AI agents use scf_trigger_dpsia to create or update resources in Scf — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Scf environment.
The tool queues/triggers an assessment process, which is a write operation that creates a new assessment job. It does not delete data or move money. The blast radius is medium because triggering an erroneous DPSIA against a vendor could produce inaccurate compliance records and affect vendor risk posture scores, but it is reversible and does not cause direct data destruction or financial harm.
From the tool's definition Queue a Data Protection Security Impact Assessment (DPSIA) for a vendor (write — editor+ role, async)
Attacks that exploit this kind of access
Queue a Data Protection Security Impact Assessment (DPSIA) for a vendor (write — editor+ role, async). Scores posture against CIA triad and certification requirements. It is categorised as a Write tool in the Scf MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Scf MCP server in PolicyLayer and add a rule for scf_trigger_dpsia: 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 Scf. Nothing to install.
scf_trigger_dpsia is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the scf_trigger_dpsia 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 scf_trigger_dpsia. 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.
scf_trigger_dpsia is provided by the Scf MCP server (mcp-server-scf). 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 →