Verify an ICD-10-CM diagnosis code (with or without the dot, e.g. E11.9) or keyword-search the official US code set (FY2026, ~98k entries). Returns a verified flag, the exact match, more-specific child codes, billable status, and short/long descriptions. CMS/NCHS public-domain data, refreshed eac...
AI agents call medical.icd10 to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only queries and returns information from a public-domain ICD-10-CM code set. It performs no writes, executes no code, deletes nothing, and moves no money. The pay-per-call settlement in USDC is a server-level billing mechanism, not a financial action performed by this specific tool. Severity is low because misuse only risks querying irrelevant codes.
From the tool's definition Verify an ICD-10-CM diagnosis code... or keyword-search the official US code set... Returns a verified flag, the exact match, more-specific child codes, billable status, and short/long descriptions.
Attacks that exploit this kind of access
Verify an ICD-10-CM diagnosis code (with or without the dot, e.g. E11.9) or keyword-search the official US code set (FY2026, ~98k entries). Returns a verified flag, the exact match, more-specific child codes, billable status, and short/long descriptions. CMS/NCHS public-domain data, refreshed each US fiscal year. Provide exactly one of code or q. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for medical.icd10: 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 Mcp. Nothing to install.
medical.icd10 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 medical.icd10 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 medical.icd10. 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.
medical.icd10 is provided by the MCP server (@2sio/mcp). 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 →