# Agent access — Give an AI agent useful work across your stack — Runner

> Runner gives your AI agent an OAuth-protected MCP connection, checks the caller's permission on every call, holds each answer to the shape its tool declares, and gives admins a stop control from the whole workspace down to a single tool. Usually bought as Composio, Zapier, Pipedream or n8n.

Canonical: https://www.runtheworld.ai/product/agent-access

**Built into Runner**

- An MCP endpoint your agent connects to, with OAuth
- Permissions checked fresh on every call, never from a cached copy
- Every tool is graded, and a public post from anyone but an owner or admin waits in Approvals
- Each answer checked against the shape its tool declares before it goes back
- A stop control for the workspace, a project, one tool or one person's connections

**Worth knowing** What an agent may call follows the permissions of the teammate it signed in as, checked again on every call, and destructive work stays off the list by design. A tool that changes a record declares the approval it needs and how it is undone; a public post runs on an owner's or admin's own call and waits in Approvals for anyone else's — these are the controls around an agent, not an agent deciding for you.

Usually bought as Composio, Zapier, Pipedream or n8n.