AgentRPC is a Integration MCP server that lets Claude Code, Cursor, Windsurf and any MCP-compatible AI agent connect to any function, any language, across network boundaries. Install in 1 minute with mcpizy install agentrpc.
Integration
Connect to any function, any language, across network boundaries. Universal RPC for AI agents.
mcpizy install agentrpcnpx -y @agentrpc/mcpIf AgentRPC doesn't fit your stack, these Integration MCP servers solve similar problems.
The AgentRPC MCP server is an Integration Model Context Protocol server that lets Claude Code, Cursor, Windsurf, VS Code with Copilot, and other MCP-compatible AI agents connect to any function, any language, across network boundaries. It exposes AgentRPC's capabilities as tools the AI can call directly from your editor or CLI.
The fastest way is the MCPizy CLI: run `mcpizy install agentrpc` and MCPizy will add the server to your `.claude.json` automatically. You can also install it manually by adding an entry under `mcpServers` in `.claude.json` with the command `npx -y @agentrpc/mcp` and restarting Claude Code.
Yes. The AgentRPC MCP server is free and open source (see the GitHub repository linked on this page). You may still need a AgentRPC account or API key to connect the server to the underlying service, but the MCP layer itself has no MCPizy subscription cost.
Yes. Any MCP-compatible client works — including Claude Code, Claude Desktop, Cursor (via `.cursor/mcp.json`), Windsurf, VS Code with Copilot Chat, and custom agents built on the MCP SDK. The same install command targets all of them; only the config file path differs.
Once installed, your AI agent can connect to any function, any language, across network boundaries directly inside your conversation. Typical use cases include asking Claude Code or Cursor to run AgentRPC operations, inspect results, chain AgentRPC with other MCP servers (see our Workflow Recipes), and automate repetitive integration tasks without leaving your editor.