Embedding Search

🚀 MCP-Embedding Search

An MCP (Model Context Protocol) server for querying a Turso database containing embeddings and transcript segments. This tool allows users to search for relevant transcript segments by asking questions without generating new embeddings.

🚀 Quick Start

This server needs to be configured via the MCP client. Below are examples for different environments:

Console Configuration

Add the following to your Cline MCP settings:

{
    "mcpServers": {
        "mcp-embedding-search": {
            "command": "node",
            "args": ["/path/to/mcp-embedding-search/dist/index.js"],
            "env": {
                "TURSO_URL": "your-turso-database-url",
                "TURSO_AUTH_TOKEN": "your-turso-auth-token"
            }
        }
    }
}

Configuration for Claude Desktop

Add the following to your Claude Desktop configuration:

{
    "mcpServers": {
        "mcp-embedding-search": {
            "command": "node",
            "args": ["/path/to/mcp-embedding-search/dist/index.js"],
            "env": {
                "TURSO_URL": "your-turso-database-url",
                "TURSO_AUTH_TOKEN": "your-turso-auth-token"
            }
        }
    }
}

✨ Features

• 🔍 Vector similarity search for transcript segments
• 📊 Relevance scoring based on cosine similarity
• 📝 Complete transcript metadata (episode title, timestamp)
• ⚙️ Configurable search parameters (limit, minimum score)
• 🔄 Efficient database connection pooling
• 🛡️ Comprehensive error handling
• 📈 Optimized performance for fast response

📚 Documentation

API

The server implements an MCP tool:

search_embeddings

Search for relevant transcript segments using vector similarity.

Parameters:

• question (string, required): Query text
• limit (number, optional): Number of results to return (Default: 5, Maximum: 50)
• min_score (number, optional): Similarity threshold (Default: 0.5, Range: 0 - 1)

Response Format:

[
    {
        "episode_title": "Episode Title",
        "segment_text": "Transcript segment content...",
        "start_time": 123.45,
        "end_time": 167.89,
        "similarity": 0.85
    }
    // More results...
]

Database Schema

This tool expects to use a Turso database with the following structure:

CREATE TABLE embeddings (
  id INTEGER PRIMARY KEY AUTOINCREMENT,
  transcript_id INTEGER NOT NULL,
  embedding TEXT NOT NULL,
  FOREIGN KEY(transcript_id) REFERENCES transcripts(id)
);

CREATE TABLE transcripts (
  id INTEGER PRIMARY KEY AUTOINCREMENT,
  episode_title TEXT NOT NULL,
  segment_text TEXT NOT NULL,
  start_time REAL NOT NULL,
  end_time REAL NOT NULL
);

The embedding column should contain vector embeddings that can be used with the vector_distance_cos function.

📦 Installation

Setup

1. Clone the repository
2. Install dependencies:

npm install

3. Build the project:

npm run build

4. Run in development mode:

npm run dev

Release

This project uses changesets for version management. To release:

1. Create a changeset:

npm run changeset

2. Version the package:

npm run version

3. Publish to npm:

npm run release

🤝 Contribution

Contributions are welcome! Please feel free to submit pull requests.

📄 License

MIT License - For more details, please refer to the LICENSE file.

🙏 Acknowledgments

This document was translated from the English version to provide a more intuitive understanding for Chinese users.