MCP server

Configure upstream MCP servers behind the P0 AI Gateway to make them available to P0-managed agents under policy.

The MCP server component configures an upstream MCP server behind the P0 AI Gateway. Once an MCP server is configured, it is available to P0-managed agents across your organization: agents connect to it through the gateway's URL, and every tool call is authenticated and checked against policy before it reaches the upstream server.

Prerequisites

• A registered Gateway component, and the gateway deployed in your environment. See Deploying the P0 AI Gateway.

Types of MCP server

When you add a server, you set its Definition: a server predefined by P0, or a custom server you define yourself.

Server	Type	Description
AWS	Predefined	Exposes the AWS CLI to agents. Requires the AWS OIDC component.
GCP	Predefined	Exposes Google Cloud APIs to agents, with one server per Google Cloud service. Requires a GCP Workload Identity Federation provider.
Custom	Custom	A server you define yourself, for any MCP server P0 does not ship a predefined definition for.

Add an MCP server

Every MCP server starts with the same steps. The final configuration screen differs by server. Continue to the AWS, GCP, or Custom page once you reach it.

1. Navigate to Integrations on p0.app and select Agentic gateway, then choose the MCP server component.

1. Click Add server.

1. Enter the server details, then click Next:

• Server identifier: a name for this server within P0.

• Gateway: the registered gateway that hosts this server.

• Path: the path, relative to the gateway URL, where agents reach this server.

1. Set the Definition to the kind of server you are adding:

   • P0: a predefined server. Continue to its page, AWS MCP server or GCP MCP server.

   • Custom: a server you define yourself. See Custom MCP server.

Next steps

Once a server is configured behind the gateway, each developer connects their own agent to it. See Use MCP servers with Claude Code.