OSTI (DOE Scientific Research) MCP for AI. Search, retrieve, and manage DOE research data.

Q: How do I find datasets using OSTI (DOE Scientific Research) MCP Server?

You use the searchdataexplorerrecords tool. This searches the dedicated DOE Data Explorer, giving you metadata on raw data sets, which is separate from the published reports found via searchostirecords.

Q: Do I need to use reservedoi first? (OSTI DOE Scientific Research)

Yes. You should run reservedoi early in your workflow. This secures the unique identifier for your research before you try to finalize and submit it using the submitrecord tool.

Q: What is the difference between getostirecord and getdataexplorerrecord? (OSTI DOE Scientific Research)

The difference is the source. getostirecord pulls metadata for a published report from OSTI.GOV; getdataexplorerrecord pulls metadata for an actual, usable dataset from the Data Explorer.

Q: Does submitrecord handle both updating and registering data?

Yes, it combines both actions into one call. When you use submitrecord, the tool first updates the bibliographic information for the record and then submits or registers the associated DOI using the E-Link API. This keeps your workflow clean.

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Connect to your AI in seconds.

OSTI (DOE Scientific Research) MCP Server connects your AI client directly to the Department of Energy’s scientific research infrastructure. Use it to query millions of records from OSTI.GOV and DOE Data Explorer, search for specific datasets using filters like sponsoring organization or date range, retrieve full metadata by unique ID, and manage digital identifiers (DOIs).

It handles everything from preliminary searching to final record submission.

What your AI can do

Get data explorer record

Retrieves the full metadata for one specific dataset record within the DOE Data Explorer by its ID.

Get osti record

Fetches all bibliographic details for a single publication record from OSTI.GOV using its unique identifier.

Reserve doi

Initiates the process to reserve a Digital Object Identifier (DOI) with minimal required metadata via the E-Link API.

+ 3 more capabilities included

Search scientific publications

Find DOE research reports, conference papers, and technical documents by title, author, or keywords across OSTI.GOV.

Discover data sets

Query the DOE Data Explorer to identify specific datasets and pull their associated metadata records for analysis.

Validate record existence

Fetch complete, structured bibliographic data for any given OSTI or Data Explorer record ID.

Reserve DOIs

Submit minimal metadata to the E-Link API to reserve a unique Digital Object Identifier (DOI) for funded research before formal publication.

Update and submit records

Write or update entire record entries in the system, finalizing the process by registering the DOI via the E-Link API.

Ask an AI about this

Included with Plan

Waiting for input…

AI Agent

OSTI (DOE Scientific Research): 6 Tools for Research Data Management

These tools let your AI client interact directly with DOE databases to search records, retrieve metadata, and manage DOI assignments.

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 OSTI (DOE Scientific Research) on Vinkius

Get Data Explorer Record

Retrieves the full metadata for one specific dataset record within the DOE Data Explorer by its ID.

Get Osti Record

Fetches all bibliographic details for a single publication record from OSTI.GOV...

Reserve Doi

Initiates the process to reserve a Digital Object Identifier (DOI) with minimal...

Search Data Explorer Records

Searches and lists multiple scientific datasets available in the DOE Data Explorer...

Search Osti Records

Performs keyword-based searches across all publications listed on OSTI.GOV...

Submit Record

Submits or updates an entire scientific record and registers the corresponding DOI using the E-Link API.

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 OSTI (DOE Scientific Research) integration is available immediately — no restart needed.

Antigravity

Configure Agent Environment

Open your Antigravity agent's workspace configuration or mcp-servers.json file.

Bind the Endpoint

Add the Vinkius endpoint URL to your agent's MCP connections list:

"mcp_servers": {
  "osti-doe-scientific-research": {
    "serverUrl": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
  }
}

Provide your secure token in place of [YOUR_TOKEN_HERE] to ensure your agent requests are authenticated.

Execute

Start your Antigravity session. The agent will autonomously discover and utilize the OSTI (DOE Scientific Research) tools with full Vinkius guardrails applied.

VS Code Copilot

⚡

One-Click Install (Recommended)

In your Vinkius Dashboard, simply click the Add to VS Code button for this server. We'll automatically configure your local workspace.

Or configure manually

Open MCP Settings

Open VS Code, press Ctrl/Cmd + Shift + P, and search for GitHub Copilot: MCP Servers.

Add Server Config

Add the Vinkius endpoint configuration to your mcp-servers.json file:

"osti-doe-scientific-research": {
  "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
}

Ensure you replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.

LangChain

Install Dependencies

Install the LangChain MCP adapters for your environment:

pip install langchain-mcp-adapters

Connect the Server

Use the SSEClient in LangChain to connect to the Vinkius managed endpoint:

from langchain_mcp_adapters.client import SSEClient

# Connect to Vinkius
client = SSEClient(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
tools = client.get_tools()

CrewAI

Define the Tool

Load the Vinkius MCP tools into your CrewAI agents:

from crewai import Agent
from mcp_crewai import MCPTool

# Connect securely to Vinkius
vinkius_tools = MCPTool(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

# Assign to Agent
researcher = Agent(
    role='Data Researcher',
    tools=vinkius_tools.get_all()
)

Execute Task

Run your CrewAI process. The agent will autonomously route tasks to the Vinkius managed server.

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

Start building

Make Your AI Do More

Start with OSTI (DOE Scientific Research), 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

OSTI (DOE Scientific Research) MCP server cover

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by OSTI. 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

Your data is protected. See how we built it.

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 6 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.

Finding scientific records shouldn't mean bouncing between four different government pages.

Right now, finding a single record requires you to jump from the main OSTI portal to the search filters page, then cross-reference that ID with the dedicated DOE Data Explorer page. You copy the title, paste it into Google Scholar, and finally check its DOI status on a third-party resolver—all just to confirm one piece of data.

With this MCP server, you tell your agent: 'Find all papers on X from Y date.' The agent runs `search_osti_records` and gives you the list. If you need the related raw numbers, it uses `search_data_explorer_records`. You get structured lists of IDs and metadata, period.

OSTI (DOE Scientific Research) MCP Server: Manage research data and publications.

Before this server, registering a DOI meant filling out multiple forms on the E-Link API website—a manual process that required knowing exactly which metadata fields were mandatory for submission. It was slow, high friction work that often stalled projects.

Now, you tell your agent to 'Reserve and submit the final report.' The agent handles the sequence: it gathers necessary data, uses `reserve_doi` to secure the identifier, and then executes `submit_record`, completing the compliance loop in a single transaction. It’s just that simple.

Support 24/7 support@vinkius.com ↗

Security Vinkius Trust Center ↗

SLA Service Level Agreement ↗

Report Listing Send Report ↗

What your AI can actually do with this

You're connecting your AI agent straight into the Department of Energy’s scientific research infrastructure with this MCP Server for OSTI. It lets you query millions of records pulled from OSTI.GOV and DOE Data Explorer, handling everything from preliminary searches to final record submission.

Finding what you need starts by searching. If you're looking through general publications—think reports, conference papers, or technical documents—you use search_osti_records. This tool performs keyword-based searches across all the content listed on OSTI.GOV, giving you a list of potential records to check out.

When you’re dealing specifically with raw scientific data sets in the DOE Data Explorer, you start with search_data_explorer_records. You can narrow down those results using keywords or filters like date ranges or sponsoring organizations to find exactly what you're looking for. These searches give you a list of potential datasets.

Once you have an ID or a record from one of those search lists, you need the full details. To pull complete bibliographic data for any single publication, whether it’s OSTI content or Data Explorer material, use get_osti_record if it's an OSTI article, or run get_data_explorer_record if it's a specific dataset record within the DOE Data Explorer.

These functions fetch all the structured metadata you need to see exactly what's contained in that single record.

Managing DOIs and submitting records is where this server really shines. If your funded research needs a unique digital identifier before publication, you kick off that process by running reserve_doi. This submits minimal required metadata through the E-Link API just to reserve the Digital Object Identifier (DOI) for future use.

When it's time to finalize or update an entry in the system—whether that’s writing a brand new record or tweaking existing information—you manage that process with submit_record. This tool allows you to submit or update entire scientific records and, crucially, registers the corresponding DOI using the E-Link API. The workflow moves from discovery to validation to final submission, all within your agent's command.

Basically, you use search_osti_records for broad publication searches on OSTI.GOV; then you might run get_osti_record if you find a promising ID and need every bit of bibliographic detail attached to it. If the data set itself is your target, you start with search_data_explorer_records, followed by running get_data_explorer_record using that specific dataset's ID to pull its full metadata structure.

For formal record management, remember this sequence: use reserve_doi to secure the DOI first; then, when all the data is locked down and ready for the permanent archive, you send everything through submit_record. You’re not just searching; you're managing the entire lifecycle of scientific documentation, from initial keyword search right through to final DOI registration.

It handles every step.

Built · Hosted · Managed by Vinkius OSTI (DOE Scientific Research) MCP Server - Manage DOE Data

Server ID 019e38d1-430e-737e-9531-4e897496f740

Vinkius Inspector

Compliance Grade F

Score 43.65/100

Report View Report ↗

Here's how it actually works

The bottom line is that you treat the entire DOE research pipeline—from search query to final DOI registration—as a single conversational workflow with your AI client.

First, your agent executes a search command (e.g., search_osti_records) to narrow down the research output using defined parameters like date or author.

Next, you specify which records need deep inspection—either retrieving metadata for a specific ID (get_osti_record) or finding accompanying data sets (search_data_explorer_records).

Finally, if the record is new or needs updating, your agent uses reserve_doi and submit_record to formally register and validate the publication using the E-Link API.

Who is this actually for?

This server targets technical roles who live in academic data and compliance. It's for the Research Data Manager tired of manually cross-referencing metadata across multiple government portals, or the Academic who needs to prove a paper’s lineage and DOI status instantly.

Research Scientist

Uses search_osti_records to quickly find foundational papers related to their field and pulls detailed metadata using unique IDs.

Data Architect

Runs search_data_explorer_records to discover usable scientific datasets, then uses get_data_explorer_record to inspect the schema before modeling.

Grant Administrator

Manages publication compliance by running reserve_doi and submitting final records using submit_record when a project milestone is met.

What Changes When You Connect

You stop sifting through manual web portals. By using search_osti_records, your AI client immediately filters millions of OSTI records by precise criteria like author or date range, giving you a list of candidates in seconds.

Data discovery becomes immediate. Instead of navigating the DOE Data Explorer manually, run search_data_explorer_records. You get back structured metadata for datasets—not just links—ready to feed into your analysis pipeline.

DOI compliance is handled end-to-end. Use reserve_doi early in the lifecycle. This ensures you secure the unique digital identifier before publication, preventing delays when submitting records via submit_record.

Record inspection is precise. If you have an ID, use either get_osti_record or get_data_explorer_record. You get all the necessary bibliographic details—full text availability, authors, sponsors—in one API call.

The workflow runs autonomously. Your agent handles the sequence: search -> inspect/filter -> reserve DOI -> submit record. This eliminates the need for you to jump between six different web tabs.

See it in action

01 01

Verifying a paper's origin and status

A researcher needs details on 'Quantum Error Correction'. Instead of searching OSTI.GOV manually, they prompt: 'Find all papers on Quantum Error Correction from 2023.' The agent runs search_osti_records, identifies the top three IDs, then uses get_osti_record to retrieve full author and sponsor details for verification.

02 02

Building a dataset index

A data scientist needs all solar irradiance datasets. They run search_data_explorer_records with 'solar irradiance.' The agent gets a list of 3 IDs, then loops through them using get_data_explorer_record to collect the required metadata fields (like measurement interval and date range) into a structured output.

03 03

Completing project documentation

A grant administrator has finalized a report. They use reserve_doi with basic metadata. Once approved, they run submit_record, which finalizes the entry and ties the reserved DOI to the official record in one step.

04 04

Filtering for specific funding sources

A librarian needs reports sponsored by a specific organization (e.g., Lawrence Berkeley National Lab). They use search_osti_records, filtering directly on the sponsoring organization field, immediately reducing millions of records down to only relevant institutional output.

The honest tradeoffs

Treating it like a simple search engine

Anti-pattern

Asking the agent to 'Find all papers and give me their full text.' This fails because finding the record is not the same as accessing the file, and you need specific IDs.

The Fix

First, run search_osti_records to get a list of relevant OSTI IDs. Then, use get_osti_record with one ID at a time to confirm full-text availability before proceeding.

Manually tracking DOI status

Anti-pattern

Submitting records and then having to visit the E-Link API website later to check if the DOI was actually reserved or assigned.

The Fix

Use reserve_doi early in your workflow. This tool handles the initial reservation check, giving you immediate feedback on the status before you even attempt a final submission with submit_record.

Overloading one search query

Anti-pattern

Trying to find both datasets and publications using only vague keywords in a single prompt.

The Fix

Separate your requests. Use search_osti_records for papers (publications) and run search_data_explorer_records separately for raw data sets. Treat them as two distinct search actions.

When It Fits, When It Doesn't

Use this server if you need to manage the full lifecycle of scientific documentation—from initial discovery through final DOI registration. It's built for compliance and depth, not speed browsing.

Do use it if: You are a data scientist needing structured metadata (search_data_explorer_records), or an administrator who needs to prove record lineage (using get_osti_record followed by reserve_doi). The staged process of searching first, then inspecting IDs, and finally submitting/reserving is its strength.

Don't use it if: You just need a general web search for 'quantum physics.' That’s too broad. This tool requires specific parameters (author names, date ranges, or dataset keywords). If you only need to view data on the public OSTI website without structured API calls, this isn't necessary. Stick to search_osti_records for targeted academic hits; don't assume it will pull every single linked PDF.

It’s critical: Always check if your workflow requires a formal DOI. If so, you must incorporate reserve_doi before calling submit_record; otherwise, the submission may fail compliance checks.

Questions you might have

How do I find datasets using OSTI (DOE Scientific Research) MCP Server? +

You use the search_data_explorer_records tool. This searches the dedicated DOE Data Explorer, giving you metadata on raw data sets, which is separate from the published reports found via search_osti_records.

Do I need to use reserve_doi first? (OSTI DOE Scientific Research) +

Yes. You should run reserve_doi early in your workflow. This secures the unique identifier for your research before you try to finalize and submit it using the submit_record tool.

What is the difference between get_osti_record and get_data_explorer_record? (OSTI DOE Scientific Research) +

The difference is the source. get_osti_record pulls metadata for a published report from OSTI.GOV; get_data_explorer_record pulls metadata for an actual, usable dataset from the Data Explorer.

Can I search by date range using search_osti_records? (OSTI DOE Scientific Research) +

Yes. You can narrow your results by defining specific publication date ranges when you call search_osti_records. This is a core filtering capability.

What credentials are required when I use `reserve_doi`? +

You must provide your OSTI E-Link Token. This token authenticates your request with the DOE's API, ensuring you have the necessary permissions to reserve a Digital Object Identifier (DOI). Without this token, the server cannot process the DOI reservation.

Does `submit_record` handle both updating and registering data? +

Yes, it combines both actions into one call. When you use submit_record, the tool first updates the bibliographic information for the record and then submits or registers the associated DOI using the E-Link API. This keeps your workflow clean.

What happens if I run `get_osti_record` with an invalid ID? +

The tool returns a standardized error response indicating that no record was found for that specific OSTI ID. Your AI client can then check the API response status code to gracefully handle the missing data, rather than failing completely.

What key fields does `search_data_explorer_records` return? +

The search returns core metadata including the dataset title, source organization, relevant date ranges, and a direct link to the record. These structured data points allow your agent to immediately assess if the dataset fits your analysis needs.

How can I search for research papers by a specific author? +

You can use the search_osti_records tool and provide the author's name in the author parameter. The agent will return a list of matching records from the OSTI.GOV repository.

What is the difference between searching OSTI records and Data Explorer records? +

Use search_osti_records for general research information like publications and reports. Use search_data_explorer_records specifically when you are looking for scientific datasets.

Can I reserve a DOI for my research before it is public? +

Yes, if you have an E-Link token, you can use the reserve_doi action. You'll need to provide the title, product type, and your site ownership code.

Connect to your AI in seconds.

Get data explorer record

Get osti record

Reserve doi

OSTI (DOE Scientific Research): 6 Tools for Research Data Management

Make your AI actually useful.

Get Data Explorer Record

Get Osti Record

Reserve Doi

Search Data Explorer Records

Search Osti Records

Submit Record

Security and governance baked right in.

Claude AI

Open Claude Settings

Add Custom Connector

Start a conversation

Claude Code

Open your terminal

Add the MCP Server

Start coding

Cursor

One-Click Install (Recommended)

Open Cursor Settings

Add New Server

Use in Composer

Antigravity

Configure Agent Environment

Bind the Endpoint

Execute

VS Code Copilot

One-Click Install (Recommended)

Open MCP Settings

Add Server Config

Windsurf

One-Click Install (Recommended)

Open Windsurf Settings

Add Server Endpoint

LangChain

Install Dependencies

Connect the Server

CrewAI

Define the Tool

Execute Task

Choose How to Get Started

Build Your Own

Make Your AI Do More

Works with Claude, ChatGPT, Cursor, and more

Finding scientific records shouldn't mean bouncing between four different government pages.

OSTI (DOE Scientific Research) MCP Server: Manage research data and publications.

What your AI can actually do with this

Here's how it actually works

Who is this actually for?

What Changes When You Connect

See it in action

Verifying a paper's origin and status

Building a dataset index

Completing project documentation

Filtering for specific funding sources

The honest tradeoffs

Treating it like a simple search engine

Manually tracking DOI status

Overloading one search query

When It Fits, When It Doesn't

Questions you might have