AI agents use scf_update_system 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.
This tool creates or modifies data in a reversible manner without permanently destroying it or executing arbitrary code. It requires editor+ role for access control. The blast radius is medium because misconfiguration of system records in a compliance platform could affect downstream risk assessments or control evaluations, but changes can be reverted.
From the tool's definition Tool description explicitly states 'Update an existing system record (write — editor+ role)'. The verb 'Update' and classification 'write' in the description confirm this modifies data reversibly.
Attacks that exploit this kind of access
Update an existing system record (write — editor+ role). All fields are optional; only provided fields are applied. 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_update_system: 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_update_system 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_update_system 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_update_system. 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_update_system 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 →