View on GitHubConnect ClickHouse to your AI assistants.
About ClickHouse MCP Server
This MCP server connects AI assistants to ClickHouse databases and can also run queries through chDB, an embedded ClickHouse engine. The README says it runs in read-only mode by default. Tools include running SQL with optional parameters, listing databases, listing tables with filters and pagination, and an optional chDB query tool.
It needs Python 3.10 or later and a ClickHouse server reachable over its HTTP interface, since native TCP ports are not supported. It installs from PyPI or runs through uv, and you add an entry to an MCP client such as Claude Desktop with connection details as environment variables. HTTP and SSE transports require authentication unless explicitly disabled for local development. The repository sits under the ClickHouse organisation and is licensed Apache 2.0, though the README does not use the word official. This is based on the project's README.
Key features
- run_query SQL tool
- list_databases and list_tables
- Optional chDB queries
- Read-only by default
- Stdio, HTTP and SSE
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

MCP Toolbox for Databases
googleapis
MCP Toolbox for Databases is an open source MCP server for databases.
17K GitHub starsGoApache-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

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