Optimize and monitor ClickHouse queries and data pipelines through an MCP interface. Built for engineers managing ClickHouse deployments who need real-time query analysis and pipeline visibility.
io.github.Aguantar/clickhouse-dataops-mcp
Local install
STDIO
No auth required
How models use it and what it is built for.
Optimize and monitor ClickHouse queries and data pipelines through an MCP interface. Built for engineers managing ClickHouse deployments who need real-time query analysis and pipeline visibility.
Local install — runs as a subprocess.
Configuration this server reads at startup.
ClickHouse HTTP host
ClickHouse HTTP port
ClickHouse password
Where to find authoritative docs and source for Aguantar Clickhouse Dataops.
Paste any of these into Agent Studio after connecting Aguantar Clickhouse Dataops.
Common questions about connecting and running Aguantar Clickhouse Dataops.
What does the ClickHouse DataOps MCP server do?
It provides query optimization analysis and pipeline monitoring for ClickHouse databases via MCP. You can analyze query performance, identify bottlenecks, and monitor data pipeline execution in real time.
How do I connect it to my ClickHouse instance?
Set the CLICKHOUSE_HOST, CLICKHOUSE_PORT, and CLICKHOUSE_PASSWORD environment variables before running the server. The server connects via ClickHouse's HTTP interface.
Can I use this with a remote ClickHouse cluster?
Yes. Point CLICKHOUSE_HOST to your remote instance's hostname or IP and set CLICKHOUSE_PORT to the HTTP port (default 8123). Ensure network connectivity and authentication credentials are correct.
What authentication methods does it support?
The server uses password-based authentication via the CLICKHOUSE_PASSWORD environment variable. It connects through ClickHouse's HTTP interface, which supports standard username/password auth.
Is there a cost to use this MCP server?
The MCP server itself is open-source and free. You only pay for your ClickHouse infrastructure (self-hosted or managed service). Check the repository for licensing details.
MCP Playground runs 10,000+ hosted MCP servers — GitHub, Linear, Notion, Stripe, Sentry and more — across Claude, GPT, Gemini, DeepSeek and 60+ AI models. Compare model answers side-by-side, save agent presets, share runs. Zero install.
Open Agent StudioJudges Panel
45 judges that evaluate AI-generated code for security, cost, and quality with built-in AST.
Addozhang Nexus
Query Sonatype Nexus Repository (OSS/Pro) for Maven, Python, and Docker artifacts
Cyanheads MCP Ts Template
TypeScript template for building MCP servers with declarative tooling, observability, and auth.
Chernistry Bernstein
Declarative agent orchestration for engineering teams