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

Q: How do I load NIH RePORTER (Research Funding) into AutoGen?

Use mcpservertools with StreamableHttpServerParams pointing to the server URL. Pass the resulting tool list directly into your AssistantAgent setup.

Give your AutoGen agents the ability to debate federal funding trends using live NIH data.

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 AutoGen

Create your Vinkius account to connect NIH RePORTER (Research Funding) to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Fuel multi-agent debates with real data

The `search_projects` tool feeds live NIH grant amounts, PI names, and organizational data straight into your agent chats. One agent pulls the financial data, and another critiques the funding allocation. This ends the cycle of agents arguing over assumptions. You give them a factual baseline. A financial agent can push for cost efficiency while a science agent defends the budget, both referencing the exact same federal record.

Audit scientific output via MCP Server

The `search_publications` tool lets your agents verify if a multi-million dollar grant actually produced results. An agent inputs the project ID and retrieves the list of published papers. The agents then negotiate the impact. A skeptic agent might point out a lack of recent papers, forcing the research agent to dig deeper into the timeline. They reach a consensus based on hard evidence.

Automate complex funding analysis

You build systems where the answer requires deliberation. An agent queries the NIH database for emerging tech grants, and a secondary agent cross-references those findings against known market gaps. You just pass the tools to the AssistantAgent constructor. The adapter handles the schema conversion automatically, letting the agents focus on analyzing the data instead of formatting API requests.

Setup guide

Set up NIH RePORTER (Research Funding) MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes NIH RePORTER (Research Funding) tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="NIH RePORTER (Research Funding)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent NIH RePORTER (Research Funding) data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="NIH RePORTER (Research Funding)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent NIH RePORTER (Research Funding) data")
    print(result.messages[-1].content)

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 AutoGen

Use mcp_server_tools with StreamableHttpServerParams pointing to the server URL. Pass the resulting tool list directly into your AssistantAgent setup.

Yes. You can equip a Data Gatherer agent with the tools to fetch the grants, while a Reviewer agent analyzes the output without needing direct access to the server.

They figure it out through conversation. An agent will pull a grant, realize it needs the publication history to evaluate success, and call the second tool based on the first tool's output.

It supports both stdio and Streamable HTTP transports. For Vinkius, you will use the HTTP endpoint to connect your local agents to the managed server.

The tools process public federal funding amounts and publication metadata. Vinkius executes the tool calls in an isolated, stateless environment, ensuring your agent's specific search parameters are destroyed the second the data returns.

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