a specific book' and is 'Useful for books not yet indexed by Calibre FTS.' The verb 'search' combined with conversion to text for querying indicates pure information retrieval with no…"

## Use case

AI agents call deep_search_book to retrieve information from Calibre without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Calibre:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "deep_search_book": {}
  }
}
```

## Other tools on Calibre (9)

- `fetch_online_metadata` — Read — https://policylayer.com/tools/2b3pro-calibre-mcp/fetch-online-metadata.md
- `get_toc` — Read — https://policylayer.com/tools/2b3pro-calibre-mcp/get-toc.md
- `read_content` — Read — https://policylayer.com/tools/2b3pro-calibre-mcp/read-content.md
- `read_file_metadata` — Read — https://policylayer.com/tools/2b3pro-calibre-mcp/read-file-metadata.md
- `search_library` — Read — https://policylayer.com/tools/2b3pro-calibre-mcp/search-library.md
- `convert_ebook` — Write — https://policylayer.com/tools/2b3pro-calibre-mcp/convert-ebook.md
- `polish_book` — Write — https://policylayer.com/tools/2b3pro-calibre-mcp/polish-book.md
- `update_metadata` — Write — https://policylayer.com/tools/2b3pro-calibre-mcp/update-metadata.md
- `write_file_metadata` — Write — https://policylayer.com/tools/2b3pro-calibre-mcp/write-file-metadata.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=2b3pro-calibre-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/2b3pro-calibre-mcp