AI agents invoke scf_revalidate_evidence_file to trigger actions in Scf. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool triggers the validation engine to re-process an evidence file, which constitutes executing an external operation (the validation pipeline). It also has a write side-effect ('write — editor+ role') as it returns an 'updated result', implying it modifies the stored validation state. Since it executes a validation engine and updates state, Execute is the most appropriate category (more severe than Write).
From the tool's definition Re-run the validation engine against an evidence file... Checks catalog existence, content type, field coverage, freshness, storage. Returns the updated result.
Attacks that exploit this kind of access
Re-run the validation engine against an evidence file (write — editor+ role). Checks catalog existence, content type, field coverage, freshness, storage. Returns the updated result. It is categorised as a Execute tool in the Scf MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Scf MCP server in PolicyLayer and add a rule for scf_revalidate_evidence_file: 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_revalidate_evidence_file is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the scf_revalidate_evidence_file 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_revalidate_evidence_file. 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_revalidate_evidence_file 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 →