mcp-golang
Quickly build Model Context Protocol servers using Go.
- Type
- MCP
- Open source
- Yes
- GitHub Stars
- ★ 1.2k
- Source
- mcp-github
- Repository
- github.com/metoro-io/mcp-golang
Overview
mcp-golang is an unofficial Go implementation of the Model Context Protocol (MCP). It enables developers to rapidly create MCP servers and clients with just a few lines of code. The library offers type-safe tool parameter definitions, automatic JSON Schema generation, support for multiple transport protocols (such as stdio and HTTP), automatic error handling and deserialization, modular design, and bidirectional communication. Ideal for developers who need to provide specific capabilities to AI, especially those familiar with Go. Integration is simple—just install and configure.
Capabilities
- ▪Type-safe tool parameter definitions
- ▪Automatic JSON Schema generation
- ▪Support for multiple transport protocols (e.g., stdio and HTTP)
- ▪Automatic error and deserialization handling
- ▪Modular design for flexible usage
Use cases
Setup
go get github.com/metoro-io/mcp-golang
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
What transport protocols does mcp-golang support?
Supports stdio and HTTP transport protocols.
How do I get started with mcp-golang?
After installation, follow the example code in the documentation for configuration.
Related skills
gemini-cli
Gemini CLI is an open-source AI agent that brings Gemini's powerful capabilities directly into the terminal.
private-gpt
Provides a complete API layer for local models, supporting RAG, skills, tools, and more.
planning-with-files
File-based persistent planning skill, ideal for AI coding agents and long-running tasks.
scientific-agent-skills
Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.
susi_alexa_skill
A skill that enables question-and-answer interactions between Alexa and Susi AI.
claude-context
Provides code search capabilities for Claude Code, turning the entire codebase into context.