Skip to main content
When a user connects an agent from their own AI client, our consent screen records a grant. It is the standing authority behind every later tools/call — see MCP export. Because the grant lives with us, you manage it through us. Both endpoints take your workspace API key, and neither is gated on credits: you must always be able to cut off access.

​
The object

​
uuid
Pass to the delete endpoint to revoke.
​
string
The subject your login bridge asserted. Every run made under this grant carries it.
​
string[]
What the client asked for and the user allowed — read, write, or both. Recorded for your audit; what the client can actually call is set by the agent’s wiring. See Scopes.
​
object
The exact published agent version this grant is for. A grant never spans agents.
​
object
The MCP client’s registered name, as it introduced itself. Treat it as a label, not an identity.
​
string
When the user first consented.
​
string
When an access token was most recently issued against the grant. null if none ever was. This tracks re-authorization, not tool calls — read requests with origin: "mcp" for activity.

​
Unique per subject, agent and client

The same user connecting the same agent from the same client twice updates one grant rather than accumulating them. Connecting from a second client, or to a second agent, is a second grant.

​
Revoking

Revoking marks the grant and expires every access token issued against it. The client may still hold a token it believes is live; it stops working at our door on its next call. Nothing already finished is undone. Only grants in your own workspace are visible or revocable. Listing returns active grants, newest first, cursor-paginated; pass subject to narrow to one user.

​
Errors