mcp-ambee

air_quality_forecast

Get an hourly air quality and pollutant forecast for the next 48 hours for a location.

You must provide EITHER:

lat and lng (if you already have or confidently know the coordinates), OR
place (a free-text place name, e.g. "Bengaluru", "Baker Street, London", "90210, US") — the API resolves this to a location itself, so do not try to geocode it yourself first, and do not call any other tool before this one.

Do not pass both lat/lng and place at once — pick one form.

Input Schema

TableJSON Schema

Name	Required	Description
`lat`	No	Latitude of the location (omit if using `place`).
`lng`	No	Longitude of the location (omit if using `place`).
`place`	No	Free-text place name like a city, street, or postcode with country (omit if using `lat`/`lng`).
`locale`	No	Optional. If set, adds local time to each hourly record.
`aqiStandard`	No	Optional. The standard used to calculate the Air Quality Index. You can pass any of these five: EPA, IN, UK, CN, CA. And default value is EPA.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

First observedSep 7, 2026

TDQS

A4.4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are present, so the description carries the behavioral burden. It discloses that the API itself resolves free-text place names and that no preceding geocoding tool call is needed. It could add more about units or error behavior, but the key behaviors for a read-only forecast are well covered.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with a one-sentence purpose, followed by a clear bullet-style breakdown of input constraints. The repetition of 'do not pass both' and 'pick one form' is slightly redundant but reinforces the most important usage rule.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Combined with 100% schema coverage and an output schema, the description provides everything needed to invoke the tool correctly: location alternatives, geocoding behavior, and forecast horizon. No critical gap remains for an agent to call it safely and correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents all five parameters. The description adds real value by defining the mutually exclusive lat/lng vs place relationship, providing concrete place examples, and warning against passing both forms at once.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('Get'), an exact resource ('hourly air quality and pollutant forecast'), and scope ('next 48 hours for a location'). This clearly differentiates it from siblings like air_quality_latest and pollen_forecast by resource and forecast horizon.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit rules for input selection: use either lat/lng or place, never both, and do not geocode first or call other tools beforehand. It does not explicitly name air_quality_latest as the current-conditions alternative, but the forecast-vs-latest distinction is clear from context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All mcp-ambee tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.6/5.0

Disambiguation5/5

Each tool has a unique combination of domain (air quality, pollen, weather) and temporal scope (forecast, latest), making selection unambiguous. No two tools overlap in purpose.

Naming Consistency5/5

All tool names follow a strict {domain}_{time_type} pattern, with every domain offering a _forecast and _latest variant. This creates a highly predictable and coherent naming scheme.

Tool Count5/5

With exactly 6 tools covering three environmental domains and two temporal modes, the count is well-balanced and each tool earns its place. The set is neither bloated nor thin.

Completeness5/5

The server provides both real-time and forecast data for all three core domains it targets (air quality, pollen, weather), offering complete coverage for its apparent purpose. No obvious missing operations that would cause agent failures.

Resources

Need Help?