Tomorrow.io MCP. Predicting Hazards, Not Just Temperature.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Tomorrow.io gives your AI agent real-time access to institutional-grade weather data. It handles hyperlocal forecasts, specialized environmental matrices like AQI and pollen counts, and complex hazard assessments for road risk or wildfire index.
If your logic flow depends on knowing if it's safe to drive through a storm or what the air quality is today, this connector feeds that intelligence directly into your agent.
What your AI agents can do
Get air quality index
Retrieves current and forecasted data on air quality indices for a specific location.
Get custom timelines
Queries weather data for custom time ranges, allowing you to specify arbitrary intervals not covered by standard tools.
Get daily forecast
Returns daily weather forecast extremes and totals spanning up to 15 days out.
Provides real-time weather data (temperature, wind speed, etc.) for a specific global location.
Generates forecasts segmented by minute, hour, or full day over up to 15 days out.
Retrieves current and forecast data for air quality index (AQI) and daily pollen density.
Runs assessments specific to driving conditions, identifying potential road hazards due to weather.
Retrieves actual recorded weather observations by specifying past dates and fields for analysis.
Ask AI about this MCP
Supported MCP Clients
OAuth 2.0 Compatible Gemini Waiting for input…
Tomorrow.io MCP Server: 10 Tools for Climate Intelligence
These tools let you query everything from current air quality to 15-day weather extremes, ensuring your agent has the most detailed environmental data available.
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 Tomorrow.io on Vinkius019d7614get air quality index
Retrieves current and forecasted data on air quality indices for a specific location.
019d7614get custom timelines
Queries weather data for custom time ranges, allowing you to specify arbitrary intervals not covered by standard tools.
019d7614get daily forecast
Returns daily weather forecast extremes and totals spanning up to 15 days out.
019d7614get historical weather
Retrieves actual recorded weather observations for specified past dates and locations.
019d7614get hourly forecast
Returns hour-by-hour predictions for a given location, up to 120 hours into the future.
019d7614get minutely precipitation
Provides minute-by-minute precipitation forecasts (nowcasts) for high precision planning.
019d7614get pollen forecast
Retrieves daily predictions and indices specifically for pollen counts.
019d7614get realtime weather
Provides current, real-time weather conditions using a location identifier (lat/lon, zip, or city).
019d7614get road weather risk
Generates assessments and predictions specifically for driving and road hazards based on weather.
019d7614get wildfire risk
Retrieves the current wildfire risk index alongside associated weather conditions.
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 Tomorrow.io, then connect any of our 4,900+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,900+ 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 Tomorrow.io. 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 server provides 10 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Planning for extreme weather doesn't work with simple dashboards.
Think about it: Today, if you need to plan a large outdoor event or manage a fleet of vehicles, you have to open three different tabs. One for the general forecast, one for wind speed/rain probability, and maybe another site just to check local air quality. You're cross-referencing data points manually—a massive time sink.
With this MCP server, that entire process collapses into a single query. Ask your agent: 'What are the expected environmental risks for the city center next week?' The system runs `get_daily_forecast` *and* checks `get_air_quality_index`, giving you one consolidated risk report. You get actionable intelligence instantly.
Tomorrow.io MCP Server: Get specific environmental data points.
Before, checking the road safety for a long haul required calling multiple dispatch lines and looking at regional weather alerts—a slow, siloed process that meant delayed routes and wasted fuel. You were always reacting to what *was* happening.
Now, you query `get_road_weather_risk` directly through your agent. It assesses the forecast across complex variables—ice buildup, high winds, low visibility—and tells you exactly when and where the route becomes unsafe. The system predicts risk before it happens.
What you can do with this MCP connector
Look, if your logic flow depends on knowing what the weather’s gonna do—and you know it does—this connector feeds all that intelligence right into your agent. You're getting institutional-grade data from Tomorrow.io, meaning you don't just get surface-level forecasts; you get hyper-specific environmental matrices for everything from pollen counts to road risk.
Getting Current Atmospheric Readings:
You can pull real-time conditions using get_realtime_weather. Just give it a location—a zip code, city, or lat/lon—and you'll get the current temperature, wind speed, pressure, and other atmospheric indicators right now. It’s what you use when your agent needs to know if it's raining this second.
Predicting Future Weather Patterns:
When predicting out, you've got options for every timescale. If you need a quick look at the big picture, get_daily_forecast gives you daily extremes and totals spanning up to 15 days. You can zoom in way deeper if you use get_hourly_forecast, which returns predictions hour-by-hour for up to 120 hours out.
But sometimes, minutes matter—and they do. Use get_minutely_precipitation when you need minute-by-minute rain forecasts (nowcasts) for super precise planning.
If the standard forecast tools don't cover the exact window your agent needs, use get_custom_timelines. This lets you query weather data over custom time ranges—you specify the arbitrary intervals, and it pulls the data. You’ll also want to check out specialized environmental forecasts: get_air_quality_index fetches current and forecasted air quality index (AQI) for any location.
For allergy season planning, get_pollen_forecast gives you daily predictions specifically for pollen counts. And if there's a wildfire brewing, get_wildfire_risk pulls the current risk index alongside associated weather conditions.
Analyzing Road Travel Risk:
You can’t just look at the temperature and assume the roads are fine. You need to run specialized checks on road hazards using get_road_weather_risk. This tool generates specific assessments for driving safety, helping you plan routes around complex weather patterns like flash flooding or icy conditions.
Querying Environmental History:
Need to audit something? Want to train a model based on what actually happened last fall? Use get_historical_weather. You can retrieve actual recorded observations by specifying past dates and locations, letting your agent analyze outcomes from any time period in the past. This isn't theoretical data; it’s real-world records.
Ultimately, this server gives your AI client everything it needs—from immediate atmospheric readings to 15-day projections, specialized hazard reports, and historical benchmarks. You'll feed all that depth directly into your agent's decision-making process.
019d7614-18ce-716f-9268-94fb40cd71d1 
How Tomorrow.io MCP Works
- 1 First, you must subscribe to the Tomorrow.io connector and provide your developer API Key in your agent's configuration.
- 2 Next, ask your AI client a query that requires weather data (e.g., 'What is the wildfire risk for Seattle next week?').
- 3 The agent automatically invokes the correct tool—like
get_wildfire_riskorget_daily_forecast—and uses the returned structured data to answer your prompt.
The bottom line is: You just ask questions in plain language, and the server runs the complex weather models for you.
Who Is Tomorrow.io MCP For?
This connector is built for operations engineers who can't afford downtime. If your job involves logistics planning, predictive maintenance, or managing field crews, you need this. It solves the problem of relying on generalized weather APIs that don't account for specific hazards like pollen spikes or localized road closures.
Uses get_road_weather_risk to check routes dynamically, rerouting trucks when the agent predicts flash flooding or high winds.
Runs get_historical_weather and fuses those recorded data points with internal business metrics (like sales) to build predictive models.
Combines get_air_quality_index and get_pollen_forecast to issue public warnings or adjust facility operating hours.
What Changes When You Connect
- You stop guessing about the weather. Using
get_road_weather_risk, you get specific hazard assessments for vehicle routes, letting your agent automatically adjust delivery paths instead of just flagging 'rain.' - Forecasting is precise. Instead of a general daily forecast, tools like
get_minutely_precipitationgive you minute-by-minute rain predictions—critical when scheduling outdoor construction work. - Your health logic gets better data. By combining
get_air_quality_indexandget_pollen_forecast, your agent can issue alerts that account for both PM2.5 levels and seasonal allergies, which simple weather APIs miss. - Planning for the long term? The
get_daily_forecastprovides 15 days of total predictions, allowing you to schedule large-scale events or resource deployments weeks in advance. - You can audit anything that happened. If a project failed due to poor visibility last month, run
get_historical_weatherto pull the exact conditions for that date and location.
Real-World Use Cases
Emergency Logistics Rerouting
A logistics manager needs a route through three states. Instead of checking Google Maps, they ask their agent: 'Find me the safest route from A to C.' The agent runs get_road_weather_risk for every segment and automatically reroutes the fleet around areas flagged with high wind or ice risks.
Annual Festival Planning
An events coordinator needs to know if they need to reschedule an outdoor market. They ask their agent: 'What are the weather risks for October 15th?' The agent runs get_daily_forecast and cross-references it with expected high pollen counts from get_pollen_forecast, flagging potential conflicts weeks ahead.
Industrial Site Monitoring
An industrial safety team needs to know if their site is at risk. They ask: 'Is the area safe for outdoor work?' The agent uses get_wildfire_risk and get_air_quality_index. If either index spikes, the system automatically locks down access protocols.
Insurance Claim Auditing
An adjuster needs to validate a claim from last season. They ask: 'What were the precise conditions at this zip code on July 2nd?' The agent runs get_historical_weather, providing exact data points for rainfall, wind speed, and temperature.
The Tradeoffs
Asking a general weather question.
User asks: 'Will it rain next week in Boston?' The agent uses get_daily_forecast but the output is vague, providing only daily summaries that don't help with immediate planning.
→
For actionable data, use specific tools. To check for constant rainfall, run get_minutely_precipitation. If you need a full 15-day look at extreme temps and totals, use get_daily_forecast.
Mixing location types.
User asks: 'What's the wildfire risk near my office?' (Office is in NYC, but they are traveling to California.) The agent fails because it doesn't know which coordinates to use for get_wildfire_risk.
→
Always provide precise geographical context (lat/lon or zip code) when querying tools like get_realtime_weather or get_wildfire_risk. Don't assume the agent knows your destination.
Over-relying on current data.
User asks: 'What are the road risks right now?' The agent uses get_realtime_weather but misses that a storm is predicted for two hours from now, which is the actual risk factor.
→
For predictive planning, run get_road_weather_risk. This tool specifically looks ahead to forecast hazards rather than just reporting current conditions.
When It Fits, When It Doesn't
Use this MCP Server if your operational decisions depend on highly specialized, granular weather intelligence. You need more than just temperature; you need environmental matrices (AQI, pollen), minute-level timing (get_minutely_precipitation), and specific hazard modeling (get_road_weather_risk).
Don't use this if you only need a general 'Will it rain today?' answer. For basic daily summaries, many simple weather APIs will suffice. But for anything involving logistics, public health mandates, or complex risk mitigation, these specialized tools are necessary because they treat environmental data as an active input to your workflow.
If your primary goal is historical trend analysis, use get_historical_weather. If you're worried about the current state of the air, stick strictly to get_air_quality_index.
Common Questions About Tomorrow.io MCP
How do I check if there will be rain minute-by-minute using get_minutely_precipitation? +
You must specify a location (lat/lon) and a time window. This tool gives you the highest level of temporal detail available, showing predicted precipitation in mm/hr at one-minute intervals.
Can I use get_historical_weather to prove weather for an insurance claim? +
Yes. By defining the precise time boundaries and field sets you need (e.g., wind speed, precipitation), this tool pulls actual recorded data points, making it useful for audits and claims verification.
What is the difference between get_hourly_forecast and get_daily_forecast? +
The hourly forecast breaks down predictions into 1-hour increments (up to 120 hours), giving you detailed timing. The daily forecast provides summarized extremes and totals over longer periods, up to 15 days.
Does get_road_weather_risk account for pollen counts? +
No. get_road_weather_risk focuses strictly on driving hazards like ice, fog, and high winds. For allergens or air quality issues, you need to call the dedicated get_pollen_forecast or get_air_quality_index tools.
What happens if I try to use get_realtime_weather without an API key? +
The request fails immediately with a 401 Unauthorized error. You must first subscribe to the service and configure your developer API Key within your agent's environment variables for any tool call to succeed.
Are there rate limits when I use get_hourly_forecast repeatedly? +
Yes, all endpoints enforce rate limiting. If you exceed the allowed calls per minute, your agent will receive a 429 Too Many Requests status code. You'll need to build backoff logic into your workflow to handle this gracefully.
How precise is the location input for get_realtime_weather? +
The system accepts four inputs: city name, zip code, latitude, or longitude. For maximum precision and reliable results, always pass specific lat/lon coordinates rather than relying on general place names.
Can I check both wildfire risk and air quality using get_wildfire_risk and get_air_quality_index? +
You must call these tools separately for the required location and timeframe. Your agent executes each tool independently, then you merge those distinct data points in your code to create a comprehensive risk assessment.
Where do I retrieve my Tomorrow.io API Key? +
Log into your account via app.tomorrow.io. Navigate directly to the API Management or Developer tab nested inside your settings. Create a new root token, copy it in its entirety, and insert it securely to enable queries.
How accurate is the 'minutely' precipitation forecast tool? +
Tomorrow.io operates proprietary radar networks, satellites, and sophisticated high-resolution systems natively intended to provide powerful precision for up to exactly 60 minutes ahead, projecting precipitation downshifts incredibly well locally.
How far into the future can the agent forecast extreme weather events? +
Using Tomorrow.io's advanced predictive modeling, the agent can provide precise hour-by-hour projections and daily forecasts up to 15 days ahead. This extended timeline offers ample opportunity for logistical and operational planning against severe environmental risks.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.