ClickHouse MCP for AI agents
Agents read ClickHouse MCP at once. Changes and sends are held for a person's approval by default.
About ClickHouse MCP
Manage and query ClickHouse Cloud observability data through the managed ClickStack MCP server.
What an agent can do in ClickHouse MCP
Every ClickHouse MCP action is classed by the platform as a read, a change or a send. Reads run at once. Changes and sends are held for a person by default.
Runs at once (reads)
Looks things up in ClickHouse MCP without asking first. 22 actions.
- Clickstack describe metricDRILL-DOWN: Use after clickstack_list_metrics (or after a clickstack_describe_source sample) to get attribute keys, sampled values, unit, and description for a specific (metricName, kind) pair. Attrib
- Clickstack describe sourceCALL THIS BEFORE WRITING QUERIES — prevents unknown-column errors. Returns the full column schema, map-attribute keys, and sampled low-cardinality values (e.g. SeverityText, StatusCode, ServiceName) f
- Clickstack emerging signalsDetect what is NEW or GONE between an earlier baseline window and a current window — log/event patterns that emerged, ramped up, or stopped. This answers "what changed / what is novel?" — NOT "what at
- Clickstack event patternsDiscover the most common log messages and event patterns. Samples random events, clusters them using the Drain algorithm, and returns patterns sorted by frequency with estimated counts and time trends
- Clickstack get alertWithout an ID: list all alerts as a high-level summary (id, name, displayName, tags, state, source, interval). Optionally filter by state (e.g. state="ALERT" for firing alerts). With an ID: get full a
- Clickstack get dashboardWithout an ID: list all dashboards (returns IDs, names, tags). With an ID: get full dashboard detail including all tiles and configuration.
- Clickstack get dashboard tileRetrieve a single tile from a dashboard by tileId. Useful for inspecting one tile without loading the full dashboard. Use clickstack_get_dashboard (without an ID) to list dashboards, then clickstack_g
- Clickstack get saved searchWithout an ID: list all saved searches as a high-level summary (id, name, tags). With an ID: get full saved search detail including query, source, filters, and configuration.
- Clickstack get source filter valuesList the available values for the required source filter columns on a single source. Use this BEFORE calling any query tool against a source whose configuration declares `requiredSourceFilters`. ONLY
- Clickstack get webhookList available webhook destinations (id, name, service type). Use the returned id as the webhookId when creating alerts with clickstack_save_alert.
- Clickstack list metricsDISCOVERY: Use this after clickstack_describe_source when you need more metric names than the per-kind sample shows, or when you want to narrow by kind / name pattern / time window. Returns paginated
- Clickstack list sourcesList all data sources (logs, metrics, traces) and database connections available to this team. Returns source IDs, names, kinds, and connection IDs as a lightweight catalog. Metric sources additionall
Show all 22
- Clickstack list teamsList all teams the current user belongs to and identify which team is active for this session. Use this to discover available teams when the user works across multiple teams. To switch teams, the MCP
- Clickstack query tileExecute the query for a specific tile on an existing dashboard. Useful for validating that a tile returns data or for spot-checking results without rebuilding the query from scratch. Use clickstack_ge
- Clickstack query tilesRun the queries for many tiles of a dashboard in ONE call and return a compact per-tile success/failure summary. This is the efficient way to validate an entire dashboard after clickstack_save_dashboa
- Clickstack searchBrowse individual log/event/trace rows. Use this when you need to see raw events, investigate specific log lines, or drill into individual records matching a filter. PREFER THIS over clickstack_sql. O
- Clickstack search dashboardsSearch dashboards by name and/or tags. Returns matching dashboards with their IDs, names, and tags. More targeted than clickstack_get_dashboard (which lists all dashboards). At least one of query or t
- Clickstack sqlExecute raw ClickHouse SQL. LAST-RESORT TOOL — do NOT reach for this first. Default to the builder tools for querying; they are more reliable and produce richer, structured results: • clickstack_table
- Clickstack tableCompute aggregated metrics as a table, single number, pie chart, or bar chart. Use this for grouped aggregations, top-N queries, single-value KPIs, or proportional breakdowns. PREFER THIS over clickst
- Clickstack timeseriesPlot metrics over time as a line or stacked bar chart. Use this when you need to visualize trends, compare time-series, or monitor metric changes over a time window. PREFER THIS over clickstack_sql. O
- Clickstack trace top time consuming operationsGiven a parent-span filter and a time window, return the child operations contributing the most cumulative time across all traces matching the parent filter. Same algorithm as the in-app "Top Most Tim
- Clickstack trace waterfallFetch all spans in ONE trace and return them as a parent/child waterfall, pre-ordered for human-readable display. Use this for "show me a concrete example trace" or "what happened in trace X" investig
Held for approval by default (changes and sends)
Held for a person's approval by default. The approval is recorded and the action is sent once, never twice, with 10 seconds to undo. 5 actions.
- Clickstack delete dashboardPermanently delete a dashboard by ID. Also removes any alerts attached to its tiles. Use clickstack_get_dashboard (without an ID) to list available dashboard IDs.
- Clickstack delete sourcePermanently delete a data source by ID. Other sources may reference it (e.g. a trace source linked to a log source) — those links are left dangling, so check dependencies first. Use clickstack_list_so
- Clickstack delete webhookPermanently delete a webhook by ID. Blocked while any alert still references it — reassign or delete those alerts first. Use clickstack_get_webhook to list available webhook IDs.
- Clickstack save saved searchCreate a new saved search (omit id) or update an existing one (provide id). A saved search stores a reusable query against a data source. Use clickstack_list_sources to find the sourceId.
- Clickstack save webhookCreate a new webhook (omit id) or update an existing one (provide id). Use the returned id as the webhookId when creating alerts with clickstack_save_alert. Required: name, service (slack, generic, or
Changes wait in Needs you
Changes and sends in ClickHouse MCP are held for a person's approval by default. The approval is recorded, and the action is sent once, never twice, with 10 seconds to undo.
Related connectors
ClickHouse MCP questions
Can an agent change data in ClickHouse MCP on its own?
Not by default. Changes and sends in ClickHouse MCP are held for a person's approval. The approval is recorded, and the action is sent once, never twice, with 10 seconds to undo.
What can an agent read in ClickHouse MCP?
This connector lists 22 read actions. Reads run at once, without waiting for approval.
How does ClickHouse MCP connect?
It connects with dcr oauth. Connectors are built and maintained by third-party developers; availability is confirmed during scoping.