Glanser Guidelines MCP Server
Glanser 指南 MCP 服务器
针对团队编码指南语料库的语义搜索。 由 FastMCP + ChromaDB + sentence-transformers (all-MiniLM-L6-v2) 提供支持。 100% 免费 — 无需 API 密钥,无需外部服务,设置后完全离线运行。
文件夹结构
mcp-server/
├── server.py ← MCP server (run this on the host)
├── ingest.py ← One-time ingestion script
├── requirements.txt ← Python dependencies
├── documents/ ← Drop your .md guideline files here
│ └── CODING_GUIDELINES.md
└── chroma_db/ ← Created automatically by ingest.py (do not edit)Related MCP server: Code Memory
设置(在主机上运行一次)
1. 安装依赖项
pip install -r requirements.txt
sentence-transformers将在首次运行时下载all-MiniLM-L6-v2模型(约 80 MB)并进行缓存。后续运行完全离线。
2. 添加您的文档
将 Markdown 文件复制到 documents/ 文件夹中:
cp /path/to/CODING_GUIDELINES.md documents/3. 摄入(嵌入一次,保存到磁盘)
python ingest.py这将读取 documents/ 中的每个 .md 文件,嵌入每个部分,并将向量持久化到 chroma_db/ 中。仅在添加新文档时才需要重新运行此操作。
有用的标志:
python ingest.py --file documents/NEW_DOC.md # add a single new doc
python ingest.py --reset # wipe and re-ingest everything
python ingest.py --list # see what is currently indexed4. 启动服务器
python server.py服务器在 http://0.0.0.0:8000 启动。
托管(团队访问)
部署到 Railway 或 Render(两者都有免费层级):
将此
mcp-server/文件夹推送到 git 仓库创建指向该仓库的新服务
设置启动命令:
python server.py在
/app/chroma_db挂载持久卷(以便嵌入在部署后保留)部署后通过主机控制台运行一次
python ingest.py
Railway/Render 会自动提供 HTTPS URL,例如:
https://glanser-guidelines-mcp.railway.app
团队 .mcp.json 条目
每位团队成员将其添加到他们的 .mcp.json 中:
{
"mcpServers": {
"coding-guidelines": {
"type": "http",
"url": "https://your-hosted-domain.com/mcp"
}
}
}可用工具
工具 | 功能 |
| 跨所有文档进行语义搜索 — 优先使用此工具 |
| 获取特定部分的完整内容 |
| 浏览语料库中所有部分的标题 |
| 按 |
| 查看所有已索引的文档及其部分计数 |
添加新文档
# 1. Copy the new doc
cp NEW_GUIDELINES.md documents/
# 2. Ingest only the new file (does not re-embed existing docs)
python ingest.py --file documents/NEW_GUIDELINES.md
# 3. No server restart needed — ChromaDB is queried live本地开发/测试(无需托管)
{
"mcpServers": {
"coding-guidelines": {
"type": "http",
"url": "http://localhost:8000/mcp"
}
}
}This server cannot be deployed
Maintenance
Related MCP Connectors
Hosted MCP memory: save sessions/decisions once, search from Claude, Cursor, ChatGPT. EU-hosted FTS.
Versioned documentation registry and semantic search for AI tools and coding assistants.
Code intelligence for coding agents: semantic, AST, graph, and full-text search. 279+ languages.
Shared memory for coding agents. Stop re-explaining your codebase every session.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables semantic code search across local projects and Git repositories using AI embeddings with ChromaDB. Supports both OpenAI and local Ollama models for private, enterprise-ready code analysis and similar code discovery.44MIT
- AlicenseAqualityDmaintenanceMCP server with local vector search for your codebase. Smart indexing, semantic search, Git history — all offline.7121 PyPI49MIT
- AlicenseAqualityAmaintenanceLocal MCP server for semantic code search using Tree-sitter AST parsing, local embeddings, and hybrid search; enables indexing and querying codebases entirely offline.5MIT
- AlicenseNot gradedqualityBmaintenanceA local hybrid-search MCP server that enables coding agents to query files and folders using natural language, returning relevant code chunks with exact source paths. Everything runs on-device with no API keys or network calls.7MIT