Search US federal biomedical research grants via NIH RePORTER. Filter by term (title/terms/abstract), org, pi, and/or fiscalYear. Returns awards with project number, title, fiscal year, award amount, PI, organization, funding agency, and dates — newest first, with a total count. Free, public-domain.
AI agents call research.funding 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 purely a query/search tool that retrieves publicly available biomedical grant information from a US federal database. No data is modified, deleted, created, or irreversibly altered. No code is executed, and no financial transactions occur (the grants themselves are historical public records being queried). The tool has no side effects beyond returning matching records.
From the tool's definition Tool searches and retrieves data from a public database (NIH RePORTER): 'Search US federal biomedical research grants via NIH RePORTER. Filter by term (title/terms/abstract), org, pi, and/or fiscalYear.
Attacks that exploit this kind of access
Search US federal biomedical research grants via NIH RePORTER. Filter by term (title/terms/abstract), org, pi, and/or fiscalYear. Returns awards with project number, title, fiscal year, award amount, PI, organization, funding agency, and dates — newest first, with a total count. Free, public-domain. 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 research.funding: 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.
research.funding 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 research.funding 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 research.funding. 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.
research.funding 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 →