SVP-MCP
Integrates AI editors with Semantic Voxel Protocol projects, enabling project status queries, AI-driven compilation across levels, and block management through MCP tools and resources.
README
SVP-MCP
Semantic Voxel Protocol - MCP Server
SVP 的 Model Context Protocol 实现,让 AI 编辑器 (Cursor, Claude Code, Windsurf 等) 能够与 SVP 项目集成。
功能
- 📊 项目状态查询 - 查看编译层级和文件状态
- 🔧 AI 编译 - 从编辑器触发 L5→L1 编译
- 📋 Block 列表 - 列出所有逻辑块
- 🔍 Block 详情 - 查看特定块的实现代码
- 📁 Resources - 暴露项目上下文作为 MCP Resources
安装
npm install -g @semanticvoxelprotocol/mcp-server
配置
Cursor
创建 .cursor/mcp.json:
{
"mcpServers": {
"svp": {
"command": "npx",
"args": ["@semanticvoxelprotocol/mcp-server", "--project", "."]
}
}
}
Claude Code
Claude Code 会自动发现 MCP servers,或手动添加:
# 在项目目录运行
npx @semanticvoxelprotocol/mcp-server --project .
其他编辑器
任何支持 MCP 的编辑器都可以使用 stdio 传输层连接:
svp-mcp --project /path/to/project
提供的 Tools
svp_status
获取项目编译状态
{
"name": "svp_status",
"arguments": {}
}
svp_compile
AI 编译指定层级
{
"name": "svp_compile",
"arguments": {
"level": 5 // 5|4|3|2
}
}
svp_compile_all
AI 编译所有层级 (L5→L1)
{
"name": "svp_compile_all",
"arguments": {}
}
svp_list_blocks
列出逻辑块
{
"name": "svp_list_blocks",
"arguments": {
"level": 3 // 3|2|1, default: 3
}
}
svp_get_block
获取特定块内容
{
"name": "svp_get_block",
"arguments": {
"blockId": "validate_order_input",
"level": 1 // 1|2, default: 1
}
}
提供的 Resources
| URI | 描述 |
|---|---|
svp://{project}/context |
项目上下文和状态 |
svp://{project}/ir/5 |
L5 蓝图 (YAML) |
svp://{project}/ir/4 |
L4 架构流程 (YAML) |
svp://{project}/ir/3 |
L3 领域模型 (YAML) |
svp://{project}/ir/1 |
L1 实现代码 (TypeScript) |
使用示例
在 Cursor 或 Claude Code 中:
> 查看 SVP 项目状态
使用 svp_status 工具查询项目编译状态...
✅ L1 (6 files)
✅ L2 (6 files)
✅ L3 (6 blocks)
✅ L4
✅ L5
> 列出所有逻辑块
使用 svp_list_blocks 工具...
L3 Logic Blocks (6):
- validate_order_input: Validate Order Input
- call_inventory_service: Call Inventory Service
...
> 查看 validate_order_input 的实现
使用 svp_get_block 工具...
// L1 Block: validate_order_input
export function validateOrderInput(request: OrderRequest): ValidationResult {
// 完整实现代码...
}
> 重新编译 L5
使用 svp_compile 工具,level=5...
✅ Successfully compiled L5 → L4
开发
# 安装依赖
npm install
# 构建
npm run build
# 测试运行
node dist/server.js --project ../template-ts
架构
┌─────────────────┐ ┌─────────────┐ ┌─────────────────┐
│ AI Editor │────▶│ MCP Client │────▶│ SVP MCP Server │
│ (Cursor/Claude) │ │ (stdio) │ │ (this package) │
└─────────────────┘ └─────────────┘ └────────┬────────┘
│
┌─────────────────────────┘
▼
┌─────────────┐
│ SVP Core │
│ AICompiler │
└─────────────┘
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.