MCP Server Template for Cursor IDE
Cursor IDE 的 MCP 服务器模板
一个使用模型上下文协议 (MCP) 为 Cursor IDE 创建自定义工具的简单模板。您可以使用此模板创建自己的代码库,修改工具并将其连接到您的 Cursor IDE。

快速入门
点击“部署到 Heroku”按钮
部署完成后,配置Cursor:
打开游标设置 → 功能
添加新的 MCP 服务器
使用带有
/sse路径的 Heroku URL(例如https://<your-app-name>.herokuapp.com/sse)
在 Cursor 中测试您的代理的心情:
询问您的代理“请询问我们的服务器状况并让我知道情况如何。”
服务器将回复一条欢快的消息和一颗心❤️
Related MCP server: MCP Server Template for Cursor IDE
替代设置方法
您可以通过三种方式运行服务器:使用 Docker、传统 Python 设置或直接在 Cursor IDE 中运行。
Docker 设置
该项目包括 Docker 支持,可轻松部署:
初始设置:
# Clone the repository
git clone https://github.com/kirill-markin/weaviate-mcp-server.git
cd weaviate-mcp-server
# Create environment file
cp .env.example .env使用 Docker Compose 构建并运行:
# Build and start the server
docker compose up --build -d
# View logs
docker compose logs -f
# Check server status
docker compose ps
# Stop the server
docker compose down该服务器将在以下位置可用:
SSE 端点: http://localhost:8000/sse
快速测试:
# Test the server endpoint
curl -i http://localhost:8000/sse连接到 Cursor IDE:
打开游标设置 → 功能
添加新的 MCP 服务器
类型:选择“sse”
网址:输入
http://localhost:8000/sse
传统设置
首先,安装 uv 包管理器:
# Install uv on macOS
brew install uv
# Or install via pip (any OS)
pip install uv使用 stdio(默认)或 SSE 传输启动服务器:
# Install the package with development dependencies
uv pip install -e ".[dev]"
# Using stdio transport (default)
uv run mcp-simple-tool
# Using SSE transport on custom port
uv run mcp-simple-tool --transport sse --port 8000
# Run tests
uv run pytest -v安装完成后,您可以将服务器直接连接到Cursor IDE:
在 Cursor 中右键单击
cursor-run-mcp-server.sh文件选择“复制路径”复制绝对路径
打开光标设置(齿轮图标)
导航至“功能”选项卡
向下滚动到“MCP 服务器”
点击“添加新的 MCP 服务器”
填写表格:
名称:选择任意名称(例如“my-mcp-server-1”)
类型:选择“stdio”(而不是“sse”,因为我们在本地运行服务器)
命令:粘贴您之前复制的
cursor-run-mcp-server.sh的绝对路径。例如:/Users/kirillmarkin/weaviate-mcp-server/cursor-run-mcp-server.sh
环境变量
可用的环境变量(可以在.env中设置):
MCP_SERVER_PORT(默认值:8000)- 运行服务器的端口MCP_SERVER_HOST(默认值:0.0.0.0)- 绑定服务器的主机DEBUG(默认值:false)-启用调试模式MCP_USER_AGENT- 用于网站抓取的自定义用户代理
附加选项
通过 Smithery 安装
要通过Smithery自动安装用于 Claude Desktop 的 Cursor IDE 的 MCP 服务器模板:
npx -y @smithery/cli install @kirill-markin/example-mcp-server --client claudeGlama 服务器评论
Available Tools
4 toolsfigma_designC
Get Figma design data including structure and images
Inputs: url (required).
generate_imageC
Generate an image using DALL-E 3
Inputs: prompt (required), size, quality, n.
mcp_fetchC
Fetches a website and returns its content
Inputs: url (required).
moodA
Ask the server about its mood - it's always happy!
Inputs: question (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose with no overlap: figma_design retrieves design data, generate_image creates new images, mcp_fetch fetches web content, and mood is a whimsical status check. The descriptions make it impossible to confuse one tool for another.
The naming is inconsistent with mixed conventions: figma_design uses snake_case, generate_image uses snake_case, mcp_fetch uses snake_case but with an acronym prefix, and mood is a single lowercase word. There's no consistent verb_noun pattern, and the styles vary enough to cause confusion.
With 4 tools, the count is borderline thin for a server template aimed at Cursor IDE, which might imply broader utility. While each tool is distinct, the set feels minimal and may not cover enough ground for typical development workflows, suggesting it's slightly under-scoped.
For a Cursor IDE template, there are significant gaps: no code-related tools (e.g., edit, lint, debug), no project management features, and no integration with common IDE functions. The tools are disparate (design, image generation, web fetch, mood) without a cohesive domain, making it incomplete for practical use.
Maintenance
Related MCP Connectors
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
A Model Context Protocol server for Wix AI tools
The OpenRouter MCP server plugs OpenRouter into the AI tools you already use. Once connected, your assistant can pull live OpenRouter data (models, prices, your credits, rankings, and docs) and send quick test messages, all without leaving your editor.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Related MCP Servers
- AlicenseBqualityDmaintenanceA simple template for creating custom tools for Cursor IDE using Model Context Protocol, deployable via Heroku, Docker, or directly within Cursor IDE.25MIT
- AlicenseBqualityDmaintenanceA template for creating custom tools for Cursor IDE using Model Context Protocol that allows users to deploy their own MCP server to Heroku and connect it to Cursor IDE.22MIT
- AlicenseCqualityDmaintenanceA template for creating custom tools for Cursor IDE using Model Context Protocol (MCP), allowing developers to extend Cursor's functionality with their own server-based tools.122MIT
- AlicenseCqualityDmaintenanceA starter template for building Model Context Protocol servers that can be integrated with Cursor or Claude Desktop, allowing developers to create custom tools and extensions for AI assistants.114ISC