clickhouse.com publishes an Agentic Resource Discovery manifest at
/.well-known/ai-catalog.json, declaring what an AI agent can call on this domain.
Everything below is read from that file. First seen by our crawler on 31 August 2026.
| Declared resource | Type |
|---|---|
| ClickHouse Cloud MCP Serveranswers in 241ms Remote MCP server for ClickHouse Cloud: explore schemas and run SQL queries against your ClickHouse Cloud services. endpoint: https://mcp.clickhouse.cloud/mcp/server-cardidentifier: urn:air:clickhouse.com:cloudpublished to be found for: query my ClickHouse Cloud database · list the tables in my ClickHouse service and describe their schemas · run this SQL against ClickHouse from my agent clickhouse mcp sql analytics | application/mcp-server-card+json |
| Managed ClickStack MCP Servernot yet checked Remote MCP server for Managed ClickStack: search logs, traces, and metrics in your ClickStack observability data. endpoint: https://mcp.clickhouse.cloud/clickstack/server-cardidentifier: urn:air:clickhouse.com:clickstackpublished to be found for: search my logs for errors in the last hour · find slow traces in my observability data · investigate a production incident with ClickStack clickstack mcp observability logs traces | application/mcp-server-card+json |
| ClickHouse API cataloganswers in 213ms RFC 9727 catalog of ClickHouse public APIs, including the ClickHouse Cloud management API with its OpenAPI description. endpoint: https://clickhouse.com/.well-known/api-catalogidentifier: urn:air:clickhouse.com:api-catalogpublished to be found for: manage ClickHouse Cloud services programmatically · find the OpenAPI spec for the ClickHouse Cloud API clickhouse api openapi | application/linkset+json |
| ClickHouse getting-started skillnot yet checked Get started with ClickHouse. What it is, and how to install, run, and query ClickHouse locally and in ClickHouse Cloud using the clickhousectl CLI. Use this when a user wants to understand ClickHouse or start building with it. endpoint: https://clickhouse.com/SKILL.mdidentifier: urn:air:clickhouse.com:skill:clickhousepublished to be found for: what is ClickHouse and when should I use it · install and run ClickHouse locally · start building an application on ClickHouse clickhouse getting-started | application/ai-skill+md |
| chdb-datastoreanswers in 246ms Use when the user has tabular data (pandas DataFrame, parquet, csv, Arrow, json) and wants to filter, group, aggregate, join, or speed up slow pandas. Provides chDB DataStore — same pandas API, ClickHouse engine underneath. Also handles reading from S3, MyS... endpoint: https://clickhouse.com/.well-known/agent-skills/chdb-datastore.tar.gzidentifier: urn:air:clickhouse.com:skill:chdb-datastorepublished to be found for: speed up my slow pandas code on a large dataset · query parquet files in S3 as a pandas DataFrame · join MySQL and Postgres data in Python without a server chdb python pandas dataframes | application/ai-skill-archive+gzip |
| chdb-sqlanswers in 149ms Use when the user wants to run SQL — especially analytical SQL — on local files (parquet/csv/json), URLs, S3 paths, or remote databases (Postgres, MySQL, MongoDB, ClickHouse Cloud, Iceberg, Delta Lake) without setting up a server. Provides chDB — embedded C... endpoint: https://clickhouse.com/.well-known/agent-skills/chdb-sql.tar.gzidentifier: urn:air:clickhouse.com:skill:chdb-sqlpublished to be found for: run ClickHouse SQL on local parquet files without a server · query CSV and JSON files with SQL from Python · read S3 or Iceberg tables with ClickHouse table functions in Python chdb python sql embedded | application/ai-skill-archive+gzip |
| clickhouse-architecture-advisornot yet checked MUST USE when designing ClickHouse architectures, selecting between ingestion or modeling patterns, or translating best practices into workload-specific system designs. Complements clickhouse-best-practices with decision frameworks and explicit provenance l... endpoint: https://clickhouse.com/.well-known/agent-skills/clickhouse-architecture-advisor.tar.gzidentifier: urn:air:clickhouse.com:skill:clickhouse-architecture-advisorpublished to be found for: design a ClickHouse architecture for high-volume event ingestion · should I use materialized views or projections for this workload · how should I model multi-tenant analytics in ClickHouse clickhouse architecture data-modeling | application/ai-skill-archive+gzip |
| clickhouse-best-practicesnot yet checked MUST USE when reviewing ClickHouse schemas, queries, or configurations. Contains 31 rules that MUST be checked before providing recommendations. Always read relevant rule files and cite specific rules in responses. endpoint: https://clickhouse.com/.well-known/agent-skills/clickhouse-best-practices.tar.gzidentifier: urn:air:clickhouse.com:skill:clickhouse-best-practicespublished to be found for: review my ClickHouse schema for problems · is my ClickHouse ORDER BY key right for this query pattern · why is this ClickHouse query slow clickhouse sql schema-design performance | application/ai-skill-archive+gzip |
| clickhouse-js-node-troubleshootingnot yet checked Troubleshoot and resolve common issues with the ClickHouse Node.js client (@clickhouse/client). Use this skill whenever a user reports errors, unexpected behavior, or configuration questions involving the Node.js client specifically — including socket hang-... endpoint: https://clickhouse.com/.well-known/agent-skills/clickhouse-js-node-troubleshooting.tar.gzidentifier: urn:air:clickhouse.com:skill:clickhouse-js-node-troubleshootingpublished to be found for: my Node.js ClickHouse client keeps throwing socket hang up errors · inserts from @clickhouse/client fail intermittently · ClickHouse Node.js connection drops randomly under load clickhouse nodejs javascript troubleshooting | application/ai-skill-archive+gzip |
| clickstack-otel-collectornot yet checked Use when a user wants to wire an OpenTelemetry collector into a Managed ClickStack service on ClickHouse Cloud, either by deploying a new local collector (Docker run or Docker Compose) or by configuring their own existing collector, then send rich synthetic... endpoint: https://clickhouse.com/.well-known/agent-skills/clickstack-otel-collector.tar.gzidentifier: urn:air:clickhouse.com:skill:clickstack-otel-collectorclickhouse | application/ai-skill-archive+gzip |
| infra-clickhouseanswers in 136ms Sets up and manages ClickHouse using the clickhousectl CLI — installs and runs a local ClickHouse server for development, and creates managed ClickHouse Cloud services for production (authentication, service creation, schema migration, application connectio... endpoint: https://clickhouse.com/.well-known/agent-skills/infra-clickhouse.tar.gzidentifier: urn:air:clickhouse.com:skill:infra-clickhouseclickhouse | application/ai-skill-archive+gzip |
| infra-postgresanswers in 340ms Sets up and manages Postgres using the clickhousectl CLI — runs a local Docker-backed Postgres for development, and creates and operates managed ClickHouse Cloud Postgres services (connections, TLS, runtime config, read replicas, failover, point-in-time res... endpoint: https://clickhouse.com/.well-known/agent-skills/infra-postgres.tar.gzidentifier: urn:air:clickhouse.com:skill:infra-postgresclickhouse | application/ai-skill-archive+gzip |
https://clickhouse.com/.well-known/ai-catalog.json, this publisher's own file.
Identifiers are reproduced exactly as published.
Note: this is the pre-v0.91 path. The specification renamed the manifest to /.well-known/ard.json, and most of the ecosystem still serves the older name.
Of the resources listed, 6 have been probed for reachability.
"Answers" and "no response" describe only whether an endpoint replied when last probed:
services go down and come back, and an entry is demoted rather than removed. None of this
is a trust, quality or safety rating.
https://neuronto.com/search, or connect an agent to https://neuronto.com/mcp.
If this is your domain, the free console shows what a registry
sees when it reads your manifest.