Typesense

Provides AI models access to Typesense collections for discovery, search, and analysis.

typescript

GitHub Stars

typescript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "suhail-ak-2-mcp-typesense-server": {
      "command": "node",
      "args": [
        "~/typesense-mcp-server/dist/index.js",
        "--host",
        "your-typesense-host",
        "--port",
        "8108",
        "--protocol",
        "http",
        "--api-key",
        "your-api-key"
      ],
      "env": {
        "HOST": "your-typesense-host",
        "PORT": "8108",
        "API_KEY": "your-api-key",
        "PROTOCOL": "http"
      }
    }
  }
}

You provision an MCP server that gives AI models access to Typesense data, enabling discovery, search, and analysis across your collections. This practical server acts as a bridge so large language models can efficiently interact with Typesense data sources.

How to use

Install and run the MCP server, then connect your MCP client to it. You can start by using the stdio-based local server or a remote, HTTP-enabled instance if you have one. Once running, you can list available collections, query documents with full-text and filters, retrieve individual documents, and obtain collection statistics. Use the provided prompts to analyze a collection, generate search suggestions, and guide your LLM to pick the right collection before querying.

How to install

Prerequisites: Node.js installed on your system. You will also need npm for package management and the ability to run npx if you choose that installation path.

Install the MCP server globally or locally to your project.

Global installation

# Global installation
npm install -g typesense-mcp-server

Local installation

# Local installation
npm install typesense-mcp-server

Additional setup for development and running

If you prefer a developer workflow, install dependencies and build the server for development.

npm install

npm run build

For active development with auto-rebuild, run the watcher.

npm run watch

Available tools

typesense_list_collections

List all available Typesense collections with their schemas and metadata, enabling zero-conf discovery and routing for an LLM. Returns field definitions and sample documents to infer schema and capabilities.

typesense_query

Execute a full-text search against a specified collection with filters, sorting, and pagination. Returns matching documents along with relevance scores.

typesense_get_document

Retrieve a single document by ID from a collection, returning complete document data.

typesense_collection_stats

Provide statistics for a collection, including document count and schema details.

typesense_search_template

Template for constructing Typesense search queries with common parameters to simplify integration.

typesense_collection_template

Template for viewing a Typesense collection’s schema and core metadata.

Built by

VeilStrat

AI signals for GTM teams