NRS-2002 MCP for AI. Standardize Nutritional Risk Screening Results
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Connect to your AI in seconds.
Nutritional Risk Screening (NRS-2002) assesses a patient's risk of malnutrition using established clinical protocols. It evaluates BMI, weight changes, food intake issues, and disease severity to give a standardized score and specific care recommendations.
Run the complete assessment in minutes.
What your AI can do
Evaluate disease impact
Calculates the disease impact score (S component) for the NRS-2002 assessment.
Evaluate nutritional status
Calculates the nutritional status score (N component) of the NRS-2002 protocol.
Perform full nrs screening
Runs a complete, end-to-end nutritional risk screening using the NRS-2002 guidelines.
Determines the patient's nutritional level based on intake and physical metrics.
Quantifies how much a patient’s existing illness is negatively affecting their body.
Performs the complete, multi-component NRS-2002 assessment in one go.
Ask an AI about this
Waiting for input…
Nutritional Risk Screening (NRS-2002) - 3 Tools
These tools allow you to calculate specific components of the NRS-2002 assessment—from nutritional status to disease impact—or run a full, single-step risk screening.
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 Nutritional Risk Screening (NRS-2002) on VinkiusEvaluate Disease Impact
Calculates the disease impact score (S component) for the NRS-2002 assessment.
Evaluate Nutritional Status
Calculates the nutritional status score (N component) of the NRS-2002 protocol.
Perform Full Nrs Screening
Runs a complete, end-to-end nutritional risk screening using the NRS-2002 guidelines.
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 NRS-2002 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 Nutritional Risk Screening (NRS-2002), 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 Nutritional Risk Screening. 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 3 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
Manually calculating nutritional risk scores takes time and invites error.
Right now, assessing a patient's nutrition often means gathering data from four different areas: their weight change history, what they ate yesterday, their BMI numbers, and the severity of their main illness. You then have to manually plug all that into complex protocols just to get one total risk score. It’s tedious work.
With this MCP, you feed those inputs once. The system handles the calculation for every component—the nutritional status, the disease impact, everything. You get a final, validated NRS-2002 total risk score and immediate recommendations without lifting a finger.
Getting Specific Component Scores with `evaluate_nutritional_status`
Instead of just getting the final number, you can isolate what’s driving the risk. You run `evaluate_nutritional_status` to specifically check if poor food intake is the main problem, or if it's the impact of their illness.
This separation is key because sometimes a patient's nutrition is bad, but that bad nutrition is *caused* by their disease. Pinpointing which component is the primary driver changes the treatment plan.
What your AI can actually do with this
Hospitalized patients need regular checks for nutritional decline, but figuring out their exact status can involve checking several different metrics—BMI, recent weight loss, current diet, and how much a primary illness is affecting them. This MCP handles that whole process. It runs on the validated NRS-2002 protocol to give clinicians a clear score and actionable advice based on ESPEN guidelines.
Instead of juggling multiple data points across various forms, you feed the patient’s core metrics into this connector. The system calculates the specific component scores—like nutritional status or disease impact—and then combines them for one total risk assessment. When you connect to Vinkius, you get access to this tool right alongside thousands of others, making it a central resource for clinical assessments.
019eedb8-fc26-710e-9d83-4b91e307e7e3 
Here's how it actually works
The bottom line is, you get an immediate, standardized clinical risk assessment that tells you exactly where the patient stands nutritionally.
Provide the patient's current data: Body Mass Index (BMI), recent weight changes, reported food intake, and the primary disease severity.
The MCP processes this input by calculating the separate nutritional status score and the disease impact score according to clinical rules.
You receive a final NRS-2002 total risk score, classifying the patient’s level of malnutrition risk and suggesting necessary support.
Who is this actually for?
Dietitians and hospital nurses who are tired of manually calculating scores across different charts. It’s for clinicians needing a quick, reliable nutritional baseline at admission or during discharge planning.
Uses the full screening to determine if the patient requires immediate enteral or parenteral feeding support.
Checks nutritional status quickly during daily rounds to flag any sudden decline in intake or weight.
Reviews the scores at discharge to ensure follow-up care addresses chronic malnutrition risk.
What Changes When You Connect
Gets a complete picture in one go. Instead of running multiple checks, you use perform_full_nrs_screening to get the total risk score and recommendations instantly.
Pinpoints specific weaknesses. Need more detail? You can isolate components using evaluate_nutritional_status or evaluate_disease_impact for deeper analysis.
Reduces charting errors. It handles complex scoring logic, so you don't have to worry about calculating the S or N component manually every time.
Provides clinical action points. The output isn't just a number; it suggests specific nutritional support interventions based on established guidelines.
Saves time at admission. You can quickly assess a new patient’s status using this MCP, speeding up care planning and resource allocation.
See it in action
Admission Screening for Surgery
A surgeon needs to know if the patient is nutritionally stable before elective surgery. They run perform_full_nrs_screening with the patient's current metrics and immediately classify the risk level, allowing them to pre-schedule nutritional consults.
Monitoring Post-Discharge Care
A primary care physician needs a follow-up assessment. They use evaluate_nutritional_status with recent weight loss data to track whether the patient’s diet is meeting their metabolic needs at home.
Assessing Acute Illness Impact
A nurse notices a sudden change in symptoms due to a new infection. They use evaluate_disease_impact to quantify how much this acute illness is lowering the patient's baseline health, helping the doctor adjust medication.
The honest tradeoffs
Treating scores as absolute facts
A clinician sees a low score from evaluate_nutritional_status and assumes the patient is fine, ignoring other signs of distress.
Use this MCP to get the baseline score, but always cross-reference that data with physical exam notes and recent history. The scores guide differential diagnosis, they aren't the final word.
Ignoring specific components
Only running perform_full_nrs_screening and then dismissing results because they don't match the initial gut feeling.
Break down the total score by checking individual parts. Use evaluate_nutritional_status to confirm intake metrics, then use evaluate_disease_impact to check the illness effect.
When It Fits, When It Doesn't
Use this MCP when you need a standardized, protocol-driven assessment of malnutrition risk using established clinical models like NRS-2002. This is perfect for admission screens or monitoring measurable changes in BMI and intake.
Don't use it if the patient’s primary issue is non-measurable (e.g., severe mental health crisis, chronic substance abuse). In those cases, you need a clinical assessment that goes beyond standard biological metrics—you’ll need tools designed for behavioral or psychological scoring instead.
Questions you might have
What is the purpose of this tool? +
It identifies patients at risk of malnutrition during hospital stays by calculating a score based on nutritional status and disease severity.
How is the risk determined? +
The tool aggregates points from BMI, weight loss, food intake, and metabolic stress. A total score of 3 or higher indicates nutritional risk.
Does it follow any specific guidelines? +
Yes, the clinical recommendations provided are based on the European Society for Clinical Nutrition and Metabolism (ESPEN) guidelines.
What specific data inputs are required when I call `perform_full_nrs_screening`? +
You must provide four core patient metrics: Body Mass Index (BMI), recent weight loss percentage, food intake status, and disease severity level. The system uses these four points to calculate the overall risk score.
Can I use `evaluate_nutritional_status` or `evaluate_disease_impact` alone? +
Yes, you can run component scores separately if needed. Using evaluate_nutritional_status gives the N component score, while using evaluate_disease_impact provides only the S component score.
What happens if I miss a required data point when running the screening? +
If you omit critical inputs like BMI or weight loss from the call, the MCP will return an error. You'll need to ensure all necessary fields are populated before attempting any assessment.
Is this MCP efficient for batch processing multiple patients? +
The tool is designed for single-patient assessments. However, your AI client can iterate through a list of patient records and call perform_full_nrs_screening sequentially to process batches.
Does the output from this MCP integrate with standard electronic health record (EHR) systems? +
The tool outputs a clear, structured score along with actionable recommendations. This data is easy for your agent to parse and map directly into existing patient records.
We've already built the connector for NRS-2002. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 3 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.