Unichat

Route requests to multiple AI vendors via MCP using predefined prompts and tools.

typescript

0

GitHub Stars

typescript

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "mcp-mirror-amidabuddha_unichat-ts-mcp-server": {
      "command": "node",
      "args": [
        "{{/path/to}}/unichat-ts-mcp-server/build/index.js"
      ],
      "env": {
        "UNICHAT_MODEL": "YOUR_PREFERRED_MODEL_NAME",
        "UNICHAT_API_KEY": "YOUR_VENDOR_API_KEY"
      }
    }
  }
}

You can run the Unichat MCP Server to route requests to several AI vendors using the MCP protocol. It supports both local (stdio) and SSE transport, letting you integrate chat-style prompts and tooling into your client apps or desktop integrations with ease.

How to use

Start the server locally or use a published version, then connect to it with your MCP client. By default, it runs over stdio, and you can opt into SSE for streaming support by adding a --sse flag. You configure the server in your MCP client so it knows how to start and where to connect. Use the provided environment variables to specify which AI model you want and to supply your API key.

How to install

Prerequisites: you need Node.js and npm installed on your system.

# Install dependencies
npm install

# Build the server
npm run build

# Optional: enable auto-rebuild during development
npm run watch

Configuration and usage notes

Two MCP connection options are shown for this server. You can run locally (stdio) or use a published version with npx. Each option requires you to specify the command, arguments, and environment variables.

Available tools

unichat

Send a request to Unichat. Requires a string argument named messages and returns the model's response.

code_review

Review code for best practices, potential issues, and improvements. Requires code (string) as an argument.

document_code

Generate documentation for code, including docstrings and comments. Requires code (string) as an argument.

explain_code

Explain how a piece of code works in detail. Requires code (string) as an argument.

code_rework

Apply requested changes to the provided code. Requires changes (string, optional) and code (string) as arguments.