// SCAN REPORT

Calibre

7 tools. 2 can modify or destroy data without limits.

2 write tools that can modify data. Rate limits recommended.

Last updated: 3 Jul 2026

2 can modify or destroy data

5 read-only

7 tools total

Community server · catalogue entry verified 03/07/2026

How to control Calibre ↓

TOOL MAP

What Calibre exposes to your agents

Read (5) Write / Execute (2) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Calibre tools

Write · Medium set_custom_column This tool creates or modifies custom column definitions in a Calibre library—a Write operation since custom columns can be deleted or updated later. Write · Medium set_metadata The tool modifies metadata fields in a Calibre library, making it a Write operation.

2 of Calibre's 7 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Calibre

PolicyLayer is an MCP gateway — it sits between your AI agents and Calibre, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "set_custom_column": {
    "limits": [
      {
        "counter": "set_custom_column_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_book_info": {
    "limits": [
      {
        "counter": "get_book_info_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Calibre — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON CALIBRE →

Instant setup, no code required.

FULL CATALOGUE

All 7 Calibre tools

WRITE 2 tools

Write set_custom_column set_custom_column Write set_metadata set_metadata

READ 5 tools

Read get_book_info Get detailed metadata for a book by its Calibre ID. Read get_custom_columns List all custom columns defined in the Calibre library. Read get_epub_path Get the absolute file path of a book's EPUB file. Read list_series List all books in a series, sorted by series_index. Read search_books search_books

FAQ

Questions about Calibre

How do I prevent bulk modifications through Calibre? +

The Calibre server has 2 write tools including set_custom_column, set_metadata. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Calibre.

How many tools does the Calibre MCP server expose? +

7 tools across 2 categories: Read, Write. 5 are read-only. 2 can modify, create, or delete data.

How do I enforce a policy on Calibre? +

Register the Calibre MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Calibre tool call.

Deterministic rules across all 7 Calibre tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON CALIBRE →

Instant setup, no code required.

7 Calibre tools catalogued and risk-classified — across an index of 43,000+ MCP servers.