MCP.Market

ClickHouse MCP server

by alyiox·io.github.alyiox/mcp-clickhousex·v0.11.0

Read-only MCP server for ClickHouse metadata, parameterized queries, and plan analysis.

B83/100grade B
What users say
No reviews yet
Be the first
Safety scan
B83/100

full report

Adoption
Growing

0 stars44 downloads/wk

Reviews

Write one

Nobody has reviewed ClickHouse yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

ClickHouse tools (3, 1 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • analyze_query

    [ClickHouse] Explain read-only SELECT.

  • list_profiles

    [ClickHouse] List configured connection profiles.

  • run_querywrite action

    [ClickHouse] Execute read-only SELECT or SHOW.

Public scan report

scanner v0.1.10 · 2026-10-02 · same rubric, same numbers if you re-run it

no findings
  • Code scan11 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancelast push 10 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 83/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How ClickHouse compares

Against every graded Databases MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
83/100
higher than 60% of 802 Databases servers
Tools
3
the typical Databases server has 8
Tools that change things
33%
typical: 10%. Fewer write tools means less an agent can break
Downloads a week
44
more than 31% of 328 Databases servers with a package

What its tools let an agent do: 2 read · 1 run or deploy

Release history: 2 versions in the registry since 2026-09-17, latest 2026-09-20, typically one every 3 days.

Install ClickHouse in Claude Code, Cursor or VS Code

claude mcp add mcp-clickhousex -- uvx mcp-clickhousex
Add to Cursor

What the publisher says

From the ClickHouse repository's README, as published. We do not edit it. Read it on GitHub

MCP ClickHouse Tool

<!-- mcp-name: io.github.alyiox/mcp-clickhousex -->

A read-only-by-default Model Context Protocol (MCP) server for ClickHouse that provides schema discovery, read-only queries, execution-plan analysis, opt-in writes, and profile-based access to multiple servers from a single toolset deployment.

Read-only is enforced by the engine, not by SQL text matching: every client carries ClickHouse's readonly=1, so writes, external table functions and query-level SETTINGS are refused by the server being queried. There is no write tool to opt into.

Requirements: Python 3.13+, a running ClickHouse instance, and connection details via environment variables or a config file.

Quick start

Set a DSN and run the server with MCP Inspector:

# Option 1: Run directly with uvx (no clone needed)
export MCP_CLICKHOUSE_DSN="http://default:@localhost:8123/default"
npx -y @modelcontextprotocol/inspector@latest uvx mcp-clickhousex
# Option 2: Run from source (clone repo, then)
export MCP_CLICKHOUSE_DSN="http://default:@localhost:8123/default"
npx -y @modelcontextprotocol/inspector@latest uv run mcp-clickhousex

Configuration

A profile is one ClickHouse connection: a DSN plus the row and timeout caps that apply to it. A profile named default always exists; every tool takes an optional profile to reach another, and list_profiles reports what is configured.

Settings come from three sources, merged field by field, later winning:

  1. the user-scoped config.json — any number of profiles;
  2. MCPCLICKHOUSEPROFILES__ environment variables — any number of profiles;
  3. flat MCPCLICKHOUSE environment variables — the default profile only.

Because the merge is per field rather than per profile, a config.json can carry the full set while a flat MCPCLICKHOUSEDSN repoints the default profile at a local server, leaving its other fields intact. With none of the three present, default falls back to http://default:@localhost:8123/default.

Each setting has one field name, spelled three ways — MCPCLICKHOUSE, MCPCLICKHOUSEPROFILES__, or the field lowercased as a JSON key:

Caps are per profile. A value above its ceiling is clamped at startup; a value that is not an integer falls back to the default.

Single connection: flat environment variables are the shortest path.

# Connection DSN.
export MCP_CLICKHOUSE_DSN="http://user:password@host:8123/database"

# Optional description for the default profile (tooling/AI discovery).
export MCP_CLICKHOUSE_DESCRIPTION="Primary cluster"

# Optional caps, defaults shown.
export MCP_CLICKHOUSE_QUERY_MAX_ROWS="500"
export MCP_CLICKHOUSE_QUERY_COMMAND_TIMEOUT_SECONDS="30"
export MCP_CLICKHOUSE_SNAPSHOT_MAX_ROWS="10000"
export MCP_CLICKHOUSE_SNAPSHOT_COMMAND_TIMEOUT_SECONDS="120"

Multiple connections: use the user-scoped config.json, which keeps credentials out of the host's process environment.

  • Unix-like: ~/.config/mcp-clickhousex/config.json
  • Windows: %USERPROFILE%\.config\mcp-clickhousex\config.json

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Grade history

  • 2026-09-19downgradeA → Bscore 83

ClickHouse: common questions

Is ClickHouse MCP server safe?
Mostly: it is graded B (83/100). Read the ClickHouse safety report
How do I install ClickHouse?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does ClickHouse need an API key?
Yes. The registry entry asks for MCP_CLICKHOUSE_DSN.
Is ClickHouse maintained?
The last commit was 42 days ago (2026-09-23). The latest release is v0.11.0.
What can I use instead of ClickHouse?
Servers from other publishers that do the same job: GoSQLX MCP server, Kubeshark MCP server and MOFi MCP server.
How does ClickHouse compare with other Databases MCP servers?
safety score 83/100 (higher than 60% of 802 Databases servers); tools 3 (the typical Databases server has 8); tools that change things 33% (typical: 10%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to ClickHouse

Same job from other publishers: the closest match first, then the best rated.

  • GoSQLX
    SQL validation, formatting, parsing, metadata extraction, linting, and security analysis.
    A
  • Kubeshark
    Real-time Kubernetes network traffic visibility and API analysis for HTTP, gRPC, Redis, Kafka, DNS.
    A
  • MOFi
    Query MOF database survey metadata and connect a bounded MOFi scientific workspace.
    A

More from alyiox →