Typesense

🚀 Type-Aware MCP Server

An MCP server that interfaces with the Typesense (https://github.com/modelcontextprotocol/python-sdk) (MCP) protocol.

🚀 Quick Start

📦 Installation

1. Install uv. On Mac, you can use homebrew to install it:

brew install uv

2. Clone the package:

git clone git@github.com:avarant/typesense-mcp-server.git ~/typesense-mcp-server

3. Update your .cursor/mcp.json for use in Cursor:

{
  "mcpServers": {
    "typesense": {
      "command": "uv",
      "args": ["--directory", "~/typesense-mcp-server", "run", "mcp", "run", "main.py"],
      "env": {
        "TYPESENSE_HOST": "",
        "TYPESENSE_PORT": "", 
        "TYPESENSE_PROTOCOL": "",
        "TYPESENSE_API_KEY": ""
      }
    }
  }
}

✨ Features

Typesense MCP Server provides the following tools:

Server Management

• check_typesense_health - Check the health status of the configured Typesense server.
• list_collections - Get a list of all collections in the Typesense server.

Collection Management

• describe_collection - Get the schema and metadata of a specific collection.
• export_collection - Export all documents in a specific collection.
• create_collection - Create a new collection with the provided schema.
• delete_collection - Delete a specific collection.
• truncate_collection - Truncate a collection by deleting all documents but keeping the schema.

Document Operations

• create_document - Create a single new document in a specific collection.
• upsert_document - Upsert (create or update) a single document in a specific collection.
• index_multiple_documents - Bulk insert (create, upsert, or update) multiple documents.
• delete_document - Delete a single document from a specific collection based on its ID.
• import_documents_from_csv - Import documents from CSV data into a collection.

Search Functionality

• search - Perform a keyword search on a specific collection.
• vector_search - Perform a vector similarity search on a specific collection.