Visit MCP Toolbox for DatabasesMCP Toolbox for Databases is an open source MCP server for databases.
About MCP Toolbox for Databases
MCP Toolbox for Databases is an open source MCP server for connecting AI agents, IDEs and applications to databases. The README describes two uses: a ready made server with prebuilt tools such as listing tables and executing SQL, and a framework where you define your own sources, tools, toolsets and prompts in a configuration file. It lives in the googleapis GitHub organisation.
The README lists support for Google Cloud services such as AlloyDB, BigQuery, Cloud SQL, Spanner and Firestore, and for others including PostgreSQL, MySQL, SQL Server, Oracle, MongoDB, Redis, Snowflake and ClickHouse. It also mentions client SDKs for Python, JavaScript, Go and Java, a test web UI, OpenTelemetry support, connection pooling and IAM integrated authentication. It can be installed as a prebuilt binary, container, Homebrew package, npx command or built from Go source, and you supply database credentials. The licence is Apache 2.0. These details come from the project's README.
Key features
- Prebuilt SQL tools
- Custom tools via configuration file
- Many database back ends
- Client SDKs in four languages
- OpenTelemetry and connection pooling
- Web UI for testing
More databases MCP servers
- Databases

AWS MCP Servers
awslabs
A suite of specialized MCP servers that help you get the most out of AWS, wherever you use MCP.
9.9K GitHub starsPythonApache-2.0 - Databases

Supabase MCP
supabase
The Model Context Protocol (MCP) standardizes how Large Language Models (LLMs) communicate with external services like Supabase. It allows AI assistants to manage tables, fetch configuration, and query data directly within Supabase projects.
3K GitHub starsTypeScriptApache-2.0 - Databases

MongoDB MCP Server
mongodb-js
A Model Context Protocol server to connect to MongoDB databases and MongoDB Atlas Clusters.
1.2K GitHub starsTypeScriptApache-2.0 - Databases

ClickHouse MCP Server
ClickHouse
Connect ClickHouse to your AI assistants.
905 GitHub starsPythonApache-2.0 - Databases

Elasticsearch MCP Server
elastic
The Elasticsearch MCP Server connects your AI agents to Elasticsearch data using the Model Context Protocol (MCP). It enables natural language interactions with your Elasticsearch indices, allowing agents to query, analyze, and retrieve data without custom APIs.
733 GitHub starsRustApache-2.0 - Databases

Neon MCP Server
neondatabase
MCP server for interacting with Neon Management API and databases
664 GitHub starsTypeScriptMIT