MCP.so
Sign In

MCP Runner

@Streamline-TS

About MCP Runner

Runs and manages MCP servers

Basic information

Category

Other

License

MIT

Runtime

rust

Transports

stdio

Publisher

Streamline-TS

Config

No standard config provided

This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.

Repository

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is MCP Runner?

MCP Runner is a Rust library for running and interacting with Model Context Protocol (MCP) servers locally. It provides a complete solution for managing MCP server processes, communicating via JSON-RPC, and optionally proxying Server-Sent Events (SSE) to enable client connections.

How to use MCP Runner?

Add mcp-runner = "0.3.1" to your Cargo.toml, then create a McpRunner from a JSON config file, a JSON string, or programmatically. Use start_all_with_proxy() to start servers and the SSE proxy, then get a client with get_client() to list tools or call them.

Key features of MCP Runner

  • Start and manage MCP server processes locally
  • Configure multiple servers through a unified interface
  • Communicate with MCP servers using JSON-RPC
  • List and call tools exposed by MCP servers
  • Access resources provided by MCP servers
  • Proxy Server-Sent Events (SSE) to enable HTTP clients

Use cases of MCP Runner

  • Integrate MCP servers into a Rust application
  • Manage multiple MCP servers from a single codebase
  • Expose MCP servers to web clients via HTTP and SSE
  • Automate tool calling across different MCP servers

FAQ from MCP Runner

What is MCP Runner?

MCP Runner is a Rust library that manages the lifecycle of MCP server processes and provides a client API for interacting with them via JSON-RPC.

How do I install MCP Runner?

Add mcp-runner = "0.3.1" to your Cargo.toml dependencies.

How do I configure MCP Runner?

Create a JSON configuration file with mcpServers (each with command and args) and optionally an sseProxy block. Load it via McpRunner::from_config_file("config.json")?.

What is the SSE proxy and how do I use it?

The SSE proxy exposes MCP servers over HTTP, allowing web clients to connect via SSE for real‑time updates. Enable it by adding an sseProxy section to your config; start it with start_all_with_proxy().

How do I handle errors in MCP Runner?

MCP Runner uses a custom Error type covering configuration, server lifecycle, communication, and serialization errors. Match on variants like Error::ServerNotFound or Error::Communication for detailed handling.

Comments

More Other MCP servers