Sold by: Waltsoft Inc.
Deployed on AWS
Quick Launch
DataPulse is a weather forecast API for AI agents and developers: one GET call returns NOAA HRRR 3km surface forecast data (temperature, wind, precipitation, cloud cover) for any contiguous US coordinate, up to 18 hours ahead. Use it over REST, MCP or A2A.
Overview
What DataPulse does
DataPulse turns a CONUS latitude/longitude into a structured weather forecast that an AI agent or a weather application can use directly.
- GET /v1/forecast?lat=30.2216&lon=-97.6206&hours=6 returns temperature at 2m (degC), dew point at 2m (degC), wind speed at 10m (m/s) and direction (degrees), precipitation in the forecast hour (mm) and total cloud cover (%) for the requested hour, plus the HRRR run, the 3km grid cell used and the data credit.
- Coverage: contiguous United States inside the HRRR grid (latitude 21-50, longitude -135 to -55). Hawaii and Alaska are not covered.
- Forecast horizon: 1 to 18 hours ahead of the current UTC hour. HRRR runs hourly; DataPulse reads the newest run available, about 2-3 hours behind.
Where the data comes from
NOAA HRRR (High-Resolution Rapid Refresh), NOAA's 3km hourly forecast model for the contiguous United States. DataPulse reads each forecast point directly from the University of Utah HRRR Zarr archive (s3://hrrrzarr), listed with NOAA HRRR on the Registry of Open Data on AWS, and rotates the model's grid-relative winds to true north. Every response names the HRRR run and grid cell it used. If the archive cannot be read the API answers 503 and the call is not billed.
- NOAA High-Resolution Rapid Refresh (HRRR) via the University of Utah HRRR Zarr archive on the Registry of Open Data on AWS. Not endorsed by NOAA.
Three ways to connect
- REST with an X-API-Key header, described by an OpenAPI 3 schema (https://datapulse.waltsoft.net/openapi.json ).
- MCP: the tool datapulse___getWeatherForecast on the Amazon Bedrock AgentCore Gateway, for Claude, Strands Agents and other MCP clients.
- A2A (Agent2Agent 0.3): the agent card at https://datapulse.waltsoft.net/.well-known/agent-card.json with the skill getWeatherForecast.
Who it is for
AI agents that need current weather conditions for routing, scheduling, or situational awareness; logistics and supply-chain pipelines; energy and solar-potential planning tools; and developers who need structured NOAA HRRR point data without handling model files.
Billing
On AWS Marketplace every successful call is one unit at $0.60, whatever the hours value, on your AWS bill. Errors (400, 401, 429) and source outages (503) are never billed. Rate limit: 100 requests per second, bursts up to 200.
Highlights
- NOAA HRRR 3km forecasts: temperature, dew point, wind speed and direction, precipitation and cloud cover for any CONUS coordinate, up to 18 hours ahead
- Fail-closed and attributed: every answer names the HRRR run and grid cell used and carries the NOAA credit; if the HRRR archive cannot be read the API returns 503 and the call is never billed
- Agent-ready: REST with an OpenAPI 3 schema, an MCP tool on Amazon Bedrock AgentCore Gateway and an A2A agent card; pay only for successful calls on your AWS bill
Details
Sold by
Categories
Delivery method
Integration protocol
Supported services
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Quick Launch
Leverage AWS CloudFormation templates to reduce the time and resources required to configure, deploy, and launch your software.
Pricing
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/unit |
|---|---|---|
API Call | Single API call to the service | $0.60 |
Vendor refund policy
No refunds for API calls already made. Contact support@waltsoft.net within 7 days of billing issues.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Supported services:
- Amazon Bedrock AgentCore
API-Based Agents & Tools
API-Based Agents and Tools integrate through standard web protocols. Your applications can make API calls to access agent capabilities and receive responses.
Additional details
Usage instructions
To get started using the remote MCP server, follow the instructions below:
Available Tools This MCP server (Amazon Bedrock AgentCore Gateway) supports the following tool:
- datapulse___getWeatherForecast - NOAA HRRR 3km weather forecast for a CONUS coordinate. Arguments: lat (decimal degrees), lon (decimal degrees), hours (1-18, default 1), api_key
Prerequisites
- An active subscription to this product. Your API key (it starts with mp_) is stored in your AWS Secrets Manager after you choose Set up your account, and is also shown on the registration page.
- Install Node.js and npm (for mcp-remote), or Python 3.10+ (for the Strands Agents SDK).
Authentication The MCP endpoint needs no connection header. Pass your key as the api_key argument of every tool call; replace YOUR_API_KEY with your actual key below. A wrong or inactive key returns statusCode 401.
MCP endpoint: https://waltsoft-marketplace-gateway-xncyjgs1uh.gateway.bedrock-agentcore.us-east-1.amazonaws.com/mcp
Claude Desktop Edit the configuration file at:
- macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
- Windows: %APPDATA%\Claude\claude_desktop_config.json
Add the below code:
{ "mcpServers": { "waltsoft-datapulse": { "command": "npx", "args": [ "mcp-remote", "https://waltsoft-marketplace-gateway-xncyjgs1uh.gateway.bedrock-agentcore.us-east-1.amazonaws.com/mcp" ] } } }Then ask, for example: "Use datapulse___getWeatherForecast with lat 30.2216, lon -97.6206, hours 6, and api_key YOUR_API_KEY".
Strands Agents (Python)
pip install strands-agents mcp from mcp.client.streamable_http import streamable_http_client from strands.tools.mcp import MCPClient URL = "https://waltsoft-marketplace-gateway-xncyjgs1uh.gateway.bedrock-agentcore.us-east-1.amazonaws.com/mcp" with MCPClient(lambda: streamable_http_client(URL)) as mcp: result = mcp.call_tool_sync("call-1", "datapulse___getWeatherForecast", {"lat": 30.2216, "lon": -97.6206, "hours": 6, "api_key": "YOUR_API_KEY"}) print(result["content"][0]["text"])Example tool result
{"statusCode": 200, "result": {"coordinate": {"lat": 30.2216, "lon": -97.6206}, "forecast_hour": 6, "valid_time": "2026-10-22T21:00:00Z", "run": {"date": "20261022", "hour": 13, "forecast_hour": 8}, "grid": {"row": 221, "col": 895, "lat": 30.216, "lon": -97.629}, "source": "NOAA HRRR 3km CONUS (University of Utah HRRR Zarr archive, s3://hrrrzarr)", "attribution": "NOAA High-Resolution Rapid Refresh (HRRR) via the University of Utah HRRR Zarr archive on the Registry of Open Data on AWS. Not endorsed by NOAA.", "variables": {"tmp_2m": {"value": 28.7, "unit": "°C"}, "wind": {"speed_ms": 2.8, "direction_deg": 58}, "tcdc": {"value": 3, "unit": "%"}}}}Billing Each successful tool call is one AWS Marketplace unit ($0.60); errors are not billed.
Data source NOAA High-Resolution Rapid Refresh (HRRR) via the University of Utah HRRR Zarr archive on the Registry of Open Data on AWS. Not endorsed by NOAA.
Rate Limits
- 100 requests per second (bursts up to 200).
- Exceeding returns HTTP 429 Too Many Requests.
- Use retry and exponential backoff to handle limits.
Learn More API Docs: https://datapulse.waltsoft.net Support: support@waltsoft.net
Support
Vendor support
Contact support@waltsoft.net . Documentation:
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
The HYSPLIT model is a complete system for computing simple air parcel trajectories, as well as complex transport, dispersion, chemical transformation, and deposition simulations. HYSPLIT continues to be one of the most extensively used atmospheric transport and dispersion models in the atmospheric sciences community. A common application is a back trajectory analysis to determine the origin of air masses and establish source-receptor relationships. HYSPLIT has also been used in a variety of simulations describing the atmospheric transport, dispersion, and deposition of pollutants and hazardous materials. Some examples of the applications include tracking and forecasting the release of radioactive material, wildfire smoke, windblown dust, pollutants from various stationary and mobile emission sources, allergens and volcanic ash.
The National Weather Service's National Centers for Environmental Prediction (NCEP) runs a series of computer analyses and forecasts operationally. NOAA's[...]
FloodPulse is a natural-hazard risk API for US addresses: one call returns the FEMA flood zone and 30-year flood odds, terrain, county extreme-heat history and FEMA National Risk Index wildfire, heat and storm ratings. Use it over REST, MCP or A2A.
The WSA-Enlil heliospheric model provides critical information regarding the propagation of solar Coronal Mass Ejections (CMEs) and transient structures within the heliosphere. Two distinct models comprise the WSA-Enlil modeling system; 1) the Wang-Sheeley-Arge (WSA) semi-empirical solar coronal model, and 2) the Enlil magnetohydrodynamic (MHD) heliospheric model. MHD modeling of the full domain (solar photosphere to Earth) is extremely computationally demanding due to the large parameter space and resulting characteristic speeds within the system. To reduce the computational burden and improve the timeliness (and hence the utility in forecasting space weather disturbances) of model results, the domain of the MHD model (Enlil) is limited from 21.5 Solar Radii (Rs) to just beyond the orbit of Earth, while the inner portion, spanning from the solar photosphere to 21.5Rs, is characterized by the WSA model. This coupled modeling system is driven by solar synoptic maps composed of nu[...]
The HRRR is a NOAA real-time 3-km resolution, hourly updated, cloud-resolving, convection-allowing atmospheric model, initialized by 3km grids with 3km radar assimilation. Radar data is assimilated in the HRRR every 15 min over a 1-h period adding further detail to that provided by the hourly data assimilation from the 13km radar-enhanced Rapid Refresh. The HRRR ZARR formatted data was originally generated by the University of Utah under a grant provided by NOAA. They are are continuing to publish ZARR versions of HRRR data. For information about data in the s3://hrrrzarr/ please contact atmos-mesowest@lists.utah.edu.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.