pickfit

BrowseMCP servers

ClickHouse MCP Server

An MCP server that lets AI assistants list databases and tables and run SQL queries on ClickHouse or the embedded chDB engine.

Tested on Linux

Use it

Linux x86_64

You need first

  • Runtimes: python>=3.10,<=3.15
  • System packages: C compiler (for lz4 on Python 3.15)
  1. uv tool install 'mcp-clickhouse[chdb]' (puts mcp-clickhouse on PATH, with the chDB extra)

    uv tool install 'mcp-clickhouse[chdb]'

Add it to your agent

claude mcp add mcp-clickhouse -- mcp-clickhouse
JSON for Claude Desktop, Cursor and other clients
{
  "mcpServers": {
    "mcp-clickhouse": {
      "command": "mcp-clickhouse",
      "args": []
    }
  }
}

Add mcp-clickhouse as an MCP server in your AI assistant's settings, with CHDB_ENABLED=true to use the embedded chDB engine or your ClickHouse connection details to query a cluster.

What it does

  • Query data with the embedded chDB engine
    How to use it
    1. Start the server with chDB on and ClickHouse off: CHDB_ENABLED=true CLICKHOUSE_ENABLED=false mcp-clickhouse.
    2. Connect your MCP client to the server.
    3. Ask the assistant to call the run_chdb_select_query tool with a SELECT query, such as SELECT number, number*2 AS doubled FROM numbers(3).
    Tested
  • Run SQL queries on ClickHouse
    Not tested
  • List databases and tables
    Not tested
  • Use read-only mode by default
    Not tested

How far pickfit got

Linux x86_64

  1. Installs
  2. Connects
  3. 1 of 4 features work
  4. Works offline

Good for

  • run SQL queries on a ClickHouse cluster from an AI assistant
  • query files and URLs with embedded chDB without ETL
  • estimate query cost before running it

How pickfit tested it

Each run starts from a clean machine and follows the steps above. How pickfit verifies

Linux x86_64

An MCP client called one of its tools

  • Replayed from scratch
  • Works offline
  • Checked on 15 Nov 2026
  • Version 0.7.0

An MCP client handshake over stdio listed 1 tool, and a call to run_chdb_select_query returned a result.

Differences the test machine hit

  • README: pip install mcp-clickhouse (base package); run_chdb_select_query requires the optional chdb extra
    In the test: Installed with uv tool install 'mcp-clickhouse[chdb]' so the chDB tool works. Without CHDB_ENABLED=true only the ClickHouse tools are listed.
  • README: ClickHouse tools need a reachable ClickHouse server (CLICKHOUSE_HOST etc.)
    In the test: The official ClickHouse binary from builds.clickhouse.com crashed with a segfault in this sandbox, so the box had no local server. run_query, list_databases and list_tables could not be tested.

How to read a tool card

Stitching
pickfit installed this tool itself. Everything under the stitches comes from that run. A tool pickfit has not run never gets stitches.
Verified on your OS
The install steps ran on the system you chose. “Ran on Linux only” means it has not been run on yours yet.
macOS, Linux and WindowsWhere it ran
Green OS marks: pickfit ran the install steps there. Grey ones: the README says it runs there, and pickfit has not tried.
How far the run got
Installs and starts, its main function works, its service answers, it produces model output. A window means a desktop app opened; a plug, an MCP client used it. The mark sits beside the run’s result, under “Why it fits and how we know” and in “How pickfit tested it”.
Visual check
pickfit looked at screenshots of the app. Green: it looks right. Amber with a number: things that look wrong; open it to see them. Grey and dashed: not checked yet.
Known vulnerabilities
Known high or critical vulnerabilities (OSV.dev) in what it installs. Green: none known. Red with a number: how many; open it for the list, and read it before you install. Grey and dashed: not checked, which does not mean safe.
About the run
The day it ran, and the version that ran.
Source of a reason
Every reason a pick fits rests on one profile field. Open the reason to see the field and the value it relies on.
Hidden gem
High quality, little known.
Quality and popularity
Two scores out of 100. Quality: how well it installed and worked when pickfit tried it, and how good its install docs and upkeep are. Popularity: from stars, downloads and Hacker News.
Features checked
Of the main features the README advertises, how many the run actually exercised (green), and how many failed (red). Grey ones were not checked, and the card says why.
Not verified
A well-known tool Fitz mentions from general knowledge. No run record, no steps, no score.