Typesense MCP Server
About
The Typesense MCP Server is a Model Context Protocol (MCP) server that interfaces with Typesense, an open-source search engine. It provides tools to manage collections, documents, and perform search operations, intended for developers integrating Typesense with MCP-compatible…
Details
- Author
- MCP-Mirror
- Downloads
- 251
- Categories
- Other
Jump to
- Check Typesense server health.
- List, describe, create, delete, and truncate collections.
- Export all documents from a collection.
- Create, upsert, and delete single documents.
- Index multiple documents in batch.
- Import documents from CSV data.
- Perform keyword and vector similarity search.
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Typesense MCP ServerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install uv, clone the repository, and configure the server in your MCP client (e.g., Cursor’s mcp.json) by setting the environment variables TYPESENSE_HOST, TYPESENSE_PORT, TYPESENSE_PROTOCOL, and TYPESENSE_API_KEY. Then run the server via the uv command.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"typesense mcp server": {
"typesense": {
"command": "uv",
"args": [
"--directory",
"~/typesense-mcp-server",
"run",
"mcp",
"run",
"main.py"
],
"env": {
"TYPESENSE_HOST": "",
"TYPESENSE_PORT": "",
"TYPESENSE_PROTOCOL": "",
"TYPESENSE_API_KEY": ""
}
}
}
}
}McpServers
{
"typesense": {
"command": "uv",
"args": [
"--directory",
"~/typesense-mcp-server",
"run",
"mcp",
"run",
"main.py"
],
"env": {
"TYPESENSE_HOST": "",
"TYPESENSE_PORT": "",
"TYPESENSE_PROTOCOL": "",
"TYPESENSE_API_KEY": ""
}
}
}Typesense MCP Server
A Model Context Protocol (MCP) Server that interfaces with Typesense
Installation
Install uv
On Mac you can install it using homebrew
brew install uv
Clone the package
git clone git@github.com:avarant/typesense-mcp-server.git ~/typesense-mcp-server
Update your .cursor/mcp.json to 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": ""
}
}
}
}
Available Tools
The Typesense MCP Server provides the following tools:
Server Management
-check_typesense_health - Checks the health status of the configured Typesense server
- list_collections - Retrieves a list of all collections in the Typesense server
Collection Management
-describe_collection - Retrieves the schema and metadata for a specific collection
- export_collection - Exports all documents from a specific collection
- create_collection - Creates a new collection with the provided schema
- delete_collection - Deletes a specific collection
- truncate_collection - Truncates a collection by deleting all documents but keeping the schema
Document Operations
-create_document - Creates a single new document in a specific collection
- upsert_document - Upserts (creates or updates) a single document in a specific collection
- index_multiple_documents - Indexes (creates, upserts, or updates) multiple documents in a batch
- delete_document - Deletes a single document by its ID from a specific collection
- import_documents_from_csv - Imports documents from CSV data into a collection
Search Capabilities
-search - Performs a keyword search on a specific collection
- vector_search - Performs a vector similarity search on a specific collectionSign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
