Tomorrow.io Plus MCP for AI. Know exactly what the weather will do next.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
How this MCP server connects to your AI agent
Tomorrow.io Plus gives your AI agent access to hyper-local weather data, real-time conditions, forecasts, and historical records. It provides structured tools for reading current temperatures, predicting hourly changes, checking 24-hour trends, and visualizing active weather alerts across any coordinates.
What AI agents can do with Tomorrow.io Automation
List alerts
Lists all active, high-priority weather warnings based on your saved locations or insights categories.
List events
Retrieves specific types of localized weather events (e.g., fog, hail) for a location by category.
Get forecast weather
Pulls hourly or daily predicted weather conditions for a given location.
The agent retrieves the latest weather reading (temperature, wind, visibility) for any specified location or coordinate.
You get a structured forecast covering specific time spans—hours by hour or day by day—for future planning.
The agent pulls detailed metrics (like temperature, wind speed, and rain intensity) for specific periods, generating a usable timeline.
You request map tiles that overlay current or predicted weather layers onto existing geospatial visualizations.
The system scans for official, pre-defined weather warnings or specific event types relevant to your monitored locations.
Ask an AI about this
Waiting for input…
What AI agents can do with Tomorrow.io Plus MCP Server: 10 Tools for Weather Data Retrieval
Use these tools to get current conditions, long-range forecasts, historical data, and active weather warnings directly through your AI client.
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 VinkiusList Alerts
Lists all active, high-priority weather warnings based on your saved locations or insights categories.
List Events
Retrieves specific types of localized weather events (e.g., fog, hail) for a...
Get Forecast Weather
Pulls hourly or daily predicted weather conditions for a given location.
Get Timelines
Gets detailed metrics (like temperature or precipitation) for a specific location...
List Insights
Lists all available pre-defined or custom categories used to filter weather data and...
List Locations
Provides a list of all previously saved geographical locations within your account for consistent querying.
Get Map Tile
Retrieves map image pieces (tiles) to overlay specific weather layers onto visual maps.
Post Timelines
Retrieves weather data points that cover complex, non-point location shapes like...
Get Realtime Weather
Gets the current, immediate atmospheric conditions for a location.
Get Recent History Weather
Retrieves recorded weather data from the past 24 hours.
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 Tomorrow.io Plus 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 Tomorrow.io, 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 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
Built on the Model Context Protocol (MCP) for 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 10 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
Planning operations based on basic web searches is a gamble., Solved with Vinkius AI Gateway
Today, figuring out operational readiness means jumping through hoops. You open the weather site for general conditions, then you switch to a separate alerts page to see warnings. If you need historical data for risk assessment, you might have to download PDFs and manually copy temperature readings into a spreadsheet. It's slow, it’s disjointed, and it often misses key details.
With this MCP server, the process is different. You talk to your agent once: 'Check wind history near the port.' The agent runs `get_recent_history_weather` or `list_alerts`, pulls the precise numbers, and gives you a clean, actionable report. It cuts out all the clicking.
Tomorrow.io Plus MCP Server: Get structured weather data into your workflow.
The biggest time sink is switching between different types of analysis—you check current conditions with one tool, then have to switch context to look at the 3-day forecast using another API call. This constant context switching adds friction and delays critical decisions.
Now you can ask for everything in one go. Your agent combines `get_realtime_weather` with `get_forecast_weather` and checks `list_alerts` simultaneously, giving you a single, cohesive picture of the immediate operational risk.
What your AI can actually do with this
You connect this server to your AI agent when you need reliable, deep weather intelligence straight from the source. This isn't just some basic API call; it gives your agent structured tools for making calls based on accurate atmospheric data. You gotta know what’s going down with the weather—right now, next week, or even last month.
When you need to check current conditions, your agent runs get_realtime_weather to pull the latest reading for any spot. This tells you immediate details like temperature, wind speed, and visibility exactly where you point it. For planning ahead, you can get predictions using get_forecast_weather, which pulls structured data covering both hourly changes and full day-by-day forecasts.
You'll know what to expect for your operations.
Building graphs over time requires more than a simple forecast. If you need deep metrics—say, tracking temperature swings or rain intensity over a specific period—you use get_timelines. For complex areas that aren’t just points on a map, like following the path of a river or a factory footprint, you send geometry data to post_timelines to pull those detailed weather metrics.
You can also see what happened in the last twenty-four hours by calling get_recent_history_weather. When visualizing this stuff on a map for your users, your agent retrieves specific map image pieces, or tiles, using get_map_tile, letting you overlay current or predicted weather layers right onto existing geospatial visuals.
For risk management, the server gives you serious control. You can check for official, pre-defined warnings by calling list_alerts; this flags high-priority weather dangers relevant to your monitored locations. If you need to know about specific kinds of bad weather—like hail or fog—you use list_events to pull those localized event types based on a category.
You don't have to guess what kind of warnings are available; calling list_insights shows all the pre-defined categories you can filter data and alerts by. To keep your operations consistent, your agent uses list_locations to manage and retrieve a list of every geographical spot you’ve saved in the account.
It's a whole system that coordinates everything. You run these tools together—you get immediate conditions from get_realtime_weather, then use get_forecast_weather for planning, pull historical data with get_recent_history_weather, map it all out with get_map_tile, and finally check the risk level using list_alerts. You'll have a full picture of what’s going down.
The whole thing gives your agent access to granular detail, making sure you never run blind on weather conditions again.
019e5d61-9606-73c0-90e0-1b7943f247b5 
Here's how it actually works
The bottom line is: you tell your AI client what weather info you need, and it handles calling the right function to get clean, usable data.
First, subscribe to the Tomorrow.io Plus server and provide your API key.
Then, prompt your AI client (Claude, Cursor, etc.) with a natural language query specifying the location and data needed (e.g., 'What's the 3-day forecast for Seattle?').
The agent uses the correct tool—like get_forecast_weather—to pull the structured weather data back to your chat or script.
Who is this actually for?
Anyone who needs operational decisions based on accurate, localized weather. Think logistics managers stuck rerouting fleets because of unexpected storms, or utility engineers planning infrastructure maintenance during high-wind warnings. If your job requires knowing the sky's mood in advance, this is for you.
You use get_forecast_weather and list_alerts to plan routes that avoid predicted heavy rain or high winds, saving fuel and time.
You run get_timelines to model potential infrastructure stress by predicting sustained temperature changes or ice buildup over several hours.
You use the 10 specific tools, especially post_timelines, to feed weather data into custom applications and visualizations without complex manual API calls.
What Changes When You Connect
Avoid guessing about conditions. Use get_realtime_weather to get immediate, precise data on temperature and wind speed right now.
Plan ahead with certainty. get_forecast_weather gives you hourly or daily predictions, so you know if a delay is coming before you even leave the dock.
list_alerts lets your agent check for high-priority warnings across all your monitored sites automatically—no need to log into 10 different dashboard pages.
Deep dive into trends. Instead of just reading 'rainy,' use get_timelines to pull specific data points, like how fast the wind speed ramped up over six hours.
Map accuracy matters. If you're building a visualization tool, get_map_tile feeds weather layers directly onto your map without extra manual processing.
See it in action
Rerouting a truck fleet during unexpected storms
A logistics manager needs to know if the planned route is safe. They ask their agent: 'Check routes 12 and 3 for alerts.' The agent runs list_alerts and get_forecast_weather. It finds an active High Wind Warning near Route 3, so the AI automatically reroutes the fleet and notifies the drivers.
Assessing utility risk after a severe storm
An energy provider needs to know which areas are most vulnerable. They ask the agent to check historical data for wind damage patterns over the last month. The agent runs get_recent_history_weather and cross-references it with list_events (like hail) to prioritize repair crews.
Building a weather dashboard visualization
A developer needs a map that updates in real-time. They use get_map_tile for the background layer, and then call list_locations first to get coordinates, which they feed into get_realtime_weather to plot current conditions.
Analyzing long-term climate patterns
A researcher wants to compare temperature readings from two different sites over a specific period. They use the complex geometries tool, post_timelines, to feed data for both site boundaries into one query, giving them comparable historical metrics.
The honest tradeoffs
Treating weather like general search
Asking the agent: 'Tell me about the weather in London.' The agent only gives a vague summary because it doesn't know what specific data point you need (temp? wind?).
Don't ask generally. Be precise and use tools like get_forecast_weather. Say, 'What is the hourly temperature forecast for London over the next 48 hours?' This forces the agent to run the correct function.
Forgetting location details
Asking for a prediction without telling the server where to look. The tool will fail or return generic data.
Always start by running list_locations if you're checking saved spots, or provide coordinates/city names directly in your prompt so the agent can use the location parameters correctly.
Overlooking complex boundaries
Trying to pull data for an irregularly shaped area (like a park or industrial zone) using simple city centers.
If your monitored area isn't a single point, use the advanced tool post_timelines and provide the location as a GeoJSON geometry. This handles complex boundaries correctly.
When It Fits, When It Doesn't
Use this server if your decision flow hinges on specific, measurable weather data—like predicting when to ship cargo or when to schedule power maintenance. You need structured access (e.g., get_timelines) over narrative text.
Don't use it if you just want a general idea ('Is it going to rain?'). In that case, a standard conversational agent might be enough. But if the answer needs to guide an action—like rerouting or shutting down power—you need list_alerts and get_forecast_weather. If your data involves complex boundaries, you must use post_timelines; simple location tools won't cut it.
Questions you might have
How do I check historical weather using get_recent_history_weather? +
You simply ask your agent for it. You specify the location and the time window, and the tool pulls all recorded metrics from the last 24 hours into a structured format.
What is the difference between get_forecast_weather and get_timelines? +
Forecasts give you predictions (what will happen). Timelines pull detailed, specific fields—like just temperature or just wind speed—for a defined time range. It's about predicting vs. charting.
When should I use post_timelines instead of get_forecast_weather? +
Use post_timelines when your location isn't a single point—like an entire industrial complex or river boundary. It handles those complex, multi-point geometries.
Can I check for multiple active warnings with list_alerts? +
Yes. You ask the agent to list all alerts across your saved locations. The tool runs against predefined insight categories and reports every warning found.
How does the `post_timelines` tool handle complex geographic areas like GeoJSON? +
It processes weather data for entire geometries, not just single points. You pass a GeoJSON object to get timelines across an area instead of querying one coordinate at a time.
What specific output do I get when using the `get_map_tile` tool? +
You receive map tiles specifically for weather layers. This allows you to integrate visual data directly into mapping applications without having to render the entire layer yourself.
Before checking alerts, how do I use `list_insights` to find out what risk categories are available? +
This function lists all pre-defined or custom insight categories. It helps your AI client determine which specific risk types it needs to monitor for proactive alerting.
If I need consistent monitoring across multiple sites, how does `list_locations` help my agent? +
The tool lists all pre-defined locations in your account. This means your AI client can consistently monitor the exact coordinates you set up without needing to input them every time.
Can I get weather data for a specific latitude and longitude? +
Yes! You can use tools like get_realtime_weather or get_timelines by passing a latlong string (e.g., '40.7128, -74.0060') as the location parameter.
How do I check for active severe weather alerts? +
Use the list_alerts tool. It will retrieve all active weather alerts based on your account's insights and monitored locations.
Can I retrieve weather history for the past few hours? +
Yes, the get_recent_history_weather tool allows you to fetch weather data for the last 24 hours for any given location.
We've already built the connector for Tomorrow.io Plus. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 10 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.