Britive MCP Gateway

What’s New

The Britive MCP Gateway sits between the AI that calls your tools and the MCP servers that run them. Every tool call flows through it, and the Gateway decides whether that identity may make it, gives the backend a credential that expires, and records what happened.

It serves people working through an assistant — Claude Desktop, Claude Code, Codex — who sign in with Britive through their browser, and autonomous agents and workloads that present a Britive token directly with nobody watching.

What It Removes

An MCP server needs credentials to be useful. Left alone that means a long-lived API key in a config file, shared by everyone using the agent, with no record of which identity triggered which call.

• The caller never holds a credential. The Gateway obtains one per call and injects it into the backend request. It is never handed to the model.
• Each identity sees only its own tools. The tool list a client receives is built from that caller’s Britive policy, so two identities on the same Gateway see different catalogues.
• Permission is checked twice — once when the catalogue is built, and again when a tool is actually invoked, so a stale list cannot be used to reach anything.

Learn More