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
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。