MCP cover image
See in Github
2025-04-14

A MCP Client for MCP/OpenMCP

25

Github Watches

3

Github Forks

25

Github Stars

OpenMCP

一款用于 MCP 服务端调试的一体化 vscode/trae 插件。

集成 Inspector + MCP 客户端基础功能,开发测试一体化。

进行资源协议、工具、Prompt 的 MCP 服务器测试。

测试完成的工具可以放入 「交互测试」 模块之间进行大模型交互测试。

支持多种大模型

TODO

需求规划

所在模块 需求内容 功能优先级 当前状态 修复优先级
all 完成最基本的各类基础设施 完整版本 100% Done
render chat 模式下支持进行成本分析 迭代版本 100% Done
ext 支持基本的 MCP 项目管理 MVP 90% P0
service 支持自定义支持 openai 接口协议的大模型接入 完整版本 100% Done
service 支持自定义接口协议的大模型接入 MVP 0% P1
all 支持同时调试多个 MCP Server MVP 0% P1
all 支持通过大模型进行在线验证 迭代版本 100% Done
all 支持对用户对应服务器的调试工作内容进行保存 迭代版本 100% Done
render 高危操作权限确认 MVP 0% P1
service 对于连接的 mcp server 进行热更新 MVP 0% P1
service 系统配置信息云同步 MVP 0% P1
all 系统提示词管理模块 MVP 0% P1

Dev

  • renderer: 前端 UI 的定义
  • service: 测试 renderer 的部分,包含一个简易的转发层
  • src: vscode 插件端定义

Renderer & Service Dev

flowchart LR
D[renderer] <--> A[Dev Server] <--ws--> B[service]
B <--mcp--> m(MCP Server)

配置项目

## linux
./configure.sh
## windows
./configure.ps1

启动 dev server

## linux
./dev.sh
## windows
./dev.ps1

端口占用: 8080 (renderer) + 8081 (service)

Extention Dev

flowchart LR
D[renderer] <--> A[extention.ts] <--> B[service]
B <--mcp--> m(MCP Server)

负载部署

## linux 
./build_service.sh

## windows
./build_service.ps1

and just press f5, いただきます

Flowchart

flowchart TB
    A[用户输入问题] --> B[选择工具]
    B --> C[大模型处理]
    C --> D{是否有tool use?}
    D -- 否 --> E[返回 content]
    D -- 是 --> F[执行工具]
    F --> G[返回工具执行结果]
    G --> C

相关推荐

  • Aurity Ltd
  • Create and Publish Business Websites in seconds. AI will gather all the details about your website and generate link to your website.

  • John Rafferty
  • Text your favorite pet, after answering 10 questions about their everyday lives!

  • Convincible Ltd
  • You're in a stone cell – can you get out? A classic choose-your-adventure interactive fiction game, based on a meticulously-crafted playbook. With a medieval fantasy setting, infinite choices and outcomes, and dice!

  • Ian O'Connell
  • Provide players' names or enter Quickstart to start the game!

  • analogchat.com
  • Efficient Spotify assistant for personalized music data.

  • Matthieu Savioux
  • Evaluates language quality of texts, responds with a numerical score between 50-150.

  • WangRongsheng
  • 🧑‍🚀 全世界最好的LLM资料总结(Agent框架、辅助编程、数据处理、模型训练、模型推理、o1 模型、MCP、小语言模型、视觉语言模型) | Summary of the world's best LLM resources.

  • langgenius
  • Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production.

  • alibaba
  • an easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.

  • av
  • Effortlessly run LLM backends, APIs, frontends, and services with one command.

  • microsoft
  • Python tool for converting files and office documents to Markdown.

  • 1Panel-dev
  • 🔥 1Panel provides an intuitive web interface and MCP Server to manage websites, files, containers, databases, and LLMs on a Linux server.

  • mindsdb
  • AI's query engine - Platform for building AI that can answer questions over large scale federated data. - The only MCP Server you'll ever need

  • Byaidu
  • PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译,支持 Google/DeepL/Ollama/OpenAI 等服务,提供 CLI/GUI/MCP/Docker/Zotero

  • AstrBotDevs
  • ✨ 易上手的多平台 LLM 聊天机器人及开发框架 ✨ 平台支持 QQ、QQ频道、Telegram、微信、企微、飞书、钉钉 | 知识库、MCP 服务器、OpenAI、DeepSeek、Gemini、硅基流动、月之暗面、Ollama、OneAPI、Dify 等。 WebUI。

  • labring
  • FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, letting you easily develop and deploy complex question-answering systems without the need for extensive setup or configuration.

  • beclab
  • Olares: An Open-Source Personal Cloud to Reclaim Your Data

  • mem0ai
  • Memory for AI Agents; SOTA in AI Agent Memory; Announcing OpenMemory MCP - local and secure memory management.

    Reviews

    3.5 (2)
    Avatar
    user_mfZlCCjB
    2025-04-23

    Openmcp-client by LSTM-Kirigaya is an impressive tool that stands out in the market. Its user-friendly interface and seamless functionality have significantly enhanced my productivity. The well-crafted welcome information makes it easy to get started, while the detailed product description provides thorough insights. Highly recommend for anyone seeking a reliable MCP application.

    Avatar
    user_wH5abq5s
    2025-04-23

    As a dedicated user of the openmcp-client by LSTM-Kirigaya, I have found it extremely efficient and user-friendly. The seamless integration and intuitive interface make it an excellent tool for managing MCP applications. The support and documentation provided are top-notch, enhancing the overall user experience. Highly recommend it for anyone looking to streamline their MCP workflows!