NIH RePORTER MCP for AI. Map funding data directly to research papers.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Connect to your AI in seconds.
NIH RePORTER provides direct access to the NIH Research Portfolio database. Use this server to search for specific research projects by PI name or fiscal year, retrieve funding amounts, and find associated scientific publications using core project numbers.
It's a single point of entry for mapping federal biomedical grants to published science.
What your AI can do
Search projects
Find NIH grants, listing associated PIs, organizations, and current funding amounts based on criteria you specify.
Search publications
Search for scientific articles and publications that are linked back to a specific core project number or application ID.
Use search_projects to find grant records based on PI names, organization names, fiscal years, or project numbers.
Run search_publications to list scientific articles associated with a specific NIH core project number or application ID.
Search for projects and filter the results by specific funding amounts, required agencies (like NIAID), or award ranges.
Query the database using fiscal years to map out research activity across time periods.
Run targeted searches using keywords (e.g., 'COVID-19' or 'Immune Regulation') to narrow down project results.
Ask an AI about this
Waiting for input…
NIH RePORTER MCP Server: 2 Tools for Biomedical Data
Use these two tools to search grant records, filter funding amounts, and link specific publications back to their original NIH project source.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using NIH RePORTER (Research Funding) on VinkiusSearch Projects
Find NIH grants, listing associated PIs, organizations, and current funding amounts based on criteria you specify.
Search Publications
Search for scientific articles and publications that are linked back to a specific...
Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
Claude AI
Open Claude Settings
Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
Add Custom Connector
Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:
https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp
Replace [YOUR_TOKEN_HERE] with your token
from cloud.vinkius.com. For OAuth-protected servers, expand
Advanced settings to add credentials.
Start a conversation
Open a new chat. The NIH RePORTER integration is available immediately — no restart needed.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with NIH RePORTER (Research Funding), then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,100+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
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.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This connection provides 2 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
Tracking grant history means jumping between three different databases.
Right now, if you want to know how much funding a PI received and what papers resulted from it, you're forced into a manual nightmare. You check the NIH site for grants using one name, then copy an ID, go to PubMed, and run another search just to see the publications. Every step requires context switching and is prone to human error.
With this MCP server, your agent handles the whole sequence. You ask it: 'Show me all papers from X PI.' The agent uses `search_projects` first to find the grants, then uses those IDs in `search_publications` automatically. It gives you one unified data feed.
NIH RePORTER MCP Server: Use `search_projects` and `search_publications` for clean data.
The most time-consuming part is the cross-referencing. You get a list of grants, but you have to manually check if those projects even resulted in papers. This kills momentum and makes analysis slow.
Now, your agent connects the two points automatically. It finds the grant using `search_projects` and immediately returns all associated publications via `search_publications`. The whole data pipeline is clean and immediate.
What your AI can actually do with this
You use search_projects to find NIH grants by specifying criteria like principal investigator names, organization IDs, fiscal years, or core project numbers. The tool pulls grant records and lets you filter results based on specific funding amounts or defined award ranges across multiple agencies; for instance, you can target projects funded specifically by NIAID.
You search for research activity over time by querying the database using precise fiscal year inputs. Furthermore, if you're hunting down a particular scientific topic—say, 'Immune Regulation' or 'COVID-19'—you run targeted searches using those keywords to narrow your project results. When you need to track related articles, you use search_publications to list scientific papers associated with an NIH core project number or application ID.
The server provides a single entry point for mapping federal biomedical grants directly to published science. Your agent sends the necessary criteria—like specifying both a PI name and a required fiscal year—and the server executes the complex query against the NIH RePORTER database, returning structured JSON data containing all associated grant details.
The output includes comprehensive records showing which organizations received funding, how much money was awarded, and exactly when that research was funded.
The process starts with search_projects, where you can pinpoint grants by organization name or project number to get a clear picture of the current funding landscape. If you're doing a historical review, querying by fiscal year lets your agent map out how much money flowed into certain fields over decades.
You don’t have to guess; you just tell it what you need—whether that's an award range or a specific program like NIGMS—and the server filters the results immediately.
Once you have a core project number from those initial searches, search_publications steps in. This tool directly links the funding work to the scientific output. You run it using either the unique NIH core project number or the original application ID to list every associated published article. Your AI client processes this structured data, giving you clean lists of publications tied back to the grant's source funding.
The entire system acts as a powerful cross-reference: you find the money through search_projects, and then you use that result to verify the science via search_publications. You get a clear chain of evidence showing who funded what, and which articles reported on it.
The server handles complex data querying across project discovery, funding analysis, and publication tracking. It’s built so your agent sends simple instructions—like 'Find all grants for Smith in 2018' or 'List papers for project XYZ-123'—and the system returns clean, actionable JSON results ready for you to analyze without wrestling with complex API calls.
You get precise funding amounts and associated principal investigators every time. This is one of those tools that lets your agent pull together a complete picture: from the initial grant application, through the awarded funds, right up to the published scientific conclusion.
019e38c8-9752-71b4-949a-a77300922694 
Here's how it actually works
The bottom line is: you use your agent to talk to the government database without needing an API key or writing complex query language yourself.
Tell your agent exactly what you need: specify the search parameters, like a PI's name and a fiscal year.
The system calls the appropriate tool (search_projects or search_publications), sending the criteria to the NIH RePORTER API endpoint.
You get back structured data listing relevant grants, funding amounts, and associated publication metadata.
Who is this actually for?
This tool is critical for academic researchers, biostatisticians, and grant writers. If your job involves linking published science back to its original federal funding source, this saves you days of manual database hopping.
Find related work or publication history for a specific lab's grants using search_projects and then linking them to papers with search_publications.
Aggregate funding trends across multiple agencies (e.g., comparing NIGMS vs. NIAID) by running filtered searches on project data for bibliometric analysis.
Research successful grant models and funding patterns within specific institutions or fields to build a stronger proposal narrative.
What Changes When You Connect
Track the money trail: Use search_projects to retrieve specific award amounts and filter grants by agency or dollar range, giving you a quantitative view of academic investment.
Connect science to dollars: Run search_publications using an NIH core project number. You instantly see all linked scientific papers without leaving the workflow.
Deep dive on PIs and Labs: Use search_projects to list grants by Principal Investigator or organization name, letting you map out a researcher's full funding history.
Target specific research areas: Filter projects using keywords (e.g., COVID-19) combined with fiscal year ranges to focus only on relevant biomedical work.
Save time building bibliometrics: By combining search_projects and filtering by dates, you quickly aggregate data for policy analysis or grant reporting.
See it in action
Tracking a PI's full funding scope
A bioinformatician needs to see every grant associated with 'Dr. Jones.' Instead of checking three separate NIH portals, the agent runs search_projects filtered by Dr. Jones' name and organization. It gets a list of all applications and their funding details, providing an immediate overview of the lab’s scope.
Validating project output
A researcher finds a promising grant ID (R01AI123456) but needs to know what was published. They run search_publications with that specific ID. The agent returns 12 article titles and PubMed IDs, confirming the research's real-world output.
Analyzing funding spikes
A policy analyst wants to see how much federal money flowed into 'Immune Regulation' in the last five years. They use search_projects with text searches and date ranges, allowing them to aggregate total award amounts from multiple agencies for a trend analysis.
Building grant history reports
A grant administrator needs to find all active grants at 'Harvard University' that exceeded $1 million in the current fiscal year. They use search_projects with both organizational matching and an award amount filter, getting a precise list for reporting.
The honest tradeoffs
Searching by keyword only
Just typing 'COVID-19 research' into the general search bar. This returns too many results and lacks structure, making it hard to filter by funding or date.
Use search_projects and specify both keywords AND a fiscal year range, like 'Keyword: COVID-19' AND 'Year: 2020-2022'. This keeps the search focused on verifiable grant records.
Ignoring project IDs
Finding a paper title via Google Scholar and assuming it relates to a specific funding source. You have no way of knowing if the NIH funded that work.
Find the PubMed ID, then use search_publications with that ID. This confirms which official NIH core project number was responsible for the publication.
Manual cross-referencing
Exporting a list of PIs from one database and manually checking them against another funding tracker to build a complete picture.
Use search_projects with PI names and organization filters. This aggregates all related records into one structured output, saving hours of copy-pasting.
When It Fits, When It Doesn't
Use this server if your research requires mapping federal funding dollars to specific projects or published literature. You need the hard data: award amounts, fiscal year boundaries, and verifiable API links (like core project numbers).
Don't use it if you just need general background knowledge on a topic—use standard search engines for that. Also, don't rely on it for qualitative details, like specific lab equipment models or non-NIH affiliated grants; the data is limited to NIH sources.
If your primary goal is finding funding amounts and filtering by agency, run search_projects. If your goal is tracing a paper back to its source of money, use search_publications after getting the project ID.
Questions you might have
How do I use search_projects to find grants by PI name? +
You pass the Principal Investigator's full name as a parameter. The tool filters all available grant records, returning funding details and associated projects for that individual.
Can I use search_publications with just a PubMed ID? +
No, search_publications primarily links publications to core project numbers or application IDs. While you can find the paper title using a PMID elsewhere, this tool needs the official NIH identifier.
Does NIH RePORTER MCP Server cover all biomedical grants? +
No, it covers data from the NIH's own databases (RePORTER). It won't include funding from private foundations or non-U.S. government sources.
How do I find funding amounts greater than $1M? +
You use search_projects and specify the minimum award amount in your criteria. The tool filters out all grants below that threshold, keeping your results focused on large-scale efforts.
Does using `search_projects` require a private API key for basic searching? +
No, standard access doesn't need a dedicated private key. You simply connect your agent to the Vinkius endpoint. The underlying NIH RePORTER service handles public data authentication automatically for initial queries.
What happens if `search_publications` returns zero results for an ID? +
Zero results mean that specific publication link isn't in the RePORTER index. The tool will return an empty list and clearly state no records were found. This usually indicates the data hasn't been formally linked to NIH yet.
Are there rate limits when running many queries through `search_projects`? +
Yes, public API usage has inherent throttling limits. The MCP server manages standard request rates. For large-scale data science jobs, you must implement exponential backoff in your agent's execution logic.
Can I use `search_projects` or `search_publications` to get the data into a structured format like CSV? +
The tools output standard JSON data. They don't export files directly, but your AI client can parse the resulting JSON structure instantly. You can then pipe that data straight into libraries like Pandas for spreadsheet use.
How can I find all NIH grants awarded to a specific university? +
Use the search_projects tool and provide the university name in the org_names array. You can also refine the search by adding fiscal_years to see awards for a specific period.
Can I see which publications resulted from a specific NIH project number? +
Yes! Use the search_publications tool and enter the project identifier in the core_project_nums field. The agent will return a list of associated PubMed records.
Is it possible to filter research projects by funding amount? +
Absolutely. The search_projects tool includes an award_amount_range parameter where you can specify min_amount and max_amount to find projects within your budget criteria.
We've already built the connector for NIH RePORTER. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 2 tools are live and waiting.
You're up and running in seconds.
Gemini Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.
Built, hosted, and secured by Vinkius. You just connect and go.