Revoke a per-project capability grant by id. Params:
AI agents call revoke_project_grant to permanently remove resources in Run402 — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Revoking a capability grant removes access permissions for a project. This is a destructive action because it permanently removes a granted capability; restoring it would require a separate re-grant action. Misuse could cause agents or users to lose access to critical project capabilities, potentially breaking workflows.
From the tool's definition 'Revoke a per-project capability grant by id' — revoking a grant is an irreversible removal of an access/capability permission that cannot be easily undone without re-granting
Attacks that exploit this kind of access
Revoke a per-project capability grant by id. Params:. It is categorised as a Destructive tool in the Run402 MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Run402 MCP server in PolicyLayer and add a rule for revoke_project_grant: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Run402. Nothing to install.
revoke_project_grant is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the revoke_project_grant rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for revoke_project_grant. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
revoke_project_grant is provided by the Run402 MCP server (kychee-com/run402). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →