LiteLLM MCP Server Bridge
Connects Antigravity to a LiteLLM instance, enabling chat completions, model listing, health checks, and more via the Model Context Protocol.
README
LiteLLM MCP Server Bridge
A Model Context Protocol (MCP) server that connects Antigravity to your deployed LiteLLM instance.
Features
This MCP server provides the following tools:
- chat_completion - Generate chat completions using any model in your LiteLLM instance
- completion - Generate text completions using the legacy endpoint
- list_models - List all available models
- health_check - Check LiteLLM instance health status
- create_embedding - Generate embeddings
- model_info - Get detailed information about a specific model
- create_image - Generate images using models available in your instance
- create_speech - Generate speech audio from text (TTS)
- rerank - Rerank documents based on a search query
- key_generate - Generate a new LiteLLM Proxy API key (admin feature)
- key_info - Get details and spend info for a LiteLLM Proxy API key (admin feature)
Setup
1. Configure Antigravity
Add the following to your Antigravity MCP configuration. This will use npx to fetch and run the latest version of the published package on-the-fly.
{
"mcpServers": {
"litellm": {
"command": "npx",
"args": [
"-y",
"litellm-mcp-server@latest"
],
"env": {
"LITELLM_BASE_URL": "https://your-litellm-url",
"LITELLM_API_KEY": "your-api-key-here"
}
}
}
}
2. Set Your Secrets
Replace your-litellm-url and your-api-key-here in the configuration with your actual LiteLLM Base URL and API key.
Usage Examples
Once configured, you can use the MCP tools in Antigravity:
Chat Completion
Use the chat_completion tool to generate a response using gpt-4
List Models
Use the list_models tool to see what models are available
Health Check
Use the health_check tool to verify the LiteLLM instance is running
Environment Variables
LITELLM_BASE_URL- Your LiteLLM instance URLLITELLM_API_KEY- Your LiteLLM API key for authentication
Troubleshooting
Server won't start
- Ensure Node.js is installed:
node --version - Check dependencies are installed:
npm install - Verify the script path in your Antigravity config is correct
- Check that your API key is valid
Connection errors
- Verify your LiteLLM instance is accessible:
curl https://your-litellm-url/health - Check your API key has proper permissions
- Ensure your network allows connections to the LiteLLM instance
Tool not showing up
- Restart Antigravity after adding the MCP server configuration
- Check Antigravity logs for any error messages
- Verify the JSON configuration is valid
Architecture
The MCP server acts as a bridge:
Antigravity ←→ MCP Server (this script) ←→ LiteLLM Instance
All requests from Antigravity are forwarded to your LiteLLM instance with proper authentication headers.
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.