MCP-Go
@OkutaniDaichi0106
MCP-Go について
A library for establishing MCP server.
基本情報
設定
ツール
ツールは検出されませんでした
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
概要
What is MCP-Go?
MCP-Go is a Go implementation of the Model Context Protocol (MCP), a lightweight protocol for efficient communication between AI models and applications. It provides a robust framework with client-server architecture, concurrent design, and type-safe APIs, suitable for developers building AI-integrated systems in Go.
How to use MCP-Go?
Install via go get github.com/OkutaniDaichi0106/mcp-go. Use the mcp.NewServer() or mcp.NewClient() factory, register tools/resources/prompts with handler functions, then create a transport (Stdio, HTTP, or custom) and call Accept() (server) or Dial() (client) to obtain a session.
Key features of MCP-Go
- Client-Server Architecture with full implementation of both roles
- Transport Flexibility via Stdio, WebSockets, or HTTP
- Concurrent Design using Go’s goroutines and channels
- Type-Safe APIs to prevent runtime errors
- Modular Components with a handler-based design pattern
- Session Management with proper lifecycle handling
Use cases of MCP-Go
- Building MCP servers that expose tools, resources, and prompts to AI models
- Creating MCP clients to consume capabilities from MCP servers
- Enabling standardized message exchange between AI models and applications
FAQ from MCP-Go
What protocol version does MCP-Go implement?
It implements the Model Context Protocol specification v2025-03-26.
What transport methods are supported?
MCP-Go supports Standard I/O, WebSockets, and HTTP transports.
How do I install MCP-Go?
Install by running go get github.com/OkutaniDaichi0106/mcp-go in your Go project.
What is the license?
MCP-Go is licensed under the MIT License.
Where can I find API documentation?
Detailed API documentation is available at GoDoc (https://godoc.org/github.com/OkutaniDaichi0106/mcp-go).
「その他」の他のコンテンツ
ACI: Open-Source Infra to Power Unified MCP Servers
aipotheosis-labsACI.dev is the open source tool-calling platform that hooks up 600+ tools into any agentic IDE or custom AI agent through direct function calling or a unified MCP server. The birthplace of VibeOps.
Reactive Resume
amruthpillaiA one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!

Peekaboo MCP – lightning-fast macOS screenshots for AI agents
steipetePeekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.
Nginx UI
0xJackyYet another WebUI for Nginx
Unity MCP ✨
justinpbarnettUnity MCP acts as a bridge between AI assistants and your Unity Editor. Give your LLM tools to manage assets, control scenes, edit scripts, and automate tasks within Unity.
コメント