4,700+ servers built on MCP Fusion
Vinkius

Calibre-Web MCP. Manage your entire digital library structure via AI chat.

Claude Claude
ChatGPT ChatGPT
Cursor Cursor
Gemini Gemini
Windsurf Windsurf
VS Code VS Code
JetBrains JetBrains
Vercel Vercel
See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Calibre-Web MCP on Cursor AI Code Editor MCP Client Calibre-Web MCP on Claude Desktop App MCP Integration Calibre-Web MCP on OpenAI Agents SDK MCP Compatible Calibre-Web MCP on Visual Studio Code MCP Extension Client Calibre-Web MCP on GitHub Copilot AI Agent MCP Integration Calibre-Web MCP on Google Gemini AI MCP Integration Calibre-Web MCP on Lovable AI Development MCP Client Calibre-Web MCP on Mistral AI Agents MCP Compatible Calibre-Web MCP on Amazon AWS Bedrock MCP Support

Just plug in your AI agents and start using Vinkius.

Calibre-Web MCP Server lets your AI client talk to your digital book library. It gives you tools to browse your entire collection using the OPDS catalog, check specific shelf contents, and prepare metadata for Kobo sync.

Access your books, categories, and device metadata directly from your chat window.

What your AI agents can do

Get opds catalog

Retrieves the main OPDS catalog feed, showing the overall structure of your entire library.

Get opds shelf

Gets the OPDS feed for a specific shelf ID, listing only the books in that curated collection.

Sync kobo library

Syncs your Calibre library data, generating metadata and download links optimized for Kobo devices (requires a Kobo Token).

Browse Full Library Catalog

The agent calls get_opds_catalog to retrieve the complete XML feed, showing all available categories, authors, and structural data in your Calibre library.

List Books on Specific Shelf

The agent uses get_opds_shelf to pull metadata for books tied to a given shelf ID, letting you check a collection's contents instantly.

Prepare Kobo Sync Metadata

The agent calls sync_kobo_library to generate the structured metadata and direct download links needed to sync your collection to Kobo devices.

Locate Specific Book Metadata

The agent inspects the library structure to find details for a named book, pulling specific metadata entries.

Supported MCP Clients

Claude Claude
ChatGPT ChatGPT
Cursor Cursor
Gemini Gemini
Windsurf Windsurf
VS Code VS Code
JetBrains JetBrains
Vercel Vercel
+ other MCP clients
Free for Subscribers

Waiting for input…

AI Agent

Calibre-Web MCP Server: 3 Tools for Library Management

Use these tools to query your library structure, fetch specific shelf data, and prepare metadata for external devices like Kobo.

get019e3873

get opds catalog

Retrieves the main OPDS catalog feed, showing the overall structure of your entire library.

get019e3873

get opds shelf

Gets the OPDS feed for a specific shelf ID, listing only the books in that curated collection.

sync019e3873

sync kobo library

Syncs your Calibre library data, generating metadata and download links optimized for Kobo devices (requires a Kobo Token).

Choose How to Get Started

Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.

Build Your Own

Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.

  • Import from OpenAPI, Swagger, or YAML specs
  • Create Agent Skills with progressive disclosure
  • Deploy to edge with MCPFusion framework
  • Built in DLP, auth, and compliance on every call
  • Real time usage dashboard and cost metering
  • Publish to catalog or keep private
Start building

Make Your AI Do More

Start with Calibre-Web, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.

  • Use this MCP plus 4,700+ others, all in one place
  • Add new capabilities to your AI anytime you want
  • Every connection is secured and compliant automatically
  • Track usage and costs across all your servers
  • Works with Claude, ChatGPT, Cursor, and more
  • New servers added to the catalog every week

What you can do with this MCP connector

Your AI client can talk directly to your digital book library through this server. You'll get tools to browse your whole collection using the OPDS catalog, check specific shelf contents, and prep metadata for Kobo sync. You can access your books, categories, and device metadata right from your chat window.

Browse Full Library Catalog: The agent calls get_opds_catalog to pull the full XML feed, showing every category, author, and structural bit of data in your Calibre library. List Books on Specific Shelf: You'll use get_opds_shelf to grab metadata for books linked to a given shelf ID, letting you check a curated collection's contents instantly. Prepare Kobo Sync Metadata: The agent calls sync_kobo_library to generate the structured metadata and direct download links you need to sync your collection to Kobo devices. Locate Specific Book Metadata: The agent inspects the library structure to find details for a named book, pulling specific metadata entries.

How Calibre-Web MCP Works

  1. 1 Subscribe to the Calibre-Web server, providing your instance URL and credentials.
  2. 2 Your AI client sends a request (e.g., 'Show me books on shelf 5') to the MCP Server.
  3. 3 The agent executes the necessary tool (e.g., get_opds_shelf) and returns the structured data directly to your chat window.

The bottom line is that your agent handles the API calls to your private library data, so you don't have to leave your coding environment to manage your ebooks.

Who Is Calibre-Web MCP For?

Digital Librarians and power readers. This is for the person who manages massive ebook collections—the one who needs to verify catalog integrity or sync a specific batch of books without logging into the Calibre Web UI. If you're tired of manual web browsing to check book metadata, this is for you.

Digital Librarian

Uses the agent to verify the exact contents of a shelf or category ID, ensuring catalog consistency before making changes.

Ebook Archivist

Automates the retrieval of metadata for large batches of books, checking structural integrity and preparing them for archival sync.

Power Reader / Hobbyist

Quickly finds a book's metadata or confirms its placement in a specific collection without leaving the chat interface.

What Changes When You Connect

  • Browse the whole collection. Use get_opds_catalog to see every category and series in your library instantly. No more clicking through dozens of manual index pages.
  • Verify shelf contents. Need to know what's on Shelf ID 5? get_opds_shelf pulls the exact list of books and metadata, letting you audit a collection's contents via chat.
  • Automate e-reader sync. sync_kobo_library handles the heavy lifting, generating structured metadata and direct download links, so you don't have to copy-paste tokens or links.
  • Direct library access. Your agent can find specific book metadata and structure information, treating your private library like a searchable database, not just a folder.
  • Consistency check. By querying the OPDS feed, you ensure the metadata your agent uses matches the actual catalog structure, reducing data integrity risks.

Real-World Use Cases

01

Auditing a book collection for publication.

A librarian needs to verify that all books in the 'Sci-Fi Classics' collection are properly cataloged and have accurate metadata. Instead of logging into the web UI and clicking through, they ask their agent to run get_opds_shelf for the relevant shelf ID. The agent returns a clean list of all 12 titles and their metadata, confirming the collection's structural integrity.

02

Preparing a bulk transfer for a Kobo device.

A user has finished curating 50 books and needs to sync them to a Kobo e-reader. They trigger the sync_kobo_library tool. The agent runs the sync, generates the required metadata and direct download links, and presents them, saving the user the manual process of token management.

03

Checking for new additions to the library.

A reader wants to know what was recently added to their vast personal library. They ask the agent to run get_opds_catalog. The agent accesses the main OPDS feed and immediately lists all 'Newest' additions, providing a quick, comprehensive overview of the library's current state.

04

Researching a specific book's history.

A student needs to confirm a book's category and associated metadata without opening the main Calibre Web page. They ask the agent to inspect the library, and the tool finds the specific book entry, returning its metadata and placement within the overall library structure.

The Tradeoffs

Manual web browsing

Trying to find a specific book's metadata or the full list of categories by manually clicking through the Calibre-Web interface and copying data snippets. This is slow, error-prone, and makes auditing impossible.

Use the agent to run get_opds_catalog for the full structure, or use get_opds_shelf if you know the shelf ID. This gets you the structured data instantly.

Relying on local file exports

Exporting the entire library from Calibre and then trying to parse the resulting XML/CSV file in a spreadsheet. This file is often too complex, lacks clean structure, and is difficult to query for specific metadata fields.

Let the agent handle it. Use get_opds_catalog for the clean, standardized feed, or use sync_kobo_library if your goal is device synchronization.

Over-relying on simple search.

Typing a simple search query into the web interface, which only returns a list of titles but provides zero structural metadata (like category, series, or author linkage).

If you need structure, run get_opds_catalog to get the full hierarchy. If you need a specific subset, run get_opds_shelf.

When It Fits, When It Doesn't

Use this if you need to interact with your private Calibre library using structured data calls. Specifically, if you need to audit the catalog structure, list books by a specific shelf ID, or generate device-ready metadata (Kobo). Don't use this if you just need to browse casually—the agent is best for programmatic data retrieval. If your goal is simply to view a single book's cover image, the web UI is faster. But if you need the data behind the view, use the agent's tools.

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Calibre-Web. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

VINKIUS INFRASTRUCTURE

Cloud Hosted

Managed infra

V8 Isolated

Sandboxed per request

Zero-Trust Proxy

No stored credentials

DLP Enforced

Policy on every call

GDPR Compliant

EU data residency

Token Compression

~60% cost reduction

How we secure it →

Works with Claude, ChatGPT, Cursor, and more

The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.

This server provides 3 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.

Available Capabilities

get_opds_catalog get_opds_shelf sync_kobo_library

Sifting through thousands of ebooks shouldn't feel like a deep web dive.

Before this server, checking your digital library meant logging into Calibre-Web and clicking through layers of categories, authors, and series. Finding the precise metadata for a collection or verifying the full scope of your catalog was a multi-click, copy-paste job, and you were always guessing if you missed a corner of the structure.

Now, your agent accesses the library's OPDS feed. You just ask: 'What books are on shelf 12?' The agent runs `get_opds_shelf` and gives you a clean, structured list. You get the data you need, immediately.

Calibre-Web MCP Server: Syncing and Cataloging Data

The manual steps that disappear are the need to jump between the web UI and a separate sync tool, or manually manage tokens. The agent handles the entire data flow—from checking the source metadata to generating the final Kobo-ready links.

It's not just reading; it's preparing. It takes the raw library data and makes it actionable for specific endpoints, whether that's the OPDS feed or a Kobo device. The process is complete in a single chat turn.

Common Questions About Calibre-Web MCP

How do I use the `get_opds_catalog` tool? +

Just ask your agent to 'Show me the full OPDS catalog.' This tool retrieves the main XML feed, giving you a structured view of all categories, series, and authors in your library.

What is the difference between `get_opds_catalog` and `get_opds_shelf`? +

The catalog shows everything—the whole library structure. get_opds_shelf only looks at one specific, curated collection (shelf ID). Use the latter when you know the exact grouping you want to inspect.

Does `sync_kobo_library` require specific credentials? +

Yes, it requires a Kobo Token. The tool uses this token to generate the necessary metadata and direct download links for syncing your collection to your Kobo e-reader.

Can I use the Calibre-Web MCP Server with other e-book tools? +

No, this server is built specifically for your Calibre-Web instance. It connects to the internal OPDS structure and Kobo sync endpoints of that specific service.

What kind of data does the Calibre-Web MCP Server retrieve? +

It retrieves structured data: OPDS XML feeds, book metadata, shelf contents, and sync-ready links. It's not a simple text search; it's structural data.

What happens if I use `get_opds_shelf` with an invalid shelf ID? +

The tool returns a specific error message detailing the invalid ID. This prevents the agent from attempting to process bad data and lets you know exactly what went wrong.

Does `sync_kobo_library` handle books that are missing metadata? +

It processes all available books, even if metadata is incomplete. The resulting data package will list the books found and indicate which fields were missing.

What is the best way to use `get_opds_catalog` for a very large library? +

For huge collections, start by getting the main OPDS feed, then use the agent to identify major categories. After that, use get_opds_shelf on the most important shelves to narrow the scope.

Can I browse my entire library structure through the AI? +

Yes. By using the get_opds_catalog tool, the agent retrieves the root XML feed of your Calibre-Web instance, allowing it to see categories, authors, and series as defined in your OPDS settings.

How do I list books from a specific custom shelf? +

You can use the get_opds_shelf tool by providing the specific shelf_id. The AI will then return the list of books and metadata associated with that particular shelf.

Does this support syncing my Kobo e-reader? +

Yes. If you provide your CALIBRE_WEB_KOBO_TOKEN, you can use the sync_kobo_library tool to get structured metadata and download links specifically formatted for Kobo device synchronization.

You might also like

Built & Managed by Vinkius 30s setup 3 tools

We've already built the connector for Calibre-Web. Just plug in your AI agents and start using Vinkius.

No hosting. No infrastructure. No complex setup.
All 3 tools are live and waiting. You're up and running in seconds.

Claude Claude
ChatGPT ChatGPT
Cursor Cursor
Gemini Gemini
Windsurf Windsurf
VS Code VS Code
JetBrains JetBrains
Vercel Vercel
+ other MCP clients

Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.

Zero hosting required Full MCP catalog included Enterprise-grade security Auto-updated by Vinkius

Built, hosted, and secured by Vinkius. You just connect and go.