AgentRPC logo

AgentRPC

by agentrpc

AgentRPC is a universal RPC layer for connecting AI agents to functions across network boundaries and languages. It allows you to wrap your functions in a universal RPC interface, connecting them to a hosted RPC server accessible through open standards.

View on GitHub

Last updated: N/A

What is AgentRPC?

AgentRPC is a platform that enables you to connect to functions in any language across network boundaries, ideal for services deployed in private VPCs, Kubernetes clusters, or multiple cloud environments. It wraps your functions in a universal RPC interface, connecting them to a hosted RPC server accessible through open standards like Model Context Protocol (MCP) and OpenAI-compatible tool definitions.

How to use AgentRPC?

  1. Register functions and APIs using the AgentRPC SDK in your preferred language. 2. The AgentRPC platform (api.agentrpc.com) registers the function and monitors its health. 3. Receive OpenAPI SDK compatible tool definitions and a hosted MCP server for connecting to compatible agents.

Key features of AgentRPC

  • Multi-language Support

  • Private Network Support

  • Long-running Functions

  • Full Observability

  • Automatic Failover

  • Framework Compatibility

Use cases of AgentRPC

  • Connecting AI agents to functions in private VPCs

  • Orchestrating services across multiple cloud environments

  • Building AI-powered applications with functions written in different languages

  • Integrating with OpenAI and other language models

  • Creating a universal interface for AI agents to interact with various tools and services

FAQ from AgentRPC

What languages are supported?

AgentRPC supports TypeScript, Go, Python, and .NET (coming soon).

Can I use AgentRPC in a private network?

Yes, AgentRPC supports registering functions in private VPCs without requiring open ports.

What is the Model Context Protocol (MCP)?

MCP is a standard protocol for AI models to interact with tools and services. AgentRPC provides a hosted MCP server for connecting to compatible agents.

How do I integrate AgentRPC with Claude Desktop?

You can integrate AgentRPC with Claude Desktop by adding a configuration to your claude_desktop_config.json file, as shown in the README.

Where can I find more examples?

Explore working examples in the examples directory.