Skip to main content
Midplane is a gateway between AI agents and your Postgres databases. Claude queries your data through it, never holds a connection string, and every statement it sends is checked against your policy before it runs. You need a running gateway (get started). claude.ai runs on Anthropic’s servers, so it reaches the gateway only at a public HTTPS URL.
1

Give the gateway a public URL

Use Anthropic’s MCP tunnel (in research preview; for claude.ai it needs the Enterprise plan) or your own ingress, such as a load balancer allowlisted to Anthropic’s IP ranges. Hosted agents sets up either.
2

Register the URL

Add it to the gateway’s public_urls. If the gateway enrolled before you added it, press Register on the project’s Gateways page.
3

Add the connector

In claude.ai, add a connector with the gateway’s public URL followed by /mcp, such as https://midplane.<tunnel domain>/mcp. The Agents page shows it under Connect an agent.
4

Sign in and choose what it may reach

Set each database to None, Read or Read + write, and Allow.
5

Try it

Ask Claude which tables it can see. Its statement shows up in the project’s Query log.
You’re set: Claude can answer questions from your data, and only what your policy allows runs. Masked columns stay masked, writes that need approval wait for a person, and every statement is in the audit log. Results go from your gateway to Anthropic, never through Midplane Cloud.
To cut it off, Revoke it under Connected agents on the Agents page. It has to sign in again within 15 minutes.

​
If it doesn’t work

  • The consent page says it wants access, with no databases: you aren’t a member of the gateway’s project, or the URL isn’t registered. Ask an owner of the organization.
  • The Gateways page shows the URL as not registered: see troubleshooting.
Tested by apps/gateway/test/urls.e2e.test.ts (several URLs, and a tunnel that rewrites Host) and apps/gateway/test/auth.test.ts for the gateway’s side; the client’s steps by hand.