How to Use the NIH RePORTER (Research Funding) MCP in Mastra AI

Q: How can I build a Mastra AI agent to monitor new grants from the NIH RePORTER (Research Funding) server?

Create a Mastra AI workflow that periodically calls the searchprojects tool with your target keywords and a recent date range. Mastra's engine handles scheduling and retries, ensuring your agent reliably checks for new funding opportunities.

Q: How do I add the NIH RePORTER (Research Funding) tools to my Mastra AI agent?

Install the @mastra/mcp package and instantiate the MCPClient with the server URL from Vinkius. From there, you can call mcpClient.listTools() and spread the resulting tool definitions directly into your agent's configuration.

Build reliable data pipelines for NIH funding analysis with Mastra AI. Automate research monitoring with built-in retries and error handling.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NIH RePORTER (Research Funding) MCP to Mastra AI

Create your Vinkius account to connect NIH RePORTER (Research Funding) to Mastra AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup NIH RePORTER (Research Funding) with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Funding Opportunity Alerts

The `search_projects` tool is for more than just one-off searches. With Mastra AI, you can build a workflow that runs it on a schedule, checking for new grants in your field of interest. Mastra's engine ensures the query runs reliably every time. If the tool finds new projects, your workflow can branch. It can then use `search_publications` to check the PI's recent output and decide whether to send a high-priority alert. You define the logic; Mastra executes it without fail.

Create Resilient Research Workflows

Use the `search_projects` and `search_publications` tools inside a Mastra AI workflow. The NIH API can be slow or have rate limits. Mastra's automatic retries with exponential backoff mean you don't have to write your own error-handling logic for these calls. Your workflow can be simple: "Try to `search_projects`. If it fails, wait and retry 3 times. If it still fails, log the error and notify an admin." This makes your data gathering process from this MCP server robust enough for production systems.

Build Conditional Workflows with Mastra AI

Mastra's strength is building data-driven logic. You can create a workflow that first runs `search_projects` on a specific research topic. Then, based on the results, it can make a decision. For example, if the total funding found is over $5M, trigger a deeper analysis using `search_publications`. If not, just log the total and end the workflow. This MCP server gives your Mastra agent the exact data it needs to execute these kinds of conditional tasks.

Setup guide

Set up NIH RePORTER (Research Funding) MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All NIH RePORTER (Research Funding) tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "nih-reporter-research-funding-mcp-client",
  servers: {
    "nih-reporter-research-funding-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "NIH RePORTER (Research Funding) Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to NIH RePORTER (Research Funding) tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent NIH RePORTER (Research Funding) transactions"
);
console.log(result.text);

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by NIH RePORTER. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect NIH RePORTER (Research Funding) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about NIH RePORTER (Research Funding) MCP in Mastra AI

Create a Mastra AI workflow that periodically calls the `search_projects` tool with your target keywords and a recent date range. Mastra's engine handles scheduling and retries, ensuring your agent reliably checks for new funding opportunities.

Yes, that's exactly what Mastra is for. Its workflow engine has built-in support for automatic retries with exponential backoff. You don't need to write custom code to handle transient network errors when calling `search_projects` or `search_publications`.

Install the `@mastra/mcp` package and instantiate the `MCPClient` with the server URL from Vinkius. From there, you can call `mcpClient.listTools()` and spread the resulting tool definitions directly into your agent's configuration.

You control which tools are used within your agent's logic. Even if the agent has access to both `search_projects` and `search_publications`, it will only invoke the ones you explicitly tell it to use in its workflow steps.

The data you're querying is public NIH research information. Your specific search queries and workflow logic are processed within the Vinkius zero-trust environment. Each request runs in a sandboxed, ephemeral V8 Isolate, ensuring your process is isolated and its state isn't persisted after execution.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript