What is easyMcp?
easyMcp is a framework to quickly build an extensible MCP server supporting all transmission modes (STDIO, SSE, Streamable HTTP).
@wenb1n-dev
基本情報
Enable developers to quickly build an MCP server service framework that supports all Model Context Protocol (MCP) transfer modes (STDIO, SSE, Streamable Http)。使开发者快速的搭建一个支持mcp协议所有传输方式(STDIO、SSE、StreamableHttp)的mcp server服务框架
ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
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。
easyMcp is a framework for quickly building an extensible MCP (Model Context Protocol) server. It supports all MCP transmission modes: STDIO, SSE, and Streamable HTTP. The project is aimed at developers who need to create custom tools for MCP clients such as Cursor or Cline.
First, optionally define configuration in src/config/.env. Second, create your own tool class in src/handles by inheriting from BaseHandler and implementing the required methods. Then start the server with uv run src/server.py (with optional flags --sse or --stdio for the respective modes). Finally, add the appropriate MCP JSON configuration to your client.
BaseHandler interface.uv for dependency management and runtime.easyMcp is a framework to quickly build an extensible MCP server supporting all transmission modes (STDIO, SSE, Streamable HTTP).
The project requires `uv` (a Python package manager) to install dependencies and run the server. The source code is in Python.
Create a new Python file in `src/handles`, inherit from `BaseHandler`, define `name`, `description`, `get_tool_description`, and `run_tool` methods, then import the class in `__init__.py`.
Configuration is stored in a `.env` file at `src/config/.env`. Environment variables can also be set in the client’s MCP JSON block (especially for STDIO mode).
It supports all three MCP transport modes: STDIO, SSE, and Streamable HTTP. The mode is selected via command-line flags when starting the server.
Set up and manage the Eddyter AI rich text editor by talking to your AI agent — for Claude, Cursor, Codex and other MCP tools. A Model Context Protocol server that lets AI tools add Eddyter to a React, Next.js, Vite or R

Public read-only MCP server for discovering, inspecting, installing, and sharing approved Codex-compatible animated pet packs.
CronWatch records every run of your scheduled jobs in your own database, and speaks up when one is missed, fails, gets stuck, runs slow or costs too much. CronWatch is free and open-source.

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.
JiCo for Jira & Confluence: local MCP server for Jira Data Center - redacts personal data before the AI model, holds every write for approval
コメント