AI agents use scf_create_vendor 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 a new vendor record in a Third-Party Risk Management (TPRM) registry, which is a reversible data modification operation. It does not delete, execute code, or move money. The 'medium' severity reflects that vendor creation could affect risk assessments and compliance records, but the impact is limited to vendor registry data and requires editor+ role access.
From the tool's definition Tool name includes 'create' and description explicitly states 'write — editor+ role' and 'Create a vendor in the TPRM registry'
Attacks that exploit this kind of access
Create a vendor in the TPRM registry (write — editor+ role). Platform auto-scores risk based on criticality and data handling. 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_create_vendor: 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_create_vendor 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_create_vendor 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_create_vendor. 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_create_vendor 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 →