lanyard-mcp-server
Provides Discord user presence information through the Lanyard API, enabling AI assistants to retrieve real-time presence data like online status, Spotify activity, and custom KV data.
README
Lanyard MCP Server
A Model Context Protocol (MCP) server that provides Discord user presence information through the Lanyard API.
Purpose
This MCP server provides a secure interface for AI assistants to retrieve real-time Discord presence data, including online status, Spotify activity, Discord activities, and custom KV data for Discord users via the Lanyard service.
Features
Current Implementation
get_user_presence- Get complete Discord presence information including status, platform info, Spotify, activities, and KV dataget_user_spotify- Get detailed Spotify listening information with track details and timestampsget_user_kv- Retrieve custom Lanyard KV (key-value) data set by the user
All tools include:
- Input sanitization and validation for Discord user IDs
- Formatted, human-readable output with emojis
- Proper error handling for API failures
- Rate limit detection
- Timeout handling
Prerequisites
- Docker Desktop with MCP Toolkit enabled
- Docker MCP CLI plugin (
docker mcpcommand) - Discord user IDs (17-20 digit numbers) of users who are using Lanyard
Installation
Step 1: Build the Docker Image
docker build -t lanyard-mcp-server:latest .
Step 2: Configure MCP Catalog
Copy the custom catalog configuration:
# Copy custom.yaml to your Docker MCP catalogs directory
cp custom.yaml ~/.docker/mcp/catalogs/custom.yaml
Step 3: VS Code Integration (Optional)
If using Visual Studio Code with MCP support:
# Copy the MCP configuration to your project
cp .vscode/mcp.json /path/to/your/project/.vscode/
Step 4: Import and Enable the Server
# Import the catalog
docker mcp catalog import custom.yaml
# Enable the Lanyard server
docker mcp server enable lanyard
Agent Prompts
When working with AI agents that have access to this MCP server, you can use these example commands:
Get User Presence Information
docker mcp tools call get_user_presence user_id=77488778255540224
Get Spotify Activity
docker mcp tools call get_user_spotify user_id=77488778255540224
Get Custom KV Data
docker mcp tools call get_user_kv user_id=77488778255540224
Usage Examples
In Claude Desktop, you can ask:
- "What is the Discord presence for user 77488778255540224?"
- "Is user 77488778255540224 listening to Spotify?"
- "Show me the custom KV data for Discord user 77488778255540224"
- "Get the current status and activities for user 77488778255540224"
- "What song is user 77488778255540224 listening to on Spotify?"
What is Lanyard?
Lanyard is a service that exposes Discord user presence data through a REST API and WebSocket. Users must opt-in by joining the Lanyard Discord server. This MCP server uses the REST API to fetch user presence information.
Architecture
AI Agent → MCP Gateway → Lanyard MCP Server → Lanyard API ↓ Discord Presence Data
Development
Local Testing
# Run directly
python lanyard_server.py
# Test MCP protocol
echo '{"jsonrpc":"2.0","method":"tools/list","id":1}' | python lanyard_server.py
# Test with a known user ID (Lanyard creator)
echo '{"jsonrpc":"2.0","method":"tools/call","params":{"name":"get_user_presence","arguments":{"user_id":"94490510688792576"}},"id":2}' | python lanyard_server.py
Adding New Tools
- Add the function to lanyard_server.py
- Decorate with @mcp.tool()
- Follow the pattern: single-line docstring, empty string defaults, return formatted string
- Update the catalog entry with the new tool name
- Rebuild the Docker image
Troubleshooting
Tools Not Appearing
- Verify Docker image built successfully:
docker images | grep lanyard - Check catalog and registry files in
~/.docker/mcp/catalogs/ - Ensure Claude Desktop config includes custom catalog
- Restart Claude Desktop completely
"User not found" Errors
- Verify the Discord user ID is correct (17-20 digits)
- Ensure the user has joined the Lanyard Discord server
- Check that the user hasn't opted out of Lanyard
Rate Limit Errors
- Lanyard API has rate limits
- Wait a few moments before retrying
- Consider implementing caching if making frequent requests
API Reference
This server uses the Lanyard REST API:
- Base URL: https://api.lanyard.rest/v1
- Endpoint: GET /users/:user_id
- Documentation: https://github.com/Phineas/lanyard
Security Considerations
- No authentication required (Lanyard API is public)
- User IDs are validated and sanitized before use
- Running as non-root user in Docker
- Request timeouts prevent hanging
- No sensitive data stored or logged
Future Enhancement Ideas
- WebSocket support for real-time updates
- Caching to reduce API calls
- Batch user lookups
- Historical presence tracking
- Activity statistics
- Custom formatting options
Testing
94490510688792576 - Phineas (Lanyard creator) 77488778255540224 - b6d (MCP integration)
Find more users by joining the Lanyard Discord server.
Limitations
- Requires users to opt-in by joining Lanyard Discord
- Subject to Lanyard API rate limits
- No real-time updates (REST only, not WebSocket)
- Presence data depends on Discord API availability
Resources
- Lanyard GitHub: https://github.com/Phineas/lanyard
- Lanyard Discord: https://discord.gg/lanyard
- MCP Documentation: https://modelcontextprotocol.io
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.