Warehouse MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 358 installs a week from pypi. Last commit 1 Nov 2026.
Governed read-only warehouse access for agents: SQL guard, row policies, PII pseudonyms, audit log.
Today is the operative word: we check Warehouse MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add warehouse-mcp -- uvx warehouse-mcp
{
"mcpServers": {
"warehouse-mcp": {
"command": "uvx",
"args": [
"warehouse-mcp"
]
}
}
}
[mcp_servers.warehouse-mcp]
command = "uvx"
args = ["warehouse-mcp"]
{
"mcpServers": {
"warehouse-mcp": {
"command": "uvx",
"args": [
"warehouse-mcp"
]
}
}
}
{
"servers": {
"warehouse-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"warehouse-mcp"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
WAREHOUSE_MCP_POSTGRES_DSN (Postgres connection string of a read-only role (Postgres configs only)), WAREHOUSE_MCP_PII_SALT (Fixed salt for stable pseudonyms across restarts (16-128 letters or digits)), WAREHOUSE_MCP_AUDIT_LOG (Path of the JSONL audit log; stderr when unset).
Governed, read-only Postgres access for AI agents: SQL safety, RLS, budgets, tamper-evident audit.
Read-only, guarded SQL access for AI agents: PostgreSQL, MySQL, ClickHouse, Oracle, SQL Server, Db2
Safe, read-only Postgres and MySQL access for AI agents. Audit log + column-level controls.
Fail-closed, read-only PostgreSQL and MongoDB access for AI agents over MCP.
Guardrail for AI agents on SQL Server: statement blocking, optional read-only mode and an audit log.
The governed database layer for agents — every store in one look, under policy: read-only by
Query your org's data in natural language — read-only MCP access to SQL, NoSQL, files & warehouses.
Safe SQL gateway for AI agents: SELECT-only validation, access policies, masking, audit trail, evals
Answers built from our own checks of this server.