What it does
Warehouse MCP provides read-only access to a data warehouse for AI agents, with controls applied to that access. The publisher lists a SQL guard, row policies, PII pseudonyms and an audit log as its governance features.
The publisher's description points to use cases where agents need warehouse data but the access must be restricted, filtered by row policy, pseudonymised for personal data, and recorded in an audit log. The publisher's documentation does not describe setup steps, so the requirements for running it are not stated here.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
Warehouse MCP
Governed read-only warehouse access for agents: SQL guard, row policies, PII pseudonyms, audit log.
v0.1.0As shown on registry.modelcontextprotocol.io when we last read it