Connect ClickHouse MCP to your AI agent
Manage and query ClickHouse Cloud observability data through the managed ClickStack MCP server.
We set up the connection using your own ClickHouse MCP account, with keys you control, and keep it running. Your agent picks it up and starts doing the work.
Actions
What your agent can do in ClickHouse MCP
Each one is a real action the agent can take on its own, the same things a person clicking around ClickHouse MCP could do. Read-only by default; write actions are confirmed against your policy.
- Clickstack delete dashboard Permanently 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 source Permanently 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_sources to find avail…
- Clickstack delete webhook Permanently 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 describe metric DRILL-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. Attribute keys vary per m…
- Clickstack describe source CALL 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) for a single data so…
- Clickstack emerging signals Detect 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 attribute value diffe…
- Clickstack event deltas Rank the properties of two row groups (logs or trace spans) by how much their value distributions differ. Same algorithm as the in-app Event Deltas view (DBDeltaChart). High-cardinality fields (IDs, request IDs, timesta…
- Clickstack event patterns Discover 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. PREFER THIS TOOL…
- Clickstack get alert Without an ID: list all alerts as a high-level summary (id, name, state, source, interval). Optionally filter by state (e.g. state="ALERT" for firing alerts). With an ID: get full alert detail including configuration an…
- Clickstack get dashboard Without an ID: list all dashboards (returns IDs, names, tags). With an ID: get full dashboard detail including all tiles and configuration.
- Clickstack get dashboard tile Retrieve 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_get_dashboard (with…
- Clickstack get saved search Without 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 values List 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 use this for source…
- Clickstack get webhook List available webhook destinations (id, name, service type). Use the returned id as the webhookId when creating alerts with clickstack_save_alert.
- Clickstack list metrics DISCOVERY: 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 metric names per ki…
- Clickstack list sources List 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. NEXT STEP: After identifying the source(s) yo…
- Clickstack list teams List 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 client must include…
- Clickstack patch dashboard Make targeted updates to a dashboard without resubmitting the full object. You can update dashboard-level fields (name, tags) and/or replace a single tile by tileId — all in one call. Unmentioned tiles and fields are pr…
- Clickstack query tile Execute 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_get_dashboard with an…
- Clickstack query tiles Run 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_dashboard — prefer it over…
- Clickstack save alert Create a new alert (omit id) or update an existing one (provide id). Alerts monitor a saved search or dashboard tile and fire when the metric crosses a threshold. A webhook notification channel is required.
- Clickstack save dashboard Create a new dashboard (omit id) or update an existing one (provide id). Call clickstack_list_sources first to obtain sourceId and connectionId values. IMPORTANT: After saving a dashboard, always run clickstack_query_ti…
- Clickstack save saved search Create 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 source Create a new data source (omit id) or update an existing one (provide id) so shipped telemetry becomes queryable. Update is a full replace of the source definition. Required for all kinds: kind, name, connection, databa…
- Clickstack save webhook Create 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 incidentio), and u…
- Clickstack search Browse 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. Only drop to raw SQL…
- Clickstack search dashboards Search 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 tags must be provide…
- Clickstack sql Execute 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 — aggregations, to…
- Clickstack table Compute 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 clickstack_sql. Only drop…
- Clickstack timeseries Plot 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. Only drop to raw SQL…
- Clickstack trace top time consuming operations Given 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 Time Consuming Operati…
- Clickstack trace waterfall Fetch 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" investigations — the tool w…
Setup
How we connect it
- 1
Connect your account
You log in with your own ClickHouse MCP account. We never see your password, and you can revoke access from ClickHouse MCP at any time.
- 2
Set the guardrails
Read-only by default. You choose which write actions the agent may take, and anything outside that policy gets confirmed with you first.
- 3
We keep it running
Health checks on every connection, updates handled for you, and we watch the first week of activity to make sure the work lands.
FAQ
ClickHouse MCP questions, answered.
You sign in with your own ClickHouse MCP account. Permissions are scoped to the minimum the agent needs, the connection is health-checked, and you can revoke access from ClickHouse MCP at any time.
The actions ClickHouse MCP's API allows, the same things a person clicking around the app could do. Connections start read-only by default; write actions are confirmed against the policy you set before the agent takes them.
Connections are priced per tool on top of the base plan. Some are included, some are premium. See pricing for how connection charges work.
Standard tools are ready inside 7 business days of the setup call. We test the connection end to end, walk you through how the agent uses it, and watch the first week of activity.
Ready to put ClickHouse MCP to work?
Tell us what your team runs on. We set up the connection, secure it, and your agent takes it from there.
All product names, logos, and brands are property of their respective owners; used for identification only. ZeroToClaw is not affiliated with or endorsed by ClickHouse MCP.