AI agents call medical.taxonomy-specialty 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 is a straightforward lookup/reference tool that maps standardized medical taxonomy codes to human-readable classifications. It performs read-only operations on medical reference data without side effects, data modification, or external command execution.
From the tool's definition Tool decodes/translates a NUCC provider-taxonomy code into structured information (grouping, classification, specialization, display name).
Attacks that exploit this kind of access
Decode a NUCC provider-taxonomy code → grouping, classification, specialization, and display name. 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.taxonomy-specialty: 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.taxonomy-specialty 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.taxonomy-specialty 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.taxonomy-specialty. 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.taxonomy-specialty 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 →