AI agents call scf_get_window_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.
The verb 'Get' combined with 'Returns full detail' clearly indicates a read-only query operation. The tool retrieves assessment metadata and results (window bounds, coverage, findings, etc.) without creating, modifying, deleting, or executing any operations. Blast radius is minimal—an AI agent misusing this would at worst access assessment data it shouldn't, without risking data loss or system harm.
From the tool's definition Tool description states 'Get one windowed AI assessment by ID. Returns full detail...' — this is a retrieval operation that queries and returns data with no side effects or modifications.
Attacks that exploit this kind of access
Get one windowed AI assessment by ID. Returns full detail: window bounds, frequency, file IDs, coverage, expected artifact types, status, relevance score, findings, summary, hashes, tokens, cost. 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_window_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_window_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_window_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_window_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_window_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 →