Books API MCP Server
MCP server that exposes book management tools for AI assistants, enabling CRUD operations on book collections through a .NET Books API backend.
README
Books API MCP Server
A Model Context Protocol (MCP) server that exposes book management tools for AI assistants. This server provides a bridge between AI applications and a .NET Books API, enabling seamless book collection management through standardized MCP tool calls.
The .NET Book API backend that this MCP server interacts with is available at: https://github.com/0x1D-1983/book-api.
Features
- MCP Protocol Support: Implements Model Context Protocol for tool discovery and execution
- RESTful API Integration: Connects to a .NET Books API backend
- Comprehensive CRUD Operations: Full Create, Read, Update, and Delete functionality for books
- FastAPI Framework: Modern, fast, and easy-to-maintain Python web framework
- Type-Safe Models: Uses Pydantic for robust data validation
- Error Handling: Comprehensive error handling with clear error messages
Available Tools
The MCP server exposes the following tools:
1. list_books
Retrieve all books from the database.
Parameters:
- None
Returns:
- Array of book objects with the following fields:
id(integer): Unique book identifiertitle(string): Book titleauthor(string): Book authorisbn(string): International Standard Book NumberpublishedDate(string): Publication date in ISO 8601 formatcreatedAt(string): Record creation timestamp
Example Usage:
result = BookService.list_books()
# Returns: List of all books in the database
2. get_book
Retrieve a specific book by its ID.
Parameters:
book_id(integer, required): The unique identifier of the book to retrieve
Returns:
- Book object with full details, or error if book not found
Example Usage:
result = BookService.get_book(1)
# Returns: Book with ID 1
3. create_book
Create a new book in the database.
Parameters:
book_data(object, required): Book information object containing:id(integer, optional): Unique identifier for the booktitle(string, required): Title of the bookauthor(string, required): Author of the bookisbn(string, optional): ISBN of the bookpublishedDate(string, optional): Publication date in ISO 8601 UTC format (must end with 'Z', e.g.,2024-04-11T00:00:00Z)
Returns:
- Created book object with all fields including generated
createdAttimestamp
Example Usage:
book_data = {
"title": "The Great Gatsby",
"author": "F. Scott Fitzgerald",
"isbn": "978-0743273565",
"publishedDate": "1925-04-10T00:00:00Z"
}
result = BookService.create_book(book_data)
Important: The publishedDate field must be in ISO 8601 UTC format ending with 'Z' to ensure PostgreSQL compatibility.
4. update_book
Update an existing book's information.
Parameters:
book_id(integer, required): The unique identifier of the book to updatebook_data(object, required): Updated book information object containing:id(integer): ID of the book (must matchbook_id)title(string, optional): New titleauthor(string, optional): New authorisbn(string, optional): New ISBNpublishedDate(string, optional): New publication date in ISO 8601 UTC format (must end with 'Z')
Returns:
- Success message if update was successful, or error if book not found
Example Usage:
book_data = {
"id": 1,
"title": "Updated Title",
"author": "Updated Author",
"isbn": "978-1234567890",
"publishedDate": "2023-01-01T00:00:00Z"
}
result = BookService.update_book(1, book_data)
5. delete_book
Delete a book from the database.
Parameters:
book_id(integer, required): The unique identifier of the book to delete
Returns:
- Success message if deletion was successful, or error if book not found
Example Usage:
result = BookService.delete_book(1)
# Returns: Success message confirming deletion
Setup Instructions
Prerequisites
- Python 3.8 or higher
- Access to a running Books API instance (default:
http://localhost:5288) - Virtual environment (recommended)
Installation
-
Clone or navigate to the project directory:
cd book-api-mcp-server -
Create and activate a virtual environment:
python3 -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate -
Install dependencies:
pip install fastapi uvicorn requests pydanticOr if you have a
requirements.txtfile:pip install -r requirements.txt -
Configure the Books API URL:
Edit
services.pyand update theBOOKS_API_URLconstant if your Books API is running on a different host/port:BOOKS_API_URL = "http://localhost:5288" # Update as needed -
Run the server:
python run.pyThe server will start on
http://0.0.0.0:8080by default.You can customize the host and port using environment variables:
export MCP_SERVER_HOST=localhost export MCP_SERVER_PORT=8080 python run.py
Testing the Server
-
Check server health:
curl http://localhost:8080/health -
List available tools:
curl http://localhost:8080/tools -
Run the test suite:
python test_tools.py
Configuration
Environment Variables
MCP_SERVER_HOST: Server host address (default:0.0.0.0)MCP_SERVER_PORT: Server port number (default:8080)BOOKS_API_URL: Base URL of the Books API (configured inservices.py, default:http://localhost:5288)
Cursor Integration
To use this MCP server with Cursor, add the following to your ~/.cursor/mcp.json:
{
"mcpServers": {
"books-api": {
"command": "python3",
"args": ["/path/to/book-api-mcp-server/run.py"]
}
}
}
Note: Restart Cursor after updating the MCP configuration for changes to take effect.
API Endpoints
The MCP server exposes the following HTTP endpoints:
GET /: Root endpoint with server informationGET /tools: List all available MCP toolsPOST /tool-calls: Execute one or more tool callsGET /health: Health check endpointGET /docs: Interactive API documentation (FastAPI Swagger UI)
Usage Examples
Using Python Client
from services import BookService
import json
# List all books
books = BookService.list_books()
print(json.dumps(books.result, indent=2))
# Get a specific book
book = BookService.get_book(1)
print(json.dumps(book.result, indent=2))
# Create a new book
new_book = {
"title": "1984",
"author": "George Orwell",
"isbn": "978-0451524935",
"publishedDate": "1949-06-08T00:00:00Z"
}
result = BookService.create_book(new_book)
print(json.dumps(result.result, indent=2))
# Update a book
updated_data = {
"id": 1,
"title": "Nineteen Eighty-Four",
"author": "George Orwell"
}
result = BookService.update_book(1, updated_data)
# Delete a book
result = BookService.delete_book(1)
Using HTTP API
# List all tools
curl http://localhost:8080/tools
# Call a tool
curl -X POST http://localhost:8080/tool-calls \
-H "Content-Type: application/json" \
-d '{
"tool_calls": [
{
"name": "list_books",
"parameters": {}
}
]
}'
Project Structure
book-api-mcp-server/
├── main.py # FastAPI application and server setup
├── routes.py # API route handlers for MCP endpoints
├── tools.py # Tool definitions and schemas
├── services.py # Business logic and Books API integration
├── models.py # Pydantic models for data validation
├── config.py # Configuration settings
├── run.py # Server entry point
├── test_tools.py # Test suite for validating tools
├── requirements.txt # Python dependencies
└── README.md # This file
Date Format Requirements
Important: All date fields (publishedDate) must be provided in ISO 8601 UTC format ending with 'Z'. This is required for PostgreSQL compatibility.
Correct Format:
2024-04-11T00:00:00Z2023-05-11T12:30:45Z
Incorrect Formats (will cause errors):
2024-04-11T00:00:00(missing 'Z')2024-04-11(not full ISO 8601)04/11/2024(not ISO 8601)
Technologies
- Python 3.8+: Programming language
- FastAPI: Modern web framework for building APIs
- Uvicorn: ASGI server for running FastAPI
- Pydantic: Data validation using Python type annotations
- Requests: HTTP library for making API calls to the Books API
Error Handling
All tools return a ToolCallResult object with the following structure:
{
"result": <data> | None, # Result data if successful
"error": <string> | None # Error message if operation failed
}
Common error scenarios:
- 404 Not Found: Book with specified ID does not exist
- 400 Bad Request: Invalid input data (e.g., missing required fields, invalid date format)
- 500 Server Error: Database or API connection issues
- Connection Error: Books API is not accessible
Troubleshooting
Server won't start
- Check if port 8080 is already in use
- Verify Python version (3.8+)
- Ensure all dependencies are installed
Tools return connection errors
- Verify the Books API is running and accessible
- Check the
BOOKS_API_URLinservices.py - Test the Books API directly:
curl http://localhost:5288/books
Date format errors
- Ensure all dates end with 'Z' for UTC timezone
- Use full ISO 8601 format:
YYYY-MM-DDTHH:MM:SSZ
License
This project is part of a book management system demonstration.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.