AI agents call scf_get_vendor_research 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 is a read-only query tool that retrieves vendor security research results. There is no data creation, modification, deletion, code execution, or financial impact. The word 'Get' combined with the polling pattern (reading results after a trigger operation) confirms this is a passive data retrieval operation.
From the tool's definition Tool description states 'Get the latest vendor research result' — a retrieval operation with no side effects. The action is to fetch and read previously generated data (breach history, vulnerabilities, security posture analysis), not modify or delete anything.
Attacks that exploit this kind of access
Get the latest vendor research result: breach history, known vulnerabilities, and security posture analysis. Poll this after scf_trigger_vendor_research. 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_get_vendor_research: 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_get_vendor_research 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_get_vendor_research 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_get_vendor_research. 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_get_vendor_research 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 →