AI agents call scf_get_evidence_maturity 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 'get_' prefix and retrieval semantics classify this as a Read operation with no side effects. However, confidence is lowered due to the truncated/unclear description that does not fully explain what is being retrieved or its sensitivity. No destructive, executable, or financial operations are indicated.
From the tool's definition Tool name 'scf_get_evidence_maturity' uses the verb 'get', which indicates a retrieval operation. Description is incomplete ('Get the organization') and uninformative.
Attacks that exploit this kind of access
Get the organization. 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_maturity: 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_maturity 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_maturity 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_maturity. 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_maturity 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 →