search_ams_any
AI agents call search_ams_any to retrieve information from USDA MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves or queries AMS (Agricultural Marketing Service) price data with no indication of side effects, modification, execution, or deletion. Even without explicit description, the naming pattern and server context classify this as a Read operation with low severity—harmless to query agricultural statistics and pricing information.
From the tool's definition Tool name 'search_ams_any' combined with server description indicating 'current cash grain prices from AMS Market News' suggests data retrieval.
Attacks that exploit this kind of access
search_ams_any. It is categorised as a Read tool in the USDA MCP Server MCP Server, which means it retrieves data without modifying state.
Register the USDA MCP Server MCP server in PolicyLayer and add a rule for search_ams_any: 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 USDA MCP Server. Nothing to install.
search_ams_any 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 search_ams_any 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 search_ams_any. 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.
search_ams_any is provided by the USDA MCP Server MCP server (nstclore/usda-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 →