ClickHouse MCP Server vs ObsessionDB

ClickHouse MCP Server

Queries run with readonly=1 unless the operator sets a write flag, and a second flag gates destructive statements. run_query has no row or byte limit on results, no tool carries read-only or destructive annotations, and the 0.3.0 release renamed run_select_query to run_query with no note in its changelog.

ObsessionDB

The hosted MCP server uses OAuth 2.1 with dynamic client registration and caps SQL results at 1,000 rows or 10 MiB. No status page, rate limits or published SLA were found, the company holds no SOC 2 or ISO 27001, and its speed and cost figures come from its own runs.

ClickHouse MCP Server

1. Put a LIMIT on every run_query call. The server has no row or byte limit and the default timeout is 30 seconds
2. Call the tool run_query. ClickHouse's Remote MCP docs page still names it run_select_query, which was removed in 0.3.0
3. Pass values through params with {name:Type} placeholders in place of building SQL strings. Tuple and Map types can't be bound
4. Set include_detailed_columns to false on list_tables for wide schemas. Page tokens are single-use and expire after one hour
5. Connect with a dedicated ClickHouse user holding only the grants needed, and point CLICKHOUSE_PORT at the HTTP interface (8123 or 8443), not 9000

ObsessionDB

1. Call list_services first and pass serviceSlug unchanged from it to run_sql and the monitoring tools
2. Push aggregation into SQL with GROUP BY or ORDER BY ... LIMIT. Results stop at 1,000 rows or 10 MiB and set truncated: true
3. Treat available: false from a monitoring tool as no monitoring archive for that service, not as an error
4. Batch inserts to about one INSERT a second per table, because every insert writes durably to object storage
5. Expect a browser sign-in on first connect. A person must approve the OAuth consent at console.obsessiondb.com