icf_search
AI agents call icf_search to retrieve information from ICF MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches WHO ICF codes—a static, standardized medical classification system. Search operations on reference data are inherently read-only with no capacity to create, modify, delete, or execute external operations. The absence of a tool description is offset by strong contextual evidence from the server purpose and sibling tools, all of which are clearly read-oriented reference lookups.
From the tool's definition Tool is named 'icf_search' and belongs to a server dedicated to 'lookup, search, browsing, and explanation of WHO's International Classification of Functioning, Disability and Health (ICF) codes and qualifiers.' All sibling tools (icf_browse_category,…
Attacks that exploit this kind of access
icf_search. It is categorised as a Read tool in the ICF MCP Server MCP Server, which means it retrieves data without modifying state.
Register the ICF MCP Server MCP server in PolicyLayer and add a rule for icf_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 ICF MCP Server. Nothing to install.
icf_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 icf_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 icf_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.
icf_search is provided by the ICF MCP Server MCP server (stayce/icf-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 →