Search ICD-10 codes by description keywords.
AI agents call icd10_search to retrieve information from MCP Healthcare Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves diagnostic coding information from a reference database. It has no side effects—it neither modifies data, triggers external operations, nor makes financial commitments. The operation is purely informational lookup, characteristic of Read category tools.
From the tool's definition Tool name 'icd10_search' and description 'Search ICD-10 codes by description keywords' indicate a read-only query operation.
Attacks that exploit this kind of access
Search ICD-10 codes by description keywords. It is categorised as a Read tool in the MCP Healthcare Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Healthcare Server MCP server in PolicyLayer and add a rule for icd10_search: 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 Healthcare Server. Nothing to install.
icd10_search 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 icd10_search 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 icd10_search. 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.
icd10_search is provided by the MCP Healthcare Server MCP server (shinegami-2002/mcp-healthcare-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 →