Agentrpc

🚀 AgentRPC Proxy

A universal RPC layer for AI agents across network boundaries and languages

AgentRPC enables you to connect to any function in any language,跨越网络边界. It's ideal for using services in the following environments:

• Private VPCs
• Kubernetes clusters
• Multiple cloud environments

AgentRPC wraps your functions in a universal RPC interface and connects them to a hosted RPC server, accessible via open standards:

• Model Context Protocol (MCP)
• OpenAI-compatible tool definitions (OpenAI, Anthropic, LiteLLM, OpenRouter, etc.)

🚀 Quick Start

Start Quickly

Follow the Quick Start example on our documentation site.

Examples

Explore real working examples in the examples directory.

✨ Features

📚 Documentation

Overview

AgentRPC allows you to connect to any function in any language,跨越网络边界. It's well-suited for using services in the following environments:

• Private VPCs
• Kubernetes clusters
• Multiple cloud environments

AgentRPC wraps your functions in a universal RPC interface and connects them to a hosted RPC server, accessible via open standards:

• Model Context Protocol (MCP)
• OpenAI-compatible tool definitions (OpenAI, Anthropic, LiteLLM, OpenRouter, etc.)

How It Works

1. Registration: Register functions and APIs in any language using our SDK.
2. Management: The AgentRPC platform (api.agentrpc.com) registers functions and monitors their health.
3. Access: Receive OpenAPI SDK-compatible tool definitions and a hosted MCP server for connecting with compatible agents.

💻 Usage Examples

MCP Server

The AgentRPC TypeScript SDK includes an optional MCP (Model Context Protocol) server.

ANGENTRPC_API_SECRET=YOUR_API_SECRET npx agentrpc mcp

This will start an MCP-compliant server for external AI models to interact with your registered tools.

Claude Desktop Integration

Add the following to claude_desktop_config.json:

{
  "mcpServers": {
    "agentrpc": {
      "command": "npx",
      "args": [
        "-y",
        "agentrpc",
        "mcp"
      ],
      "env": {
        "AGENTRPC_API_SECRET": "<YOUR_API_SECRET>"
      }
    }
  }
}

More Information

Cursor Integration

Add the following to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "agentrpc": {
      "command": "npx",
      "args": ["-y", "agentrpc", "mcp"],
      "env": {
        "AGENTRPC_API_SECRET": "<YOUR_API_SECRET>"
      }
    }
  }
}

More Information

📄 License

This project is licensed under the Apache License 2.0. Please refer to the LICENSE file for details. This repository contains all open-source components and SDKs of AgentRPC.