Unichat MCP Server
The Unichat MCP Server enables sending requests to multiple AI providers
🔌 MCP Tools
Overview
Unichat MCP Server
The Unichat MCP Server is a Python-based implementation (also available in TypeScript) that enables sending requests to multiple AI providers including OpenAI, MistralAI, Anthropic, xAI, Google AI, and DeepSeek using the Model Context Protocol (MCP).
Core Features
Main Tool The server provides a single tool called "unichat" that handles message requests and returns responses.
Built-in Prompts
- Code Review: Analyzes code for best practices and potential improvements
- Document Code: Generates comprehensive code documentation
- Explain Code: Provides detailed code explanations
- Code Rework: Implements requested code modifications
Configuration
Installation Options
- Quick installation via Smithery:
npx -y @smithery/cli install unichat-mcp-server --client claude
Environment Setup Configuration requires:
- Selection of a supported AI model as SELECTED_UNICHAT_MODEL
- Valid API key as YOUR_UNICHAT_API_KEY
Development Tools
Debugging The MCP Inspector provides enhanced debugging capabilities:
npx @modelcontextprotocol/inspector uv --directory {{your source code local directory}}/unichat-mcp-server run unichat-mcp-server
Build Process Package preparation involves:
uv sync
uv build
uv publish --token {{YOUR_PYPI_API_TOKEN}}