MCP Clickhouse MCP Server

by infoinlet-marketplace Your server? Claim it

local only

MCP Clickhouse runs on your own machine — the client starts it, so there is no endpoint to ping. 47 installs a week from npm.

Read-only ClickHouse for AI agents — analytics queries, table inspection, sizes, health.

The linked repository no longer exists on GitHub — it was deleted or made private.

Installs per day peak 12 · avg 4 · +292% w/w

a month agotoday

Installs / week

npm · @infoinlet/mcp-clickhouse

—

Stars

on GitHub

—

Last commit

no releases in 90 days

—

License

language unknown

This one has been quiet for a while

Quiet is not dead — but it is worth knowing when it wakes up, or when someone else takes it over. We watch the repository and tell you either way.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add mcp-clickhouse -- npx -y @infoinlet/mcp-clickhouse

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "mcp-clickhouse": {
      "command": "npx",
      "args": [
        "-y",
        "@infoinlet/mcp-clickhouse"
      ]
    }
  }
}

~/.codex/config.toml

[mcp_servers.mcp-clickhouse]
command = "npx"
args = ["-y", "@infoinlet/mcp-clickhouse"]

.cursor/mcp.json

{
  "mcpServers": {
    "mcp-clickhouse": {
      "command": "npx",
      "args": [
        "-y",
        "@infoinlet/mcp-clickhouse"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "mcp-clickhouse": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@infoinlet/mcp-clickhouse"
      ]
    }
  }
}

Alternatives to MCP Clickhouse

same job, measured the same way

QueryInbox

by queryinbox

Read-only Google Search Console and Google Analytics for AI agents.

answering

OXVO Insights

by oxvo

Read-only OXVO Insights analytics: list tracked events and run queries for one app you authorize.

answering

Google Search Console MCP Server

by conorbronsdon

Google Search Console for AI agents: search analytics, sitemaps, URL inspection.

56 installs/wk local only

Searchdock CLI

by xplormityai

Read-only Google Search Console analytics, URL inspection and sitemaps via SearchDock CLI.

55 installs/wk local only

SearchConsole.ai

by searchconsole

Read-only Search Console analytics, URL inspection, indexing diagnostics, and sitemaps.

answering

Google Search Console MCP

by scalably

Read-only Google Search Console MCP: Search Analytics, sitemaps, URL inspection. 5 tools.

134 installs/wk local only

Convalytics

by dan-cleary

Read-only analytics for Convex apps, queryable via MCP from Claude, Cursor, and other clients.

15 tools answering

Ironflowsh

by ironflowsh

Read-only Hyperliquid data for AI agents: fills, candles, funding, liquidations, wallet analytics.

316 installs/wk 36 tools answering

MCP Clickhouse — questions

Answers built from our own checks of this server.

Why is there no uptime for MCP Clickhouse?

MCP Clickhouse runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the npm package @infoinlet/mcp-clickhouse was installed 47 times last week.

Is MCP Clickhouse still maintained?

The linked repository no longer exists on GitHub — it was deleted or made private. We show this because it changes what you can expect: an unmaintained server may keep answering for months and then stop without warning.

How do I connect MCP Clickhouse?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls @infoinlet/mcp-clickhouse straight from npm; nothing to host, nothing to sign up for.

How many people use MCP Clickhouse?

The npm package @infoinlet/mcp-clickhouse was installed 47 times in the last week. Week over week that is +292%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.