Get per-theme evidence metrics: controls with evidence, file counts by assessment status, average relevance score, and derived confidence (strong/moderate/weak/none). Use for KSI evidence dashboards.
AI agents call scf_get_capability_theme_evidence_posture 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 reads and aggregates compliance evidence data for dashboard purposes. It performs no writes, deletions, or code execution. The metrics retrieved are derived from existing data without side effects. While it may expose compliance posture information, the read-only nature and lack of operational impact classify it as Read with low severity.
From the tool's definition Tool retrieves and queries evidence metrics and control data: 'Get per-theme evidence metrics,' 'controls with evidence,' 'file counts,' 'average relevance score,' 'derived confidence.' No modification, deletion, or execution operations implied.
Attacks that exploit this kind of access
Get per-theme evidence metrics: controls with evidence, file counts by assessment status, average relevance score, and derived confidence (strong/moderate/weak/none). Use for KSI evidence dashboards. 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_capability_theme_evidence_posture: 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_capability_theme_evidence_posture 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_capability_theme_evidence_posture 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_capability_theme_evidence_posture. 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_capability_theme_evidence_posture 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 →