AI agents call scf_get_capability_theme 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 returns capability theme information (posture scores, metrics, and metadata) for compliance/security frameworks. It performs no write, delete, execution, or financial operation. The verb 'Get' and lack of any modifying language confirm this is a retrieval operation with no side effects.
From the tool's definition Tool name 'scf_get_capability_theme' with description 'Get a single capability theme (KSI) with full posture, multi-axis scores, band, and legacy posture_percentage' — uses 'Get' verb and retrieves read-only data without modification or side effects.
Attacks that exploit this kind of access
Get a single capability theme (KSI) with full posture, multi-axis scores, band, and legacy posture_percentage. 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: 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 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 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. 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 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 →