mcp

mcp

3.4

If you are the rightful owner of mcp 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 MCP MariaDB Server provides a Model Context Protocol (MCP) interface for managing and querying MariaDB databases, supporting both standard SQL operations and advanced vector/embedding-based search.

The MCP MariaDB Server is designed to facilitate seamless integration of AI-driven data workflows with relational and vector databases. It offers a standardized protocol for interacting with MariaDB databases and vector stores, making it an ideal solution for AI assistants. The server supports a range of operations, including listing databases and tables, retrieving table schemas, executing safe, read-only SQL queries, and managing vector stores for embedding-based search. By integrating with popular embedding providers like OpenAI, Gemini, and HuggingFace, the server enables advanced semantic search capabilities. The server is highly configurable, allowing users to set environment variables for database connections, embedding providers, and more. With its robust set of tools and features, the MCP MariaDB Server is a powerful resource for developers looking to enhance their applications with AI-driven data processing and search capabilities.

Features

  • Standardized protocol for database and vector store interactions
  • Support for read-only SQL queries and schema retrieval
  • Integration with popular embedding providers for semantic search
  • Configurable environment variables for flexible setup
  • Tools for creating and managing vector stores

Tools

  1. list_databases

    Lists all accessible databases.

  2. list_tables

    Lists all tables in a specified database.

  3. get_table_schema

    Retrieves schema for a table (columns, types, keys, etc.).

  4. execute_sql

    Executes a read-only SQL query.

  5. create_database

    Creates a new database if it doesn't exist.

  6. create_vector_store

    Creates a new vector store (table) for embeddings.

  7. delete_vector_store

    Deletes a vector store (table).

  8. list_vector_stores

    Lists all vector stores in a database.

  9. insert_docs_vector_store

    Batch inserts documents into a vector store.

  10. search_vector_store

    Performs semantic search for similar documents using embeddings.