search_combined
AI agents call search_combined to retrieve information from NIH RePORTER MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and searches data from the NIH RePORTER database with no indication of write, destructive, execute, or financial capabilities. The context of sibling read-only tools (search_projects, search_publications, get_item, list_items) and the database's documented purpose (conversational searching) strongly indicate this is a Read operation.
From the tool's definition Tool is part of a read-only research database query system (NIH RePORTER). Sibling tools include search_projects, search_publications, and get_item—all retrieval operations.
Attacks that exploit this kind of access
search_combined. It is categorised as a Read tool in the NIH RePORTER MCP MCP Server, which means it retrieves data without modifying state.
Register the NIH RePORTER MCP server in PolicyLayer and add a rule for search_combined: 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. Nothing to install.
search_combined 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_combined 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_combined. 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_combined is provided by the NIH RePORTER MCP server (jbdamask/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 →