Calculate Risk Adjustment Factor (RAF) score
AI agents call calculate_raf to retrieve information from Medikode Medical Coding MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
RAF score calculation is a read-only analytical operation on medical coding data. It retrieves or processes existing documentation and codes to compute a risk adjustment metric—a standard healthcare actuarial calculation with no side effects, data modification, or irreversible actions.
From the tool's definition Tool name 'calculate_raf' and description 'Calculate Risk Adjustment Factor (RAF) score' indicate a computational/analytical operation that reads existing medical coding data (CPT/ICD-10 codes, HCC codes) to derive a RAF metric.
Attacks that exploit this kind of access
Calculate Risk Adjustment Factor (RAF) score. It is categorised as a Read tool in the Medikode Medical Coding MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Medikode Medical Coding MCP Server MCP server in PolicyLayer and add a rule for calculate_raf: 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 Medikode Medical Coding MCP Server. Nothing to install.
calculate_raf 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 calculate_raf 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 calculate_raf. 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.
calculate_raf is provided by the Medikode Medical Coding MCP Server MCP server (raelango/medikode-mcp-server). 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 →