mcp-go
A Go implementation of the Model Context Protocol (MCP) that enables seamless integration between LLM applications and external data sources and tools.
- Type
- MCP
- Transport
- stdio
- Open source
- Yes
- GitHub Stars
- ★ 8.8k
- Source
- mcp-github
- Repository
- github.com/mark3labs/mcp-go
Overview
mcp-go is a Go language implementation of the Model Context Protocol (MCP). It allows LLM applications to seamlessly integrate with external data sources and tools. With mcp-go, developers can easily create MCP servers and focus on building powerful tools without dealing with complex protocol details. Ideal for developers who need to integrate LLM applications with external systems.
Capabilities
- ▪Create MCP servers
- ▪Add tools and resources
- ▪Handle tool requests
- ▪Support multiple transport protocols
Use cases
Setup
go get github.com/mark3labs/mcp-go
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
What transport protocols does mcp-go support?
Currently supports the stdio protocol.
How do I get started with mcp-go?
After installation, refer to the example code to create an MCP server and add tools.
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.