Create a guardrail from a description

If this connection lists call_platform_tool instead of the tools this workflow names, find each named tool with search_platform_tools, describe it with describe_platform_tool, then run it with call_platform_tool and the same arguments. Whether a tool exists for you is decided by describe_platform_tool with its exact name, not by tools/list or one page of search results: a name returned in not_found is unavailable to you, so say so rather than guess. The call itself still checks your access. When execute is also listed, a multi-step read may run in execute with tools.search, tools.describe and tools.call on platform--<tool name> paths. End each execute run at a confirmation point and ask the user before any write.

Turn "stop agents deleting anything in production" into a reviewed policy: map the description to a preset, show the administrator exactly what the policy will do, and create it only after they confirm.

Scope and prerequisites

• Use the executing client's authenticated Platform MCP connection. Installing this skill or signing in to the dashboard does not establish MCP authorization.
• Policy writes need org:admin in the connected organization and require an explicit project slug. Do not silently choose the Default project; a request that explicitly names it is sufficient.
• Never request or expose credentials. If authentication or permissions fail, stop and ask the user to reconnect or obtain access through the approved setup flow.
• This skill creates one policy. It does not edit existing policies, create exclusions, or change MCP configuration.

Workflow