search_projects
AI agents call search_projects 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.
The tool appears to query a public grant database for project information. No side effects, modifications, deletions, code execution, or financial transactions are indicated. This is a straightforward data retrieval operation with minimal blast radius if misused by an AI agent.
From the tool's definition Tool name 'search_projects' combined with sibling tools focused on 'search', 'retrieve', 'get', and 'find' data from NIH RePORTER database (a read-only public grant database).
Attacks that exploit this kind of access
search_projects. 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 search_projects: 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.
search_projects 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_projects 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_projects. 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_projects is provided by the NIH RePORTER MCP Server MCP server (pradeept95/nih-reporter-mcp-server). 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 →