AI agents call scf_get_evidence_assessment 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 operation that queries and returns existing evidence assessment results (status, scores, findings, metadata). It has no side effects and merely retrieves already-stored analysis data. The highest blast radius would be information disclosure of compliance/risk assessment details, which is low severity in a compliance platform context.
From the tool's definition Tool name contains 'get'; description states 'Get the AI assessment' and 'Poll after'—retrieves pre-computed assessment data without modifying, creating, or deleting anything.
Attacks that exploit this kind of access
Get the AI assessment for an evidence file: status, relevance score (0–100), structured findings, summary, and audit metadata (model, tokens, cost). Poll after scf_trigger_evidence_assessment. 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_evidence_assessment: 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_evidence_assessment 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_evidence_assessment 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_evidence_assessment. 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_evidence_assessment 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 →