mcp-server-mariadb-vector
by DavidRamosSal
The MariaDB Vector MCP server provides tools for LLM agents to interact with a MariaDB database with vector support, offering a natural language interface for data storage and interaction. It is compatible with any MCP client, including Claude Desktop, Cursor/Windsurf, LangGraph, and PydanticAI.
Last updated: N/A
What is mcp-server-mariadb-vector?
The MariaDB Vector MCP server is a tool that enables LLM agents to interact with a MariaDB database with vector support using the Model Context Protocol (MCP). It allows users to store, query, and manage vector embeddings using natural language.
How to use mcp-server-mariadb-vector?
To use the server, you can either run it as a Python package using uv or as a Docker container. Configuration is done via environment variables. The server can be integrated with applications like Claude Desktop, Cursor, and Windsurf by configuring the MCP server settings in their respective configuration files.
Key features of mcp-server-mariadb-vector
Vector Store Management (create, delete, list)
Document Management (add, query)
Semantic Search
OpenAI Embedding Provider
MCP Compatibility
Use cases of mcp-server-mariadb-vector
Providing context from a knowledge-base to LLM agent conversations
Storing and querying conversations with LLM agents
Building natural language interfaces for MariaDB databases
Implementing semantic search capabilities within MariaDB
FAQ from mcp-server-mariadb-vector
What MariaDB version is required?
What MariaDB version is required?
MariaDB version 11.7 or higher with vector support is required.
What embedding providers are supported?
What embedding providers are supported?
Currently, OpenAI's embedding models are supported.
How do I configure the server?
How do I configure the server?
The server is configured using environment variables such as MARIADB_HOST, MARIADB_PORT, MARIADB_USER, MARIADB_PASSWORD, MARIADB_DATABASE, EMBEDDING_PROVIDER, EMBEDDING_MODEL, and OPENAI_API_KEY.
How do I run the server with Docker?
How do I run the server with Docker?
Build the Docker image using docker build -t mcp-server-mariadb-vector . and then run the container with the necessary environment variables.
How do I integrate with Claude Desktop/Cursor/Windsurf?
How do I integrate with Claude Desktop/Cursor/Windsurf?
Add the server configuration to the respective configuration file (claude_desktop_config.json, mcp.json, or mcp_config.json) using either the command option for stdio transport or the URL option for SSE transport.