MCP Server

@dimahike

代码仓库

基本信息

分类

开发工具

传输方式

stdio

作者

dimahike

关于 MCP Server

A middleware server that acts as a bridge between Cursor IDE and AI models, validating AI responses using project context and Gemini.

MCP Server 配置

暂无标准配置

该服务器的 README 中没有可解析的 MCP 配置块，请前往代码仓库查看安装说明。

代码仓库

MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is MCP Server?

MCP Server is a middleware server that acts as a bridge between Cursor IDE and AI models, validating AI responses using project context and the Gemini API. It is intended for developers using Cursor IDE who want to ensure AI-generated code or suggestions are consistent with their project’s context.

How to use MCP Server?

Clone the repository, install dependencies with npm install, create a .env file with your Gemini API key and configuration options, build the project with npm run build, and start the server with npm start. For development with hot-reloading use npm run dev. A local deployment script (./scripts/deploy-local.sh) is also provided for streamlined setup.

Key features of MCP Server

Project context management
AI response validation
Integration with Gemini API
Real‑time context updates
Comprehensive logging system
Easy local deployment

Use cases of MCP Server

Validate AI responses against current project context
Manage real‑time context updates inside Cursor IDE
Bridge Cursor IDE with Gemini‑powered AI models

常见问题

What are the prerequisites for MCP Server?

Node.js v14+ recommended, npm or yarn, a Google Cloud account for Gemini API access, a Gemini API key, and Cursor IDE.

How do I obtain a Gemini API key?

The README does not detail how to obtain the key, but it states you need a Google Cloud account and a Gemini API key to use the server.

How do I deploy the server locally?

Use the provided script `./scripts/deploy-local.sh`, which checks for a `.env` file, installs dependencies, builds the project, and starts the server in production mode. Alternatively follow the manual steps: `npm install`, `npm run build`, `npm start`.

What API endpoints does MCP Server expose?

GET `/api/health` for health checks, POST `/api/context/initialize` and `/api/context/refresh` for context management, and POST `/api/validate` and `/api/cursor/validate` for AI response validation.

Where are server logs stored?

Logs are saved in the `logs/` directory, as shown in the project structure.

开发工具分类下的更多 MCP 服务器

SSH MCP Server

hypnosis

SSH MCP server for AI agents: remote commands, file transfer, log search and server audits through OpenSSH.

Rams

HSLA0001 Inc.

Design review for UI code, inside your agent. quick_review checks the files you just changed in about ten seconds. review_files returns a 0-100 score and patches. verify_fixes confirms the fixes landed, free. review_url

Yocoolab

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools

Mcp-Warden

ermoluk

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.

FARPY

mangomunchr

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP