As artificial intelligence reshapes the data landscape, MariaDB has been evolving to ensure you can leverage the power of AI directly with your data. This led to the introduction of Vector Embedded Search, allowing you to store and query vector embeddings alongside your transactional data, laying the groundwork for intelligent applications. We further expanded our capabilities by focusing on seamless AI Framework integrations, ensuring you could utilize popular tools and models with your MariaDB datasets. Now, we’re proud to introduce the MariaDB MCP Server.
The MariaDB MCP Server enables seamless integration between MariaDB databases and AI-driven applications, thanks to its support for the Model Context Protocol (MCP). It provides both traditional SQL operations and modern vector-based semantic search, unlocking the power of embeddings from providers like OpenAI and HuggingFace. Ideal for building RAG systems, semantic search, or recommendation engines—directly on your existing MariaDB stack.
From Community Innovation to Core Feature
The vision for the MariaDB MCP Server was sparked by the innovative spirit of our community. A project emerging from a recent MariaDB Foundation hackathon demonstrated the transformative potential of integrating vector operations directly within an MCP Server. This initiated us to expand the MCP server that we have been engineering for traditional database operations, to natively include these advanced AI capabilities. The dual approach ensures the server is not only a powerful tool for modern AI development but also a practical, unified solution for existing relational workflows.
The AI Challenge with Traditional Databases
As AI adoption grows, organizations are increasingly looking to bring semantic search, intelligent recommendations, and language model integration into their data infrastructure. However, most relational databases aren’t built to handle embedding vectors natively or AI-native workflows—until now.
Understanding the Model Context Protocol (MCP)
MCP provides a standardized way for language models and other AI systems to interact with external tools and data sources. The open-source and model-agnostic MCP Server implements this protocol, ensuring a consistent and reliable method for AI assistants and applications to request information and perform operations. This approach streamlines the development and deployment of AI-integrated systems by enabling seamless communication between AI models and various data sources.
Why the MariaDB MCP Server
The MariaDB MCP Server is engineered to provide a robust MCP interface specifically for MariaDB. Its primary objective is to facilitate seamless interaction between AI models and MariaDB databases, supporting both standard relational data operations and the increasingly vital vector search capabilities required for modern AI applications. Designed with AI assistants in mind, it simplifies data workflows and enhances the ability to integrate database interactions into intelligent systems.
Core Capabilities: Beyond Standard SQL
The MariaDB MCP Server offers a comprehensive suite of tools, categorized into standard database operations and advanced vector functionalities.
Standard Database Operations
These tools provide fundamental control and insight into your MariaDB environment:
- list_databases: Discovers all accessible databases on the connected MariaDB instance.
- list_tables: Enumerates all tables within a specified database.
- get_table_schema: Retrieves the detailed schema for a specific table, including column names, data types, nullability, keys, and default values.
- execute_sql: Allows for the execution of read-only SQL queries such as SELECT, SHOW, and DESCRIBE. It supports parameterized queries for enhanced security and can be configured to enforce read-only mode.
- create_database: Enables the creation of new databases within the MariaDB server if they do not already exist.
Please note that by default read-only mode is enabled, can turn it off by changing MCP_READ_ONLY = false
Harnessing the Power of Vectors: Advanced AI Functionality
The true innovation of the MariaDB MCP Server lies in its integrated vector functionality, enabling semantic search and other embedding-based operations directly within your database environment.
- Vector Store Management:
- create_vector_store: Facilitates the creation of new tables specifically designed as vector stores. These tables are optimized for storing and searching embedding vectors, with a predefined schema including id, document, embedding (VECTOR type), and metadata (JSON) columns. Users can specify the embedding model and distance function (e.g., cosine, euclidean) during creation.
- list_vector_stores: Lists all tables within a given database that are identified as vector stores, based on their specific schema structure.
- delete_vector_store: Securely removes a vector store table from the database.
- Embedding and Search Operations:
- insert_docs_vector_store: Allows for the insertion of documents along with their corresponding metadata into a designated vector store. The server handles the generation of embeddings for these documents using a configured embedding service.
- search_vector_store: Performs semantic similarity searches. Given a user query, this tool generates an embedding for the query and searches the specified vector store to find the ‘k’ most similar documents based on vector distance.
The Engine Behind Intelligence: Embeddings
Embeddings are numerical representations of text (or other data types) that capture semantic meaning. The MariaDB MCP Server integrates an Embedding Service to generate these vectors.
- Supported Providers: The server is designed to work with multiple embedding providers, currently offering robust support for OpenAI, Google Gemini, and open models from HuggingFace.
- Flexible Model Selection: Users can configure a default embedding model or specify a particular model at the time of a request, choosing from a list of allowed models for each provider. This ensures flexibility in balancing cost, performance, and embedding quality.
- Embedding Dimensionality: The system can determine the correct embedding dimensions based on the selected model.
Direct Integration with AI-Native IDEs – Helping to Increase the Vibe in Coding with AI
Connecting the MariaDB MCP Server with AI-native IDEs like Cursor and Windsurf streamlines the development process by making the database a native component of your coding environment. This integration allows developers to interact with MariaDB using natural language directly within the editor—whether to run a standard SQL query or perform a complex vector search.
This removes the need to switch to separate database clients, reducing friction and keeping the developer focused. For those building AI applications like RAG systems, the ability to query a vector store from the IDE simplifies testing and iteration. By bringing database operations into the core development loop, the MCP Server makes building data-driven features more efficient.
Empowering Technical Professionals
The MariaDB MCP Server offers distinct advantages for:
- Developers: Offers a streamlined path to building AI-powered features into applications as well as integrating w/ AI based code editing workflows like Cursor and Windsurf. The standardized MCP interface and clear toolset reduce the complexity of interacting with both relational data and vector embeddings.
- AI/ML Engineers: Simplifies the integration of MariaDB data into AI/ML pipelines. The native vector search capabilities allow for building sophisticated applications like RAG (Retrieval Augmented Generation) systems, semantic search engines, and recommendation systems directly on top of existing databases.
- Database Administrators: Offers a streamlined path to building AI-powered features into applications. The MCP interface and clear toolset reduce the complexity of interacting with both relational data and vector embeddings.
The Future of Data Interaction
The MariaDB MCP Server represents a significant step forward in unifying traditional database management with the demands of modern AI development. By providing a rich set of tools accessible via the Model Context Protocol, and especially by integrating powerful vector search capabilities, it empowers organizations to build more intelligent, data-driven applications with greater efficiency and control.
Get Started with MariaDB MCP Server
Integrating the MariaDB MCP Server into your environment is straightforward.
- Prerequisites: Ensure you have Python 3.11, uv (the dependency manager), and access to a MariaDB server (accessing through Docker is recommended).
- Configuration: Key settings are managed via environment variables, typically defined in a .env file. This includes database connection parameters (host, user, password, port, database name) and embedding provider details (API keys, default models).
- Installation: After cloning the repository, dependencies can be installed using uv pip sync.
Ready to bring AI capabilities to your MariaDB database?
Get started by visiting our GitHub repo for the MariaDB MCP Server
