AI agents call scf_get_evidence_validation 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 purely informational query operation that retrieves pre-computed validation metadata about an evidence file. It has no destructive impact, does not execute arbitrary code, does not create or modify records, and does not involve financial operations. The blast radius of misuse is minimal—an agent could only read validation information already stored in the system.
From the tool's definition Tool retrieves validation results for evidence files, returning status, completeness score, rule findings, source, and timestamp. No side effects, no data modification, no execution, no deletion.
Attacks that exploit this kind of access
Get the validation result for a single evidence file: status (valid/warning/partial/invalid), completeness score, individual rule findings, source, and timestamp. 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_validation: 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_validation 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_validation 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_validation. 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_validation 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 →