AI agents call scf_get_risk 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 tool queries and retrieves existing risk assessment data. It has no side effects, does not modify state, execute code, delete records, or move money. Classification as Read is appropriate; severity is low because unauthorized disclosure of risk metadata poses minimal risk to system integrity or agent misuse potential.
From the tool's definition Tool description explicitly states 'Get one risk assessment in detail' — a retrieval operation with no modification, deletion, or execution of external operations. Returns metadata: likelihood, impact scores, treatment plan, owner, and review date.
Attacks that exploit this kind of access
Get one risk assessment in detail: likelihood, inherent and residual impact scores, treatment plan, owner, and review date. 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_risk: 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_risk 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_risk 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_risk. 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_risk 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 →