MCP 服务器

RAG Notes Search MCP Server

Enables semantic search over personal study notes by exposing a vector search tool that Claude Desktop can call to retrieve relevant note content and synthesize grounded answers.

README

RAG Notes Search — MCP Server

A semantic search system over personal study notes, exposed as an MCP (Model Context Protocol) tool that Claude Desktop can call mid-conversation.

What it does

Ask Claude Desktop anything about your notes and it automatically:

Decides whether to search your notes based on the question
Calls the search_notes tool with a semantic query
Retrieves the most relevant note content with similarity scores
Synthesizes an answer grounded in your actual notes

Example queries that work:

"What have I written about machine learning pipelines?"
"Search my notes for how vector databases work"
"What do my notes say about GCP Cloud Run?"

Architecture

Claude Desktop (MCP Client) ↓ stdio MCP Server (mcp_server.py) ↓ search_notes() tool ↓ Chroma Vector DB (local) ↓ fastembed (all-MiniLM-L6-v2, ONNX)

Tech stack

MCP — Anthropic's Model Context Protocol (v1.28.1) for tool exposure
Chroma — local vector database storing note embeddings
fastembed — lightweight ONNX-based embedding model (no PyTorch dependency)
sentence-transformers/all-MiniLM-L6-v2 — embedding model, 384 dimensions
Docker — containerized for reproducibility, built for linux/amd64
GCP — Container Registry hosts the image, Cloud Run deployment planned

Key technical decisions

Why fastembed over sentence-transformers? sentence-transformers pulls in PyTorch (~2GB). fastembed uses ONNX runtime (~200MB), making Docker builds 10x faster and the image significantly smaller.

Why a similarity threshold? Without a threshold, vector search always returns something even when nothing is relevant — this is how RAG systems silently hallucinate. A threshold of 0.25 means the system returns "no relevant notes found" rather than a low-confidence garbage result.

Why absolute paths in the MCP server? Claude Desktop spawns the MCP server as a subprocess with an unpredictable working directory. Relative paths like ./chroma_db break silently. Absolute paths are required for reliable subprocess execution.

Why stderr for all logging? MCP uses stdout as a JSON wire protocol. Any print() to stdout corrupts the MCP message stream. All logging goes to stderr which Claude Desktop reads separately via the log file.

Setup

Prerequisites

Python 3.11
Claude Desktop
conda or venv

Install

conda create -n rag_demo python=3.11
conda activate rag_demo
pip install chromadb==1.5.9 sentence-transformers mcp fastembed numpy==1.26.4

Index your notes

Add .txt files to the notes/ folder, then run the indexing notebook:

jupyter notebook demo.ipynb

Run all cells — this embeds your notes into Chroma.

Connect to Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "notes-search": {
      "command": "/opt/anaconda3/envs/rag_demo/bin/python",
      "args": ["/absolute/path/to/rag_demo/mcp_server.py"],
      "cwd": "/absolute/path/to/rag_demo"
    }
  }
}

Restart Claude Desktop. Look for the tools icon in the chat input.

Docker

# Build for linux/amd64
docker buildx build --platform linux/amd64 -t rag-demo .

# Run with local chroma_db mounted
docker run --rm \
  -v /absolute/path/to/chroma_db:/app/chroma_db \
  rag-demo

Bugs fixed during development

Bug	Cause	Fix
`Read-only file system`	Relative `./chroma_db` path breaks in subprocess	Use absolute path
`Unexpected token 'L' is not valid JSON`	`print()` polluting MCP stdout wire	Route all logs to `stderr`
`cached_download` ImportError	sentence-transformers version conflict	Switched to fastembed
`np.float_` AttributeError	NumPy 2.0 removed deprecated types	Pinned `numpy==1.26.4`
`no such column: collections.topic`	Chroma version mismatch between dev and Docker	Matched versions exactly