MCP servers · aguantar

ClickHouse DataOps MCP Server

An MCP server for ClickHouse that adds query optimization advice, CDC pipeline latency analysis and data quality checks to read-only query access.

This text was machine-translated from the publisher's own information and has not been checked by a human editor. The publisher's original text is the reference.

This resource was imported automatically from the sources listed below and has not been reviewed by the AI Gate team yet. The description is the publisher's own, as published. Check the repository before installing.

What it does

The clickhouse-dataops-mcp server exposes eight tools. ch_query runs SELECT statements with partition pruning warnings, and ch_explain_query performs EXPLAIN-based analysis with optimization suggestions. ch_table_schema returns table metadata such as columns, keys, partitions and samples, and ch_list_tables gives a table catalog with built-in descriptions. Further tools cover per-segment CDC pipeline latency (p50, p95, p99), null, duplicate and gap detection with market coverage checks, slow query detection with root cause diagnosis, and disk analysis with TTL and optimization recommendations.

The publisher positions it as a query optimization advisor rather than a plain query runner. It suits DataOps work on ClickHouse, such as monitoring CDC pipelines, checking data quality and investigating slow or costly queries.

It connects to ClickHouse over its HTTP interface and is configured through environment variables: host, port, user, password, default database and query timeout. The publisher's documentation shows setup through an .mcp.json file for Claude Code. All queries are intended to be read-only: DDL and DML statements are blocked at the SQL validation layer, comments are stripped before validation, and system tables are limited to an allowlist. The code is released under the MIT license.

Limitations and requirements

Requires a reachable ClickHouse HTTP endpoint and credentials supplied through environment variables; the default password is empty. Queries time out after 30 seconds by default. Row limits are enforced. Multi-statement queries (using ';') are blocked, and DDL and DML statements such as DROP, INSERT, UPDATE and ALTER are not allowed. System tables are restricted to an allowlist.

Safety

Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.

  • Runs code or changes an assistant's behaviour

Sources

  • Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
    io.github.Aguantar/clickhouse-dataops-mcp

    DataOps ClickHouse MCP server with query optimization and pipeline monitoring

    v0.1.1
    As shown on registry.modelcontextprotocol.io when we last read it
MCP servers
hashicorp

Terraform MCP Server (HashiCorp)

HashiCorp's MCP server that gives an assistant current Terraform Registry information on providers, modules and policies, and can manage HCP Terraform workspaces.

1.6K GitHub starsCloud & DevOpsSoftware development
Updated 17 Nov 2026
MCP servers
neondatabase

Neon MCP Server (Postgres)

Neon's MCP server for managing Neon Postgres in plain language: create projects and branches, run queries and prepare schema migrations from your editor.

663 GitHub starsData & databasesSoftware development
Updated 17 Nov 2026
MCP servers
redis

Redis MCP Server

Redis's official MCP server that lets an AI assistant store, read and search data in a Redis database, including streams, JSON documents and vector indexes.

642 GitHub starsData & databasesSoftware development
Updated 17 Nov 2026
MCP servers
supabase-community

Supabase MCP Server

Supabase's MCP server that connects an AI assistant to your Supabase project to design tables, run queries, read configuration and look up documentation.

Data & databasesSoftware development
Updated 17 Nov 2026