Current US disease surveillance from the CDC (NNDSS weekly notifiable-disease counts, MMWR 2022→current). Filter by condition (substring), location (state/region/territory/national), and/or year; weeks/limit page results. Returns current-week count, prior-52-week max, and cumulative YTD per condi...
AI agents call health.disease-surveillance 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 data retrieval tool that queries publicly available CDC epidemiological data with optional filtering parameters. It has no side effects—it only fetches and returns existing surveillance statistics. No write, execute, destructive, or financial capabilities are present. The tool is read-only access to free public health information.
From the tool's definition Tool retrieves and filters CDC disease surveillance data (NNDSS weekly notifiable-disease counts). Verbs used: 'Filter', 'Returns', 'page results'. No modification, deletion, execution, or financial operations are described.
Attacks that exploit this kind of access
Current US disease surveillance from the CDC (NNDSS weekly notifiable-disease counts, MMWR 2022→current). Filter by condition (substring), location (state/region/territory/national), and/or year; weeks/limit page results. Returns current-week count, prior-52-week max, and cumulative YTD per condition+location+week. Free, keyless CDC data. At least one of condition/location required. 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 health.disease-surveillance: 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.
health.disease-surveillance 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 health.disease-surveillance 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 health.disease-surveillance. 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.
health.disease-surveillance 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 →