cds-mcp
MCP server for searching and retrieving documents, metadata, and files from CERN Document Server (CDS) with optional CERN SSO authentication.
README
CDS MCP Server
A Model Context Protocol (MCP) server for integrating with CERN Document Server (CDS), built on the Invenio digital library framework.
Features
- Search CDS documents with filters for experiments, document types, and date ranges
- Get detailed document information including full abstracts, authors, and metadata
- Access document files with download URLs and file metadata
- Browse experiments and document types for better search filtering
Installation
Requires Python 3.10+.
Quickstart (recommended)
No installation needed, just use uvx to run directly:
uvx cds-mcp
From PyPI
pip install cds-mcp
From source
git clone https://github.com/MohamedElashri/cds-mcp
cd cds-mcp
uv sync
Usage
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"cds": {
"command": "uvx",
"args": ["cds-mcp"],
"env": {
"CERN_CLIENT_ID": "your-client-id",
"CERN_CLIENT_SECRET": "your-client-secret"
}
}
}
}
For public access only, omit the authentication environment variables:
{
"mcpServers": {
"cds": {
"command": "uvx",
"args": ["cds-mcp"]
}
}
}
Note for macOS users: If you see an error about uvx not being found, you may need to provide the absolute path. Claude Desktop does not support ~ or $HOME expansion.
- Run
which uvxin your terminal to find the path (e.g.,/Users/yourusername/.local/bin/uvx). - Use that absolute path in the
commandfield:
"command": "/Users/yourusername/.local/bin/uvx"
Claude Code
Project-specific (default) — installs in the current directory's configuration:
claude mcp add cds-mcp -- uvx cds-mcp
Global — installs for your user account (works in all projects):
claude mcp add --scope user cds-mcp -- uvx cds-mcp
To include authentication, add the CERN credentials before the --:
# Example: Global installation with CERN SSO authentication
claude mcp add --scope user -e CERN_CLIENT_ID=your_client_id -e CERN_CLIENT_SECRET=your_client_secret cds-mcp -- uvx cds-mcp
Manual Configuration — you can also manually edit your global config at ~/.claude.json (on Linux/macOS) or %APPDATA%\Claude\claude.json (on Windows):
{
"mcpServers": {
"cds": {
"command": "uvx",
"args": ["cds-mcp"],
"env": {
"CERN_CLIENT_ID": "your_client_id",
"CERN_CLIENT_SECRET": "your_client_secret"
}
}
}
}
GitHub Copilot
Add to your VS Code settings.json:
{
"mcp": {
"servers": {
"cds": {
"command": "uvx",
"args": ["cds-mcp"],
"env": {
"CERN_CLIENT_ID": "your_client_id",
"CERN_CLIENT_SECRET": "your_client_secret"
}
}
}
}
}
Or add a .vscode/mcp.json to your project:
{
"servers": {
"cds": {
"command": "uvx",
"args": ["cds-mcp"],
"env": {
"CERN_CLIENT_ID": "your_client_id",
"CERN_CLIENT_SECRET": "your_client_secret"
}
}
}
}
Gemini CLI
Add to your ~/.gemini/settings.json:
{
"mcpServers": {
"cds": {
"command": "uvx",
"args": ["cds-mcp"],
"env": {
"CERN_CLIENT_ID": "your_client_id",
"CERN_CLIENT_SECRET": "your_client_secret"
}
}
}
}
Direct usage
# Run with uvx (no install needed)
uvx cds-mcp
# Or if installed from PyPI
cds-mcp
# Or from source
uv run cds-mcp
# With CERN SSO authentication
CERN_CLIENT_ID=your_client_id CERN_CLIENT_SECRET=your_client_secret uvx cds-mcp
Authentication & Access Control
CERN SSO Authentication (Recommended)
The CDS MCP server now supports proper CERN SSO authentication using OAuth2/OIDC for accessing restricted content.
Setup Instructions
-
Register your application in the CERN Application Portal:
- Create a new OIDC application
- Select "Confidential Client" type
- Note your
Client IDandClient Secret
-
Configure authentication by setting environment variables:
export CERN_CLIENT_ID="your-client-id" export CERN_CLIENT_SECRET="your-client-secret" -
Use with MCP clients - the server will automatically handle token acquisition and refresh.
Supported Access Levels
- Public Records: Available without authentication
- Restricted Collections: Requires CERN SSO authentication and appropriate experiment membership
- ATLAS: Internal Notes, Communications, Conference Slides
- CMS: Internal Notes, Analysis Notes
- LHCb: Internal Notes, Analysis Notes
- ALICE: Internal Notes, Analysis Notes
Tools
search_cds_documents: Search CDS with various filtersget_cds_document_details: Get detailed information about a specific documentget_cds_document_files: Get file information and download URLsget_cds_experiments: List available CERN experiments for filteringget_cds_document_types: List available document types for filtering
Development
git clone https://github.com/MohamedElashri/cds-mcp
cd cds-mcp
uv sync
uv run python tests/test_integration.py # Test real CDS API integration
uv run python tests/test_mcp_server.py # Test MCP server functionality
License
MIT License - see LICENSE for details.
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
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
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.