The full upstream README, mirrored here for reference. Install config, tool schemas, adoption signals, and an original overview live on the Didlogic MCP listing page.
A Model Context Protocol (MCP) server implementation for the Didlogic API. This server allows Large Language Models (LLMs) to interact with Didlogic services through a standardized interface.
When using uv no specific installation is needed. We will
use uvx to directly run didlogic_mcp.
Alternatively you can install didlogic_mcp via pip:
After installation, you can run it as a script using:
The server supports three transport modes:
For local integration with Claude Desktop or similar tools. Uses the DIDLOGIC_API_KEY environment variable for authentication.
For remote access and web clients. Requires Bearer token in Authorization header for each request.
Environment Variables:
PORT - Server port (default: 8000)DIDLOGIC_API_URL - Didlogic API base URL (default: https://app.didlogic.com/api)Note: In HTTP mode, clients must provide their API key as a Bearer token in the Authorization header.
For streaming communication with persistent connections. Ideal for real-time updates and streaming scenarios. Requires Bearer token in Authorization header for each request.
Environment Variables:
PORT - Server port (default: 8000)DIDLOGIC_API_URL - Didlogic API base URL (default: https://app.didlogic.com/api)Note: In SSE mode, clients must provide their API key as a Bearer token in the Authorization header for persistent streaming connections.
Add to your Claude settings:
For Claude Code, you can connect to a running SSE server instance:
Prerequisites:
python -m didlogic_mcp --transport sseYOUR_DIDLOGIC_API_KEY with your actual API keyCustom configuration:
http://localhost:8000/sse to match your server's PORT settinglocalhost with the server's hostname or IP addressMIT