The Kuzu Database MCP Server is a Model Context Protocol server designed to provide access to Kuzu databases. It enables Large Language Models (LLMs) to inspect database schemas and execute queries on Kuzu databases, making it a powerful tool for integrating structured data with AI workflows.
getSchemaquerycypher (string): The Cypher query to run.generateKuzuCypherquestion (string): The question in natural language.config.json:~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.jsonmcpServers object:json
{
"mcpServers": {
"kuzu": {
"command": "docker",
"args": [
"run",
"-v",
"{Absolute Path to the Kuzu database}:/database",
"--rm",
"-i",
"kuzudb/mcp-server"
]
}
}
}{Absolute Path to the Kuzu database} with the actual path.npm installconfig.json:~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.jsonmcpServers object:json
{
"mcpServers": {
"kuzu": {
"command": "node",
"args": [
"{Absolute Path to this repository}/index.js",
"{Absolute Path to the Kuzu database}"
]
}
}
}{Absolute Path to this repository} and {Absolute Path to the Kuzu database} with the actual paths.To run the server in read-only mode, set the KUZU_READ_ONLY environment variable to true. This prevents any queries that attempt to modify the database. Add the following configuration to the mcpServers object:
{
"mcpServers": {
"kuzu": {
"command": "docker",
"args": [
"run",
"-v",
"{Absolute Path to the Kuzu database}:/database",
"-e",
"KUZU_READ_ONLY=true",
"--rm",
"-i",
"kuzudb/mcp-server"
]
}
}
}
The Kuzu Database MCP Server integrates seamlessly with Claude Desktop, enabling users to leverage the power of Kuzu databases within their AI workflows. Whether you're developing or deploying, the server provides a robust interface for schema inspection and query execution.
The Kuzu Database MCP Server is an open-source project licensed under the MIT license. It is designed to facilitate the integration of Kuzu databases with AI models, providing a bridge between structured data and natural language processing.