get_spending_categories
AI agents call get_spending_categories to retrieve information from NIH Reporter MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to retrieve or enumerate spending categories within the NIH funding system—a read-only query operation. No indication it modifies, deletes, or executes external operations. The NIH Reporter API is fundamentally a research data lookup service. Confidence is slightly reduced due to absent description, but the tool name and server context strongly suggest a safe Read operation.
From the tool's definition Tool name 'get_spending_categories' and server context (NIH Reporter API for querying research data) indicate data retrieval.
Attacks that exploit this kind of access
get_spending_categories. It is categorised as a Read tool in the NIH Reporter MCP Server MCP Server, which means it retrieves data without modifying state.
Register the NIH Reporter MCP Server MCP server in PolicyLayer and add a rule for get_spending_categories: 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 NIH Reporter MCP Server. Nothing to install.
get_spending_categories 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 get_spending_categories 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 get_spending_categories. 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.
get_spending_categories is provided by the NIH Reporter MCP Server MCP server (jhalsey87/mcp_nih_reporter). 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 →