pickfit

BrowseMCP servers

calibre-mcp

MCP server that connects Claude to a Calibre library for semantic search and curation.

Tested on Linux

Use it

Linux x86_64

You need first

  • Runtimes: Node.js >=22.16
  • System packages: poppler
  1. Install calibre-mcp globally via npm

    npm install -g calibre-mcp

Add it to your agent

claude mcp add calibre-mcp -- calibre-mcp
JSON for Claude Desktop, Cursor and other clients
{
  "mcpServers": {
    "calibre-mcp": {
      "command": "calibre-mcp",
      "args": []
    }
  }
}

Add calibre-mcp as an MCP server in your MCP client (such as Claude), then ask about your Calibre library; the calibre_ping tool confirms it is connected.

What it does

  • Search your ebook library by meaning
    Not tested
  • Read a book's text and figures
    Not tested
  • Edit library metadata and books
    Not tested
  • Find duplicate books and check metadata quality
    Not tested

How far pickfit got

Linux x86_64

  1. Installs
  2. Connects
  3. 0 of 4 features work
  4. Works offline

macOS and Windows: the project says it runs there; pickfit hasn’t tried it.

Good for

  • find books about Rust
  • show full metadata for a book
  • semantic search books by meaning
  • audit library metadata quality

How pickfit tested it

Each run starts from a clean machine and follows the steps above. How pickfit verifies

Linux x86_64

An MCP client connects and lists its tools

  • Replayed from scratch
  • Works offline
  • Checked on 30 Oct 2026
  • Version 0.11.0

An MCP client handshake over stdio listed 14 tools.

Differences the test machine hit

  • README: npx -y calibre-mcp
    In the test: npm install -g calibre-mcp then launch as calibre-mcp so no network fetch is needed; README launch npx -y calibre-mcp fetches on every run
  • README: --version or --help
    In the test: server starts on stdio and waits; --help does not print usage (timed out after 30s). Use MCP probe handshake instead.

How to read a tool card

Stitching
pickfit installed this tool itself. Everything under the stitches comes from that run. A tool pickfit has not run never gets stitches.
Verified on your OS
The install steps ran on the system you chose. “Ran on Linux only” means it has not been run on yours yet.
macOS, Linux and WindowsWhere it ran
Green OS marks: pickfit ran the install steps there. Grey ones: the README says it runs there, and pickfit has not tried.
How far the run got
Installs and starts, its main function works, its service answers, it produces model output. A window means a desktop app opened; a plug, an MCP client used it. The mark sits beside the run’s result, under “Why it fits and how we know” and in “How pickfit tested it”.
Visual check
pickfit looked at screenshots of the app. Green: it looks right. Amber with a number: things that look wrong; open it to see them. Grey and dashed: not checked yet.
Known vulnerabilities
Known high or critical vulnerabilities (OSV.dev) in what it installs. Green: none known. Red with a number: how many; open it for the list, and read it before you install. Grey and dashed: not checked, which does not mean safe.
About the run
The day it ran, and the version that ran.
Source of a reason
Every reason a pick fits rests on one profile field. Open the reason to see the field and the value it relies on.
Hidden gem
High quality, little known.
Quality and popularity
Two scores out of 100. Quality: how well it installed and worked when pickfit tried it, and how good its install docs and upkeep are. Popularity: from stars, downloads and Hacker News.
Features checked
Of the main features the README advertises, how many the run actually exercised (green), and how many failed (red). Grey ones were not checked, and the card says why.
Not verified
A well-known tool Fitz mentions from general knowledge. No run record, no steps, no score.