AgentRPC MCP Server

Connect to any function, any language, across network boundaries using AgentRPC.

Remote serverstreamable-httpPython

What is the AgentRPC MCP server?

Agentrpc mcp server connects AgentRPC to AI assistants that speak the Model Context Protocol. Connect to any function, any language, across network boundaries using AgentRPC.

What AgentRPC does

AgentRPC allows you to connect to any function, in any language, across network boundaries. It's ideal when you have services deployed in: - Private VPCs - Kubernetes clusters - Multiple cloud environments

Tools it exposes

Once connected, the assistant can call these 3 tools directly:

  • OpenAI — compatible tool definitions (OpenAI, Anthropic, LiteLLM, OpenRouter, etc.)
  • Feature — Description
  • Examples — Explore working examples in the examples directory

Installing the agentrpc mcp server

The server is distributed via npm as agentrpc, so most clients can run it without a manual build step. Add it to your MCP client's configuration and restart the client to pick it up — the copy-paste configs for Claude Desktop, Claude Code and Cursor are on this page.

Configuration

Before the server will start you need to supply 3 environment variables: AGENTRPC_API_SECRET, ANGENTRPC_API_SECRET, YOUR_API_SECRET. Keep credentials in your client's env block or a secrets manager rather than committing them.

Where it fits

AI-service servers chain other models into your assistant, turning a single chat into a small production pipeline. AgentRPC sits in that group, and the shape of its toolset — OpenAI, Feature, Examples — tells you what it is really for. Worth comparing against the other ai services servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.

Practical notes

  • This is a hosted server — you point your client at an endpoint rather than running a local process, so there is nothing to keep updated on your machine.
  • It will not start until its required credentials are present, so set those before wondering why the tools never appear.
  • Written in Python.
  • MCP clients ask for confirmation before each tool call by default. Keep that on while you learn what the agentrpc mcp server actually does with your data.
  • Every entry in this directory is reviewed by hand before it goes live, and details are checked against the project's own documentation.

Available tools

ToolWhat it does
OpenAIcompatible tool definitions (OpenAI, Anthropic, LiteLLM, OpenRouter, etc.)
FeatureDescription
ExamplesExplore working examples in the [examples](./examples) directory.

How to install the AgentRPC MCP server

{
  "mcpServers": {
    "agentrpc": {
      "command": "npx",
      "args": ["-y", "agentrpc"],
      "env": {
        "AGENTRPC_API_SECRET": "your-value",
        "ANGENTRPC_API_SECRET": "your-value",
        "YOUR_API_SECRET": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
AGENTRPC_API_SECRETCredential the server authenticates with.Yes
ANGENTRPC_API_SECRETCredential the server authenticates with.Yes
YOUR_API_SECRETCredential the server authenticates with.Yes

Example prompts to try

  • Use AgentRPC to OpenAI.
  • Use AgentRPC to Feature.
  • Use AgentRPC to Examples.

Frequently asked questions

It connects AgentRPC to MCP-compatible AI assistants such as Claude and Cursor, exposing 3 tools (OpenAI, Feature, Examples) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with AgentRPC directly.