LLM Radar MCP Server

Example Use Cases

• 1

  Current and accurate AI model information from multiple providers.

• 2

  Compare AI models side-by-side with detailed capabilities and pricing.

• 3

  Query and filter models by provider, type, or modality support.

Description

LLM Radar is an MCP server that fetches fresh AI model data daily from OpenAI, Anthropic, and Google APIs, enriches it with Claude for better descriptions, and exposes it via the Model Context Protocol for any compatible client. It solves the problem of outdated AI model knowledge in assistants by providing current model details, pricing, capabilities, and recommendations. The server supports multiple connection methods including stdio and HTTP/SSE, and can be self-hosted via Docker or other platforms.