Breezometer Google Pollen API
47
AI ReadinessFoundational (D)47/100
Agent-ready OpenAPI document · curated by JenticMaps GeolocationPlaces SearchapiKey2 EndpointsREST
Know of an official OpenAPI document? Contribute it →
For Agents
Look up 5-day pollen forecasts (grass, tree, weed) for any latitude/longitude and fetch heatmap tiles via two Google Pollen API endpoints behind a Google Maps API key.
Use for: I want to fetch the 5-day pollen forecast for a city, Get the grass pollen index for a latitude and longitude, Retrieve a pollen heatmap tile for a map zoom level, Find when tree pollen is forecast to peak this week
Not supported: Does not handle air quality, weather forecasts, or geocoding - use for pollen forecasts and pollen heatmap tiles only.
Jentic publishes the only available OpenAPI specification for Google Pollen API, keeping it validated and agent-ready. Google Pollen API (formerly BreezoMeter Pollen) is part of Google Maps Platform and returns up to five days of pollen information at 1km resolution across more than 65 countries. Two endpoints cover the use cases: a JSON forecast lookup at GET /forecast:lookup that takes latitude, longitude, and an optional days range, and a heatmap-tile endpoint at GET /mapTypes/{mapType}/heatmapTiles/{zoom}/{x}/{y} for rendering pollen layers on a map. Authentication is a Google Maps API key passed as the key query parameter, which makes the API straightforward to wire into health, allergy, and weather applications.
Install Jentic One Beta
Connect the Google Pollen API to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Google Pollen API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
1
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fbreezometer.com%2Fbreezometer" | sh2
Step 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fbreezometer.com%2Fbreezometer" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
Capabilities
What an agent can do with Google Pollen API.
Get a 1-5 day pollen forecast for a coordinate via GET /forecast:lookup with latitude, longitude, and days
Render pollen heatmap tiles by zoom and x/y via GET /mapTypes/{mapType}/heatmapTiles/{zoom}/{x}/{y}
Filter forecasts by plant type (grass, tree, weed) using the plant detail flags on the lookup endpoint
Localise category descriptions and recommendations by passing a languageCode on the lookup endpoint
Power 1km-resolution allergy maps for more than 65 countries on a single API key
Use Cases
Patterns agents use Google Pollen API for, with concrete tasks.
★ Allergy and wellness app forecasts
Power an allergy app that shows users the pollen forecast for their home and any saved locations. The client geocodes the location, then calls GET /forecast:lookup with location.latitude, location.longitude, and days=5 to get per-plant indexes. Localised category descriptions support multilingual users without bespoke translation work.
GET /forecast:lookup with location.latitude=40.7128, location.longitude=-74.0060, days=5, languageCode='en' and return the dailyInfo array with pollenTypeInfo per day.
Pollen heatmap layer on weather maps
Add a pollen heatmap layer on top of a base map so users can see where pollen is concentrated regionally. The frontend requests heatmap tiles by zoom/x/y from GET /mapTypes/{mapType}/heatmapTiles/{zoom}/{x}/{y}, choosing a mapType such as TREE_UPI, GRASS_UPI, or WEED_UPI. This is the same tile flow used in Google Maps Platform overlays.
GET /mapTypes/TREE_UPI/heatmapTiles/8/72/96 (with key) and render the returned PNG as a tile in the map's pollen overlay.
Outdoor activity planning
Help runners and cyclists plan workouts on lower-pollen days. The backend reads GET /forecast:lookup for the next five days and recommends outdoor sessions when the worst plant index falls below a configured threshold. Plant-specific filtering supports users with a known sensitivity to grass or ragweed.
GET /forecast:lookup for the user's location with days=5; for each day, take the maximum pollenTypeInfo[].indexInfo.value and surface days where the max < 3.
AI agent integration via Jentic
An agent answering 'how bad is the pollen tomorrow at my address?' can discover the Google Pollen API through Jentic, load the forecast lookup operation, and execute it without holding the Maps API key in its prompt context. Jentic injects the key as the query parameter at execution time and returns typed forecast data the agent can summarise.
Through Jentic, search 'get a pollen forecast for a location', load the GET /forecast:lookup operation, and execute with location.latitude, location.longitude, and days=3.
Key Endpoints
2 endpoints — jentic publishes the only available openapi specification for google pollen api, keeping it validated and agent-ready.
METHOD
PATH
DESCRIPTION
GET
/forecast:lookup
Pollen forecast for a latitude/longitude over 1-5 days
GET
/mapTypes/{mapType}/heatmapTiles/{zoom}/{x}/{y}
Pollen heatmap tile for a map zoom level
GET
/forecast:lookup
Pollen forecast for a latitude/longitude over 1-5 days
GET
/mapTypes/{mapType}/heatmapTiles/{zoom}/{x}/{y}
Pollen heatmap tile for a map zoom level
Jentic AI Readiness Score
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
G
Google Pollen API
- Foundational (D)47/100
100
Foundational Compliance63
Developer Experience & Jentic Compatibility47
AI-Readiness & Agent Experience94
Agent Usability15
Security63
AI DiscoverabilityPowered by JenticScoring Framework 1.0.0 | Scoring Engine 0.4.0
Show dimension breakdown
100
Foundational Compliance
Base layer of spec validity and structural soundness.
Grade: A+Signals: 4
99%
Lint Results
Aggregated quality score from linter diagnostics, weighted by severity.
100%
Resolution Completeness
Percentage of `$ref` references that resolve successfully.
100%
Specification Validity
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
100%
Structural Integrity
Structural correctness score based on schema issues using logarithmic dampening.
63
Developer Experience & Jentic Compatibility
Clarity, completeness, and ingestion readiness for developers and tooling.
Grade: B-Signals: 4
0%
Example Density
How richly the API is illustrated with examples.
100%
Example Validity
Percentage of examples that conform to their schemas.
50%
Response Coverage
Percentage of operations with complete response definitions (success, client error, server error).
100%
Tooling Readiness
Health of API ingestion, bundling, and resolution within Jentic pipelines.
47
AI-Readiness & Agent Experience
Semantic breadth, depth, and agent comprehension for AI systems.
Grade: DSignals: 4
38%
Description Coverage
Coverage of descriptions across API elements.
0%
Error Standardization
Coverage of RFC 9457 Problem Details for error responses.
100%
OperationId Quality
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
50%
Summary Coverage
Coverage of summaries across operations/tags/info.
94
Agent Usability
Functional utility, complexity comfort, and AI orchestration readiness.
Grade: A+Signals: 1
94%
Complexity Comfort
Agent comfort level based on API operational and structural complexity.
15
Security
Trust, risk posture, and security compliance.
Grade: FSignals: 1
15%
Authentication Strength
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
63
AI Discoverability
Findability, semantic richness, and reasoning readiness.
Grade: B-Signals: 1
62%
Descriptive Richness
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>Why Jentic?
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Google Pollen API by hand means provisioning a Google Maps key, appending it as the key query parameter on every request, and handling the forecast lookup and tile-coordinate math yourself. Through Jentic you install once, import the Google Pollen API from the API Directory, store the key once, and your agent calls it.
Permission scoping
The Pollen API takes its location and tile coordinates in the request, not as a resource id in the URL path, so scoping is operations-only: limit the agent to the operations it needs, such as the forecast lookup, and leave out the heatmap-tile operation if it only needs text forecasts. You choose which of these read operations it may call.
Credential isolation
Your Google Maps key for the Pollen API is stored once, encrypted, by your own Jentic One instance and injected as the key query parameter at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'get a pollen forecast for a location', and Jentic returns the GET /forecast:lookup operation with its latitude, longitude, and days parameters typed, plus the heatmap-tiles operation when the agent needs imagery, so it calls the right endpoint without browsing the reference docs.
Related APIs
Alternatives and complements available in the Jentic catalogue.
FAQs
Specific to using Google Pollen API through Jentic.
Why is there no official OpenAPI spec for Google Pollen API?
Google Maps Platform documents the Pollen API in narrative form rather than publishing a downloadable OpenAPI specification. Jentic generates and maintains this spec so that AI agents and developers can call Google Pollen API via structured tooling. It is validated against the live API and kept up to date. Get started with Jentic One, the self-hosted execution layer.
What authentication does the Google Pollen API use?
It uses a standard Google Maps API key passed as the key query parameter on every request. Restrict the key by HTTP referrer or IP in the Google Cloud Console; through Jentic, the key is held in the encrypted vault and appended to /forecast:lookup and tile requests at execution time.
How many days of pollen forecast does the Google Pollen API return?
GET /forecast:lookup returns up to 5 days of pollen information when you pass days=5. Coverage spans more than 65 countries at 1km resolution, with separate indexes for tree, grass, and weed pollen on each day.
What are the rate limits for the Google Pollen API?
Pollen API quotas are managed through the Google Cloud Console as part of Google Maps Platform - daily request quotas and per-second QPS are configurable per project. Check your Cloud Console quotas page before fanning out heatmap-tile requests across many zoom levels.
How do I get a pollen forecast through Jentic?
Install with pip install jentic, then await client.search('get a pollen forecast for a location'), await client.load on the GET /forecast:lookup operation, and await client.execute with location.latitude, location.longitude, and days. Jentic appends the Maps API key at execution time.
Does the Google Pollen API support heatmap tiles?
Yes. GET /mapTypes/{mapType}/heatmapTiles/{zoom}/{x}/{y} returns PNG tiles for tree (TREE_UPI), grass (GRASS_UPI), and weed (WEED_UPI) heatmap layers. Use them as a tile overlay on a base map alongside the forecast lookup data.
Can I limit what my agent is allowed to do with the Google Pollen API?
Yes. Because the Google Pollen API takes location and tile coordinates in the request rather than as resource ids in the URL path, scoping is operations-only, and your self-hosted Jentic One instance lets you decide which operations the agent may call. If the agent only needs text forecasts, allow just GET /forecast:lookup and leave out the GET /mapTypes/{mapType}/heatmapTiles/{zoom}/{x}/{y} tile operation. Your own rules also govern the Google Maps API key, which is injected as the key query parameter at execution time and never enters the agent's prompt.
GET STARTED