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

Q: How do I use the NIH RePORTER (Research Funding) server with the Vercel AI SDK to find cancer research projects?

Pass the searchprojects tool to generateText with a prompt like "find projects related to cancer research." The AI SDK will stream the results directly into your UI components. You'll see project titles and funding amounts appear as the data is fetched.

Q: Can I show publications for a specific grant in real-time using NIH RePORTER (Research Funding) and the Vercel AI SDK?

Yes. Once you have a project ID from searchprojects, your agent can call searchpublications. The AI SDK will then stream the associated publications right into your app's interface, creating a fluid user experience without page reloads.

Q: What's the setup for connecting the NIH RePORTER (Research Funding) MCP Server to my Vercel AI SDK project?

It's minimal. Install the @ai-sdk/mcp package, then use createMCPClient with the server URL Vinkius provides. That gives you a client instance to access the NIH tools and pass them to your AI model.

Stream NIH funding and publication data directly into your Next.js app with the Vercel AI SDK. No more loading spinners, just live results.

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 Vercel AI SDK

Create your Vinkius account to connect NIH RePORTER (Research Funding) to Vercel AI SDK 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live-stream NIH Project Data

The `search_projects` tool lets your Vercel AI SDK-powered app find NIH grants in real time. As your agent finds matching projects, the AI SDK streams them directly into your React components. Users see results appearing one by one, not all at once after a long wait. This turns your app into a dynamic dashboard for exploring research funding. You can build a UI that feels alive, showing grant details, funding amounts, and principal investigators as they are discovered. It's a much better experience than a static list.

Find Linked Publications Instantly

Use the `search_publications` tool to fetch all papers associated with a specific NIH grant. When a user interacts with a project in your app, your agent can call this tool. The AI SDK then streams the publication data, populating the UI without a page reload. This isn't your typical data fetch. A user can click a project, and the list of related papers just appears, title by title. This MCP Server gives your React app the ability to create a deeply connected view of the NIH research ecosystem.

Build Research Frontends with the AI SDK

Combine the tools to create powerful, user-facing research applications. For instance, build a search interface where a user can look up a PI. Your agent, using the Vercel AI SDK, calls `search_projects` to find their grants, streaming them to the screen, and then immediately calls `search_publications` for each grant. Your job is to build the UI components. You pass the tools from the MCP client to `generateText`, and the AI SDK handles the streaming and rendering logic. You don't have to write complex data-fetching code to get this live-updating behavior.

Setup guide

Set up NIH RePORTER (Research Funding) MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all NIH RePORTER (Research Funding) tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent NIH RePORTER (Research Funding) transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

Pass the `search_projects` tool to `generateText` with a prompt like "find projects related to cancer research." The AI SDK will stream the results directly into your UI components. You'll see project titles and funding amounts appear as the data is fetched.

Yes. Once you have a project ID from `search_projects`, your agent can call `search_publications`. The AI SDK will then stream the associated publications right into your app's interface, creating a fluid user experience without page reloads.

It's minimal. Install the `@ai-sdk/mcp` package, then use `createMCPClient` with the server URL Vinkius provides. That gives you a client instance to access the NIH tools and pass them to your AI model.

No, Vinkius handles it. The single endpoint token you get covers authentication for the MCP Server. The AI SDK also has an `authProvider` option if you need to integrate more complex OAuth flows for your own app's users.

The NIH RePORTER data itself is public information. This server only processes your search queries, like keywords or PI names, to fetch that public data. Vinkius runs the server in an ephemeral, zero-trust sandbox, so your specific query patterns aren't stored.

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