"clickhouse" matching MCP servers:

Exposes an Apache Ossie semantic model over MCP so AI agents can discover metrics, dimensions and relationships, then translate business-term questions into a single ClickHouse query. Also serves the generated SQL and model descriptions, letting agents validate and recover from mistakes without knowing ClickHouse specifics.

Connects Claude Desktop to self-hosted enterprise tools such as Confluence, Jira, Bitbucket, Airtable, and databases (MySQL, MariaDB, ClickHouse, Oracle) via MCP.

Enables AI agents to interact with ClickHouse analytics through a semantic layer, exposing datasets and metrics for natural-language querying.

Enables AI to execute SQL queries against MySQL and ClickHouse connections, retrieve and manage results, and inject them into the aiQueryLab VSCode IDE.

An MCP server for chDB, the in-process SQL OLAP engine powered by ClickHouse. Lets agents query Parquet, CSV, JSON, and pandas DataFrames with one tool — no separate server, no Docker.

Ranks log patterns by volume and cost on Splunk, Datadog, Elasticsearch, CloudWatch and ClickHouse, and plans compact, tier down or offload for the excess over each cap. Runs locally over stdio; no log data reaches log10x. Read-only against a public demo dataset without an API key.

Enables LLM clients to query ClickHouse analytics tables read-only through MCP, with an allowlist of permitted tables and an optional HTTP healthcheck.

Enables AI agents to discover and query data federated across MySQL/MariaDB, PostgreSQL, ClickHouse, S3 and Kafka with SQL, exposing tools to list databases, schemas, tables and connections, describe columns, search objects, inspect table statistics, run EXPLAIN, and execute arbitrary statements. It runs locally over stdio against a PostgreSQL-wire endpoint and returns structured results or SQLSTATE-coded errors.

Enables AI agents to query MySQL, ClickHouse, Trino, and S3-compatible object stores through the same local daemon used by VSCode, including running SQL from files and browsing buckets.

Enables read-only access to Percona Monitoring and Management 2.x through PromQL metric queries and Query Analytics, so clients can list monitored databases, surface the slowest queries, inspect query details, and run validated SELECT queries against QAN's ClickHouse data. TLS verification, input validation, and Viewer-role tokens keep access strictly observational.

Multi-datasource MCP server that connects AI assistants to 6 database types (MySQL, PostgreSQL, ClickHouse, MongoDB, SQLite, Huawei DWS) with dynamic configuration, encrypted credential storage, and schema discovery.

MCP server that enables natural-language SQL queries across multiple databases (ClickHouse, Teradata, PostgreSQL, MySQL, SQL Server, DB2, Oracle, MongoDB) with dialect-correct SQL generation, PII masking, and security-by-construction controls.