Access real-time US weather data and historical sensor trends. 
Claude 
ChatGPT 
Cursor 
Gemini 
Windsurf 
VS Code 
JetBrains 
Vercel
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Connect to your AI in seconds.
NOAA Observations — US Current Conditions provides real-time sensor data from thousands of official NWS stations across the United States.
Your AI agent uses this server to check current temperature, wind speed/direction, barometric pressure, and humidity levels at any specified station ID.
It also allows you to query recent historical trends over several hours or list all active radar station statuses (NEXRAD).
This is critical infrastructure data for monitoring US weather conditions.
What your AI can do
Get stations
Finds nearby NWS stations by using latitude/longitude coordinates in the United States.
Get latest observation
Pulls the most current weather readings (temp, wind, pressure, humidity) for a given 4-character NWS station ID.
Get observation history
Retrieves a trend report showing how specific weather metrics have changed over recent hours at an NWS station.
You input a 4-character station ID; the agent returns the latest recorded temperature, wind vector, humidity, and pressure.
The agent pulls data showing how key metrics (like temp or wind) have changed over a specified period of recent hours.
You provide latitude and longitude, and the server returns a list of nearby NWS stations that report weather data.
The agent queries and lists every active NEXRAD radar station, confirming its current operational status.
You pass a station ID to get detailed metadata, including the location and specific types of data that station reports.
Ask an AI about this
Compatible AI Apps
OAuth 2.0 Compatible Gemini Waiting for input…
NOAA Observations: 5 Tools for Weather Data Access
Use these five tools to check real-time weather observations, track historical trends, find nearby stations, and monitor radar status across the US.
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 NOAA Observations — US Current Conditions on VinkiusGet Stations
Finds nearby NWS stations by using latitude/longitude coordinates in the United States.
Get Latest Observation
Pulls the most current weather readings (temp, wind, pressure, humidity) for a given...
Get Observation History
Retrieves a trend report showing how specific weather metrics have changed over...
Get Station Metadata
Fetches detailed background information, including location and capabilities, for a...
Get Radar Stations
Lists all active NEXRAD radar stations and reports their current operational status.
Connect to your AI in seconds. 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 NOAA Observations 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 NOAA Observations — US Current Conditions, then connect any of our 5,000+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,000+ 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 NOAA. 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 5 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
Relying on manual weather data checks wastes hours of time.
Right now, checking a critical site's condition means opening NOAA’s website, finding the right station ID by coordinates, clicking through multiple pages to find the 'Current Observations,' and then manually copying down the wind speed, pressure, and temp. If you have ten sites, that's ten sets of clicks, five minutes minimum, just for a basic status report.
With NOAA Observations, your agent handles the whole process. You simply ask: 'What is the latest observation at KORD?' The server pulls the data across all those fields—temp, wind, pressure, humidity—and gives you one clean, structured answer. No clicking required.
NOAA Observations — US Current Conditions MCP Server
The hardest part of weather monitoring isn't getting the data; it's knowing which station reports what, and whether that feed is even active. You waste time cross-referencing spreadsheets to confirm if a site has radar coverage or just basic temperature readings.
This server eliminates that guesswork. Use `get_station_metadata` first. It tells you exactly what the physical sensor array at that location can report—its full data schema—before your agent even tries to read it. You get reliable context, every single time.
What your AI can actually do with this
NOAA Observations — US Current Conditions
This server gives your AI agent direct access to live sensor feeds from official National Weather Service stations across the United States. You don't gotta write boilerplate API calls; this thing handles pulling, standardizing, and presenting complex meteorological data.
Finding Your Data Point
You first need a station ID or coordinates. If you know where you are but not which station reports the weather, use get_stations. Just pass in latitude and longitude for a spot anywhere in the US, and it'll give you a list of nearby NWS stations that report data.
Once you have a potential station, you can run get_station_metadata to deep-dive into its background. You feed this tool a specific station ID, and it returns detailed info—you’ll get the location coordinates, plus exactly what kind of data that particular station reports. This tells you if it's got temperature readings, wind measurements, or something else entirely.
Checking Current Conditions
When you need to know what’s happening right now, get_latest_observation is your tool. You pass in a four-character NWS station ID, and the agent spits out the most current readings it has. This includes temperature, wind vector (speed and direction), barometric pressure, and humidity levels. It's the real-time snapshot you need.
Tracking Trends and Radar Status
Sometimes the immediate reading isn't enough; you gotta see how things are changing. Use get_observation_history to pull a trend report showing how specific metrics—like temperature or wind speed—have shifted over several recent hours at an NWS station.
For a picture of the whole network, run get_radar_stations. This lists every active NEXRAD radar station and reports its current operational status. It confirms whether the whole system is running smoothly or if there are issues with any specific unit. You can track how key metrics have changed over time, pinpoint nearby stations using coordinates, get the detailed specs for a single location, or check the real-time data from every active radar site—all in one place.
019d75de-f8dc-7297-b269-8a06f959a99b 
Here's how it actually works
The bottom line is: You ask an operational question about a specific location or trend, and we deliver the validated NWS data immediately.
First, you tell your agent which piece of data you need—for example, 'What's the wind history at KORD?'
The agent then calls the specific tool (get_observation_history) and passes the required parameters (station ID and time window).
The server executes the query against NOAA feeds and returns a structured JSON object containing the raw weather data, which your agent processes for you.
Who is this actually for?
Anyone who needs reliable weather data—not just 'tech teams'. Think meteorologists running emergency simulations, logistics managers scheduling cross-country freight, or field service engineers prepping for site visits. If your job depends on accurate, real-time environmental status reports, you need this.
Uses get_stations to find the nearest weather reporting hub before scheduling a cross-country shipment, checking for predicted wind delays.
Calls get_latest_observation immediately upon arrival at a site to verify current conditions (temp, pressure) against expected parameters.
Uses get_observation_history across multiple station IDs to plot and analyze long-term micro-climatic shifts in an area.
What Changes When You Connect
Instant status checks: Use get_latest_observation to get temperature, wind, pressure, and humidity for any station ID in one call. No more navigating multiple NOAA pages just to find the current readings.
Trend analysis without spreadsheets: Running get_observation_history lets you see how conditions changed over the last six hours—it's perfect for spotting rapid shifts or persistent patterns.
Smart location finding: Instead of guessing, use get_stations with just lat/lon. It gives you a list of actual, reporting NWS stations nearby.
Full network visibility: Check radar status across the board using get_radar_stations. You instantly know if critical NEXRAD feeds are online or down.
Deep station context: Before trusting data, run get_station_metadata on a station ID. This confirms its exact location and what specific sensor types it reports.
See it in action
Pre-trip Site Assessment
A logistics manager needs to know if the staging ground in Miami is safe for equipment transport. They ask their agent, which calls get_stations first using the coordinates. The agent identifies the closest station (e.g., KJFK), then runs get_latest_observation to confirm current wind speed and barometric pressure before approving the route.
Analyzing Storm Intensity
A meteorologist suspects a cold front moved faster than predicted. They use get_observation_history on three different stations along the path, comparing temperature drop rates over the past 4 hours to model the front's speed and strength.
Checking System Readiness
An engineer needs to confirm if all regional monitoring systems are operational. They run get_radar_stations first, immediately flagging any offline NEXRAD unit, then cross-reference that list with get_station_metadata for critical sensor gaps.
Understanding Data Scope
A developer is building a new data visualization dashboard and needs to know what fields are available at every potential source. They run get_stations to find all possibilities, then loop through those IDs calling get_station_metadata once to build the full schema.
The honest tradeoffs
Only checking current data
Thinking that just running get_latest_observation is enough. You get a snapshot, but you don't know if conditions were stable or rapidly changing.
Always pair the instant check with history. If you use get_latest_observation for KORD, immediately follow up by calling get_observation_history to see the trend over the last 6 hours. That gives context.
Using coordinates without finding stations
Asking the agent to pull data based purely on a rough set of latitude/longitude numbers, assuming NOAA has an endpoint for that.
First, call get_stations with your lat/lon. This validates nearby reporting hubs and gives you actual 4-character station IDs (like KMDW) before running any observation tools.
Assuming all stations are comparable
Getting data from a generic source without knowing if the station reports pressure, or if it's even an active radar site.
Before trusting the numbers, use get_station_metadata to confirm that the specific station ID you are targeting actually provides the sensor data you need (e.g., checking for barometric readings).
When It Fits, When It Doesn't
Use this MCP Server if your work requires reliable, verifiable atmospheric metrics tied to physical US locations. You must use it when assessing risk based on real-time environmental variables: Is wind speed spiking? Did temperature drop too fast? Is a critical radar feed offline?
Don't use it merely for general knowledge (e.g., 'What is the typical Chicago weather in summer?')—use those kinds of queries with historical databases or generalized APIs. This server is about live and recent data, not climate averages. If your goal is to map out all possible reporting points, start with get_stations. If you need a deep dive on one specific location's history, use get_observation_history after confirming the ID via get_station_metadata. Never skip metadata validation.
Questions you might have
How do I find nearby stations using NOAA Observations — US Current Conditions MCP Server? +
Use the get_stations tool, passing in the latitude and longitude coordinates. It returns a list of actual reporting NWS station IDs that you can then use for other tools.
Is NOAA Observations — US Current Conditions MCP Server better than just using Google Weather? +
Yes, because it gives raw sensor data directly from the official NWS feed. You get structured access to fields like barometric pressure and specific wind vectors that general consumer apps don't expose.
What if I want to check a station ID but don't know its details? (Using `get_station_metadata`) +
Run get_station_metadata with the ID. This provides the location and lists all available data types, letting you confirm if the station even reports humidity or radar status.
Can NOAA Observations — US Current Conditions MCP Server tell me about future weather? +
No. This server only handles real-time sensor readings and historical trends up to the present moment. For forecasting, you need a dedicated predictive model API.
Does NOAA Observations — US Current Conditions MCP Server work for locations outside the United States? +
No. The server pulls real-time sensor data exclusively from official NWS stations within the U.S. You can't use get_stations to locate international weather posts; its coverage is strictly limited to U.S. coordinates and IDs.
What should I do if I use the `get_latest_observation` tool with an invalid station ID? +
The server returns a specific error code indicating the 4-character ID is not found or active. Before running get_latest_observation, you must verify the ID first, perhaps by checking the metadata using get_station_metadata.
Are there rate limits when I query multiple historical trends with `get_observation_history`? +
Yes. Excessive calls over a short time can trigger usage restrictions. It’s best practice to batch your requests or implement a slight delay between querying get_observation_history and other tools to prevent hitting rate limits.
Does the data from `get_latest_observation` standardize units for temperature and pressure? +
Yes. The server is designed to provide dual readings, giving you both Fahrenheit/Celsius for temperature and hPa units for barometric pressure in a single output for consistency.
How often are observations updated? +
Most NWS stations report hourly (METAR), with some reporting every 5-15 minutes during significant weather (SPECI).
What are METAR and SPECI reports? +
METARs are routine hourly weather reports generated primarily at airports. SPECI reports are unscheduled updates issued when there is a significant change in weather conditions.
Can I check the status of a local weather radar? +
Yes, you can query the operational status of NEXRAD sites across the country to see if a station is active, down for maintenance, or scanning.
We've already built the connector for NOAA Observations. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 5 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.