Unichat MCP Server logo

Unichat MCP Server

by amidabuddha

The Unichat MCP Server allows you to send requests to various AI providers like OpenAI, MistralAI, and Anthropic using the MCP protocol. It supports tools and predefined prompts for tasks like code review and documentation.

View on GitHub

Last updated: N/A

What is Unichat MCP Server?

The Unichat MCP Server is a Python-based server that enables communication with multiple AI providers through the Model Context Protocol (MCP). It provides a standardized way to interact with different AI models using tools and predefined prompts, simplifying integration into applications like Claude Desktop.

How to use Unichat MCP Server?

To use the server, you need to configure it within your application (e.g., Claude Desktop) by specifying the server command, arguments, and environment variables, including the desired AI model and API key. You can also install it automatically via Smithery. The server exposes tools like unichat for sending requests and prompts like code_review, document_code, explain_code, and code_rework for specific tasks. Use the MCP Inspector to debug.

Key features of Unichat MCP Server

  • Supports multiple AI providers (OpenAI, MistralAI, Anthropic, etc.)

  • Implements the Model Context Protocol (MCP)

  • Provides predefined prompts for common tasks

  • Includes a tool for sending requests to Unichat

  • Easy installation via Smithery

  • Debugging support with MCP Inspector

Use cases of Unichat MCP Server

  • Integrating AI models into Claude Desktop

  • Automating code review processes

  • Generating code documentation

  • Explaining complex code snippets

  • Reworking code based on specified changes

FAQ from Unichat MCP Server

What is the MCP Inspector?

The MCP Inspector is a tool for debugging MCP servers that run over stdio. It allows you to inspect the communication between the client and the server.

How do I install the Unichat MCP Server?

You can install it manually by configuring your application or automatically using Smithery with the command npx -y @smithery/cli install unichat-mcp-server --client claude.

What API keys do I need?

You need the API keys for the AI providers you want to use, such as OpenAI, MistralAI, or Anthropic. These keys should be added to the server's environment variables.

How do I specify which AI model to use?

You can specify the AI model using the UNICHAT_MODEL environment variable. A list of supported models can be found in the unichat repository.

Where can I find the list of supported models?

A list of currently supported models to be used as SELECTED_UNICHAT_MODEL may be found here.