Skip to main content

A Model Context Protocol (MCP) server for Library of Congress Subject Headings and Name Authorities.

Project description

cataloger mcp server

A Model Context Protocol (MCP) server that provides access to the Library of Congress Subject Headings (LCSH) through a simple API interface.

Overview

This MCP server allows AI assistants like Claude to search the Library of Congress Subject Headings (LCSH) using the public suggest2 API. It provides a clean interface for querying LCSH data and handling the various response formats from the API.

Installation

Option 1: Install from PyPI (Recommended)

The easiest way to install the cataloger mcp server is directly from PyPI:

pip install cataloger-mcp-server

Option 2: Install from Source

If you prefer to install from source:

git clone https://github.com/kltng/cataloger-mcp-server.git
cd cataloger-mcp-server
pip install -e .

Setting up with Claude Desktop

  1. Install Claude Desktop if you haven't already from https://claude.ai/desktop

  2. Install the cataloger mcp server using one of the installation methods above

  3. Open Claude Desktop and navigate to Settings:

    • Click on your profile picture in the bottom-left corner
    • Select "Settings" from the menu
  4. Configure the MCP Server:

    • In the Settings panel, click on "MCP Servers"
    • Click "Add Server"
    • Fill in the following details:
      • Name: cataloger mcp search
      • Command: cataloger-mcp-server
    • Click "Save"
  5. Enable the Server:

    • Toggle the switch next to the cataloger mcp search server to enable it
    • Claude will now have access to the LCSH search capabilities

Using the cataloger mcp server with Claude

Once the server is set up and enabled in Claude Desktop, you can ask Claude to search for Library of Congress Subject Headings. Here are some example prompts:

  • "Can you search the Library of Congress Subject Headings for 'artificial intelligence'?"
  • "Look up 'climate change' in LCSH and tell me the official subject headings."
  • "What are the LCSH terms related to 'quantum computing'?"

Claude will use the MCP server to query the LCSH and LCNAF databases and return the results.

  • "Find the name authority record for 'Smith, John Adam'."

Features

  • MCP Tool Integration: Exposes search_lcsh (for subject headings) and search_name_authority (for personal names) tools that can be used by AI assistants.
  • Resource Endpoints: Provides resource endpoints at lcsh://search/{query} and lcnaf://search/{query}.
  • Robust Error Handling: Gracefully handles API errors, connection issues, and unexpected response formats
  • Multiple Response Formats: Supports both dictionary (hits) and list response formats from the LCSH API

Troubleshooting

If you encounter issues with the MCP server:

  1. Check Server Status: In Claude Desktop, go to Settings > MCP Servers and check if the server is enabled and running
  2. Restart the Server: Toggle the server off and on again
  3. Check Console Output: If running the server manually, check the console output for any error messages
  4. Verify Network Connection: Ensure your computer has an active internet connection to access the LCSH API

License

This project is licensed under the MIT License - see the LICENSE file for details.

For Developers

For more detailed documentation about the server implementation, API references, and testing information, please refer to the references.md file.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

cataloger_mcp_server-0.1.4.tar.gz (22.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

cataloger_mcp_server-0.1.4-py3-none-any.whl (6.7 kB view details)

Uploaded Python 3

File details

Details for the file cataloger_mcp_server-0.1.4.tar.gz.

File metadata

  • Download URL: cataloger_mcp_server-0.1.4.tar.gz
  • Upload date:
  • Size: 22.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.8

File hashes

Hashes for cataloger_mcp_server-0.1.4.tar.gz
Algorithm Hash digest
SHA256 7a3acb92fb45c8c0cda31335ec8b69f2330ec7837a57a949b49336d2ba05c36c
MD5 b3e7e459c1ba37608549606264fe7849
BLAKE2b-256 2625c24e8d52b86060956fddd8a882632c5e27fafd2a13c3e1509d37c95fb396

See more details on using hashes here.

File details

Details for the file cataloger_mcp_server-0.1.4-py3-none-any.whl.

File metadata

File hashes

Hashes for cataloger_mcp_server-0.1.4-py3-none-any.whl
Algorithm Hash digest
SHA256 26cf8a3a28cffacea276f31f5d07c7094c1ae11d19b01e0bd6ca6a3dd3e4b7f7
MD5 d918a0f0e35ae52244db062f3c812af1
BLAKE2b-256 aaa705f41fdad88bfdfecb835c91186fd51ab74ecaae9236c881de284f1395bc

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page