UniChat MCP Server

v1.0.0Coding Agentsstable

🐍/📇 ☁️ - Send requests to OpenAI, MistralAI, Anthropic, xAI, Google AI or DeepSeek using MCP protocol via tool or predefined prompts. Vendor API key required

unichat-mcp-servermcpai-integration
Share:
37
Stars
0
Downloads
0
Weekly
0/5

What is UniChat MCP Server?

UniChat MCP Server is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 🐍/📇 ☁️ - send requests to openai, mistralai, anthropic, xai, google ai or deepseek using mcp protocol via tool or predefined prompts. vendor api key required

🐍/📇 ☁️ - Send requests to OpenAI, MistralAI, Anthropic, xAI, Google AI or DeepSeek using MCP protocol via tool or predefined prompts. Vendor API key required

This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • 🐍/📇 ☁️ - Send requests to OpenAI, MistralAI, Anthropic, xAI,

Use Cases

Send requests to multiple AI providers
Support OpenAI, Claude, Gemini
amidabuddha

Maintainer

LicenseMIT License
Languagepython
Versionv1.0.0
UpdatedMar 30, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx unichat-mcp-server

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use UniChat MCP Server

Unichat MCP Server is a Python-based MCP server that acts as a universal AI provider gateway, allowing Claude and other MCP clients to send requests to OpenAI, MistralAI, Anthropic, xAI (Grok), Google AI (Gemini), and DeepSeek through a single consistent interface. It exposes one tool (unichat) and four predefined prompts for common coding tasks — code review, documentation generation, code explanation, and code rework — making it practical for developers who want to compare responses across providers or route specific tasks to the best model for the job, all without leaving their primary AI client.

Prerequisites

  • Python 3.10+ and uv or uvx package manager installed
  • An API key from at least one supported provider: OpenAI, MistralAI, Anthropic, xAI, Google AI, or DeepSeek
  • The UNICHAT_MODEL environment variable set to a valid model ID for your chosen provider
  • An MCP-compatible client such as Claude Desktop
1

Install via Smithery (recommended)

The fastest way to install and configure Unichat MCP Server for Claude Desktop is via Smithery, which handles installation and config file updates automatically.

npx -y @smithery/cli install unichat-mcp-server --client claude
2

Or install manually with uvx

If you prefer manual setup, use uvx to run the published package directly without a separate install step.

uvx unichat-mcp-server
3

Obtain an API key from your chosen provider

Get an API key from the provider whose model you want to use: platform.openai.com for OpenAI, console.anthropic.com for Anthropic, console.mistral.ai for MistralAI, aistudio.google.com for Gemini, or console.x.ai for xAI. The key goes in UNICHAT_API_KEY.

4

Add the server to Claude Desktop config

Edit claude_desktop_config.json to add the Unichat server. Set UNICHAT_MODEL to the exact model ID you want to use and UNICHAT_API_KEY to the vendor key. UNICHAT_BASE_URL is only needed for custom OpenAI-compatible endpoints.

{
  "mcpServers": {
    "unichat-mcp-server": {
      "command": "uvx",
      "args": ["unichat-mcp-server"],
      "env": {
        "UNICHAT_MODEL": "gpt-4o",
        "UNICHAT_API_KEY": "your_api_key_here"
      }
    }
  }
}
5

Restart Claude Desktop and test

Restart Claude Desktop. The unichat tool and four predefined prompts (code_review, document_code, explain_code, code_rework) will be available. Ask Claude to send a test message via unichat to verify connectivity.

UniChat MCP Server Examples

Client configuration

Claude Desktop config using uvx to run unichat-mcp-server with OpenAI's gpt-4o model. Change UNICHAT_MODEL and UNICHAT_API_KEY to use a different provider.

{
  "mcpServers": {
    "unichat-mcp-server": {
      "command": "uvx",
      "args": ["unichat-mcp-server"],
      "env": {
        "UNICHAT_MODEL": "gpt-4o",
        "UNICHAT_API_KEY": "sk-your-openai-key-here"
      }
    }
  }
}

Prompts to try

Example prompts using both the unichat tool and the four predefined prompt templates for coding tasks.

- "Use the unichat tool to ask GPT-4o: what are the key differences between TCP and UDP?"
- "Use the code_review prompt to review this Python function: def add(a, b): return a + b"
- "Use document_code to generate docstrings for my authentication module"
- "Use explain_code to walk me through how this recursive fibonacci implementation works"
- "Use code_rework to refactor this SQL query to use parameterized inputs instead of string concatenation"

Troubleshooting UniChat MCP Server

Server returns 'invalid model' or 'model not found' error

The UNICHAT_MODEL value must be an exact model identifier supported by the provider whose UNICHAT_API_KEY you provided — for example 'gpt-4o' for OpenAI, 'claude-3-5-sonnet-20241022' for Anthropic, 'gemini-1.5-pro' for Google. Check the provider's documentation for current model IDs.

uvx command not found

uvx is part of the uv toolchain. Install it with: curl -LsSf https://astral.sh/uv/install.sh | sh (macOS/Linux) or irm https://astral.sh/uv/install.ps1 | iex (Windows PowerShell). Then restart your shell and try again.

API requests fail with 'authentication failed' even though the key looks correct

Each provider requires its own key format — OpenAI keys start with 'sk-', Anthropic keys start with 'sk-ant-', etc. Ensure you are not mixing up keys between providers. The UNICHAT_API_KEY must correspond to the provider that serves the model in UNICHAT_MODEL.

Frequently Asked Questions about UniChat MCP Server

What is UniChat MCP Server?

UniChat MCP Server is a Model Context Protocol (MCP) server that 🐍/📇 ☁️ - send requests to openai, mistralai, anthropic, xai, google ai or deepseek using mcp protocol via tool or predefined prompts. vendor api key required It connects AI assistants to external tools and data sources through a standardized interface.

How do I install UniChat MCP Server?

Follow the installation instructions on the UniChat MCP Server GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with UniChat MCP Server?

UniChat MCP Server works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is UniChat MCP Server free to use?

Yes, UniChat MCP Server is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.

Browse More Coding Agents MCP Servers

Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "unichat-mcp-server": { "command": "npx", "args": ["-y", "unichat-mcp-server"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use UniChat MCP Server?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides