AI agents call scf_list_vendors to retrieve information from Scf without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves vendor information from the compliance platform. It performs a read-only operation that does not create, modify, delete, or execute any actions. The blast radius of misuse is minimal—an AI agent could only retrieve existing vendor data, which is informational in nature within a compliance context. No financial, destructive, or executable side effects are possible.
From the tool's definition Tool name and description: 'scf_list_vendors' — 'List third-party vendors in the organization'. The verb 'list' indicates a retrieval operation with no side effects.
Attacks that exploit this kind of access
List third-party vendors in the organization. It is categorised as a Read tool in the Scf MCP Server, which means it retrieves data without modifying state.
Register the Scf MCP server in PolicyLayer and add a rule for scf_list_vendors: 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_list_vendors is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the scf_list_vendors 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_list_vendors. 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_list_vendors 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 →