- MCP Open Library
MCP Open Library
MCP Open Library
A Model Context Protocol (MCP) server for the Open Library API that enables AI assistants to search for book and author information.
Overview
This project implements an MCP server that provides tools for AI assistants to interact with the Open Library. It allows searching for book information by title, searching for authors by name, retrieving detailed author information using their Open Library key, and getting URLs for author photos using their Open Library ID (OLID). The server returns structured data for book and author information.
Features
- Book Search by Title: Search for books using their title and get detailed information
- Author Search by Name: Search for authors using their name and get relevant details
- Structured Response Format: Returns book and author information in a consistent JSON structure
- Error Handling: Proper validation and error reporting
- Testing: Comprehensive test coverage with Vitest
Installation
# Clone the repository
git clone https://github.com/your-username/mcp-open-library.git
cd mcp-open-library
# Install dependencies
npm install
# Build the project
npm run build
Usage
Running the Server
You can use the MCP Inspector to test the server:
npm run inspector
Access the MCP Inspector and then test the tool e.g.

Using with an MCP Client
This server implements the Model Context Protocol, which means it can be used by any MCP-compatible AI assistant or client e.g. Claude Desktop. The server exposes the following tools:
get_book_by_title: Search for book information by titleget_authors_by_name: Search for author information by nameget_author_info: Get detailed information for a specific author using their Open Library Author Keyget_author_photo: Get the URL for an author's photo using their Open Library Author ID (OLID)
Example get_book_by_title input:
{
"title": "The Hobbit"
}
Example get_book_by_title output:
[
{
"title": "The Hobbit",
"authors": [
"J. R. R. Tolkien"
],
"first_publish_year": 1937,
"open_library_work_key": "/works/OL45883W",
"edition_count": 120,
"cover_url": "https://covers.openlibrary.org/b/id/10581294-M.jpg"
}
]
Example get_authors_by_name input:
{
"name": "J.R.R. Tolkien"
}
Example get_authors_by_name output:
[
{
"key": "OL26320A",
"name": "J. R. R. Tolkien",
"alternate_names": [
"John Ronald Reuel Tolkien"
],
"birth_date": "3 January 1892",
"top_work": "The Hobbit",
"work_count": 648
}
]
Example get_author_info input:
{
"author_key": "OL26320A"
}
Example get_author_info output:
{
"name": "J. R. R. Tolkien",
"personal_name": "John Ronald Reuel Tolkien",
"birth_date": "3 January 1892",
"death_date": "2 September 1973",
"bio": "John Ronald Reuel Tolkien (1892-1973) was a major scholar of the English language, specializing in Old and Middle English. He served as the Rawlinson and Bosworth Professor of Anglo-Saxon and later the Merton Professor of English Language and Literature at Oxford University.",
"alternate_names": ["John Ronald Reuel Tolkien"],
"photos": [6791763],
"key": "/authors/OL26320A",
"remote_ids": {
"viaf": "95218067",
"wikidata": "Q892"
},
"revision": 43,
"last_modified": {
"type": "/type/datetime",
"value": "2023-02-12T05:50:22.881"
}
}
Example get_author_photo input:
{
"olid": "OL26320A"
}
Example get_author_photo output:
https://covers.openlibrary.org/a/olid/OL26320A-L.jpg
An example of this tool being used in Claude Desktop can be see here:
Docker
You can test this MCP server using Docker. To do this first run:
docker build -t mcp-open-library .
docker run -p 8080:8080 mcp-open-library
You can then test the server running within Docker via the inspector e.g.
pnpm run inspector http://localhost:8080
Development
Project Structure
src/index.ts- Main server implementationsrc/types.ts- TypeScript type definitionssrc/index.test.ts- Test suite
Available Scripts
npm run build- Build the TypeScript codenpm run watch- Watch for changes and rebuildnpm test- Run the test suitenpm run format- Format code with Prettiernpm run inspector- Run the MCP Inspector against the server
Running Tests
npm test
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.