接入你的智能体
發布者自己的指令。不是 PlugMCP 端點。
用我們的金鑰與日誌託管一份副本。
npx -y @andrea9293/[email protected]Claude Code 沒有本機指令的安裝連結。複製下方指令並在終端機中執行。
claude mcp add andrea9293-mcp-documentation-server -- npx -y @andrea9293/mcp-documentation-server@1.15.3在終端機中執行。
{ "mcpServers": { "andrea9293-mcp-documentation-server": { "command": "npx", "args": [ "-y", "@andrea9293/[email protected]" ] } }}claude_desktop_config.json
遠端 URL 還是本機指令? 兩種安裝方式的差異
Local-first document management and semantic search for AI coding agents. No external databases, no cloud APIs, no vendor lock-in.
Unlike other MCP servers that are CLI-only, this one ships with a full web dashboard — browse, search, upload, and manage your knowledge base from your browser. Every MCP tool is also exposed as a REST API, giving AI agents a lean, schema-free interface.
.txt, .md, .pdf support{
"mcpServers": {
"documentation": {
"command": "npx",
"args": ["-y", "@andrea9293/mcp-documentation-server"]
}
}
}
Open your browser at http://localhost:3080 — the web UI starts automatically.
Every MCP tool is also accessible via the REST API on http://127.0.0.1:3080/api/. This is the recommended way to interact from AI agents (Claude Code, OpenCode, Gemini CLI, Cursor) because it avoids loading MCP tool schemas into the conversation context — only the response JSON enters.
curl -s http://127.0.0.1:3080/api/config
curl -s http://127.0.0.1:3080/api/documents
curl -s -X POST http://127.0.0.1:3080/api/search-all \
-H "Content-Type: application/json" \
-d '{"query": "your search", "limit": 5}'
A ready-to-use skill is included at skills/documentation-server/SKILL.md — it teaches your agent every endpoint with examples. Install it:
npx skills add https://github.com/andrea9293/mcp-documentation-server --skill documentation-server
add_document or place .txt / .md / .pdf files in the uploads folder and call process_uploads.search_all_documents, or within a single document with search_documents.get_context_window to fetch neighboring chunks and give the LLM broader context.The web interface starts automatically on port 3080 when the MCP server launches. From the web UI you can:
GEMINI_API_KEY is set){
"mcpServers": {
"documentation": {
"command": "npx",
"args": ["-y", "@andrea9293/mcp-documentation-server"]
}
}
}
{
"mcpServers": {
"documentation": {
"command": "npx",
"args": ["-y", "@andrea9293/mcp-documentation-server"],
"env": {
"MCP_BASE_DIR": "/path/to/workspace",
"GEMINI_API_KEY": "your-api-key-here",
"MCP_EMBEDDING_MODEL": "Xenova/all-MiniLM-L6-v2",
"START_WEB_UI": "true",
"WEB_HOST": "127.0.0.1",
"WEB_PORT": "3080"
}
}
}
}
All environment variables are optional. Without GEMINI_API_KEY, only the local embedding-based search tools are available.
The server registers the following tools (all validated with Zod schemas):
Configure via environment variables or a .env file in the project root:
~/.mcp-documentation-server/ # Or custom path via MCP_BASE_DIR
├── data/
│ ├── orama-chunks.msp # Orama vector DB (child chunks + embeddings)
│ ├── orama-docs.msp # Orama document DB (full content + metadata)
│ ├── orama-parents.msp # Orama parent chunks DB (context sections)
│ ├── migration-complete.flag # Written after legacy JSON migration
│ └── *.md # Markdown copies of documents
└── uploads/ # Drop .txt, .md, .pdf files here
Set via MCP_EMBEDDING_MODEL:
Models are downloaded on first use (~80–420 MB). The vector dimension is determined automatically from the provider.
⚠️ Important: Changing the embedding model requires re-adding all documents — embeddings from different models are incompatible. The Orama database is recreated automatically when the dimension changes.
Server (FastMCP, stdio)
├─ Web UI (Express, port 3080)
│ └─ REST API → DocumentManager
└─ MCP Tools
└─ DocumentManager
├─ OramaStore — Orama vector DB (chunks DB + docs DB + parents DB), persistence, migration
├─ IntelligentChunker — Parent-child chunking (code, markdown, text, PDF)
├─ EmbeddingProvider — Local embeddings via @xenova/transformers
│ └─ EmbeddingCache — LRU in-memory cache
└─ GeminiSearchService — Optional AI search via Google Gemini
git clone https://github.com/andrea9293/mcp-documentation-server.git
cd mcp-documentation-server
npm install
npm run dev # FastMCP dev mode with hot reload
npm run build # TypeScript compilation
npm run inspect # FastMCP web UI for interactive tool testing
npm start # Direct tsx execution (MCP server + web UI)
npm run web # Run only the web UI (development)
npm run web:build # Run only the web UI (compiled)
git checkout -b feature/nameMIT — see LICENSE
MCP Documentation Server - Bridge the AI Knowledge Gap. ✨ Features: Document management • Gemini integration • AI-powered semantic search • File uploads • Smart chunking • Multilingual support • Zero
{ "mcpServers": { "andrea9293-mcp-documentation-server": { "command": "npx", "args": [ "-y", "@andrea9293/[email protected]" ] } }}總覽
MCP Documentation Server - Bridge the AI Knowledge Gap. ✨ Features: Document management • Gemini integration • AI-powered semantic search • File uploads • Smart chunking • Multilingual support • Zero-setup 🎯 Perfect for: New frameworks • API docs • Internal guides
工具
尚無工具清單。遠端伺服器會在首次健康檢查後取得工具清單。
常見問題
在本頁複製適用於 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 設定。它使用發布者的安裝方式,而不是 PlugMCP 代理伺服器。
這筆記錄未列出必要的環境變數。
MCP Documentation Server 透過 stdio 在本機執行。
上次檢查時間:2026-10-26。 MCP Documentation Server - Bridge the AI Knowledge Gap. ✨ Features: Document management • Gemini integration • AI-powered semantic search • File uploads • Smart chunking • Multilingual support • Zero-setup 🎯 Perfect for: New frameworks • API docs • Internal guides