mcp-server-mariadb-vector
If you are the rightful owner of mcp-server-mariadb-vector and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
The MariaDB Vector MCP server provides tools that LLM agents can use to interact with a MariaDB database with vector support, offering a natural language interface for data storage and interaction.
The MariaDB Vector MCP server is designed to facilitate interaction between LLM agents and a MariaDB database with vector support. By leveraging the Model Context Protocol (MCP), this server ensures compatibility with any MCP client, including popular applications like Claude Desktop and Cursor/Windsurf, as well as LLM Agent frameworks such as LangGraph and PydanticAI. The server allows users to provide context from a knowledge base to their conversations with LLM agents and to store and query these conversations. It supports vector store management, document management, and embedding provider functionalities, making it a versatile tool for managing and querying data using natural language.
Features
- Vector Store Management: Create and delete vector stores in a MariaDB database and list all vector stores.
- Document Management: Add documents with optional metadata to a vector store and query using semantic search.
- Embedding Provider: Use OpenAI's embedding models to embed documents.
Tools
mariadb_create_vector_store
Create a vector store in a MariaDB database.
mariadb_delete_vector_store
Delete a vector store in a MariaDB database.
mariadb_list_vector_stores
List all vector stores in a MariaDB database.
mariadb_insert_documents
Add documents with optional metadata to a vector store.
mariadb_search_vector_store
Query a vector store using semantic search.
