EPA Air Quality & Toxics
Server Details
Toxics Release Inventory, Superfund sites, air quality data, and AQI
- Status
- Healthy
- Last Tested
- Transport
- Streamable HTTP
- URL
Glama MCP Gateway
Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.
Full call logging
Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.
Tool access control
Enable or disable individual tools per connector, so you decide what your agents can and cannot do.
Managed credentials
Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.
Usage analytics
See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.
Tool Definition Quality
Average 4/5 across 5 of 5 tools scored.
Each tool has a clearly distinct purpose with no overlap: annual air quality summaries, AQI forecasts, current AQI readings, Superfund sites, and TRI facilities. The tools target different data types (historical vs. forecast vs. current vs. regulatory lists) and different query parameters, making them easily distinguishable.
All tools follow a consistent verb_noun pattern with 'get_' prefix and descriptive suffixes (e.g., get_annual_air_quality, get_aqi_forecast). The naming is uniform across all five tools, using snake_case throughout without any deviations in style or structure.
Five tools is reasonable for an EPA server covering air quality and toxics, but it feels slightly thin for the broad domain. The tools cover key areas, but additional tools for specific pollutants or detailed site data could enhance completeness without being overwhelming.
The server covers air quality (historical, forecast, current) and toxics (Superfund, TRI) well, but there are notable gaps. Missing operations include updates or deletions (not applicable here), but more critically, there's no tool for detailed pollutant analysis across locations or time-series queries beyond annual summaries, which limits agent flexibility.
Available Tools
5 toolsget_annual_air_qualityAInspect
Get annual air quality summary data for a US state.
Returns annual statistics from the EPA Air Quality System (AQS),
including mean concentrations, max values, and exceedance counts
for the specified pollutant across all monitoring sites in the state.
Args:
state: Two-letter US state abbreviation (e.g. 'CA', 'NY').
parameter: Pollutant to query. Options: 'PM2.5', 'Ozone', 'SO2', 'NO2', 'CO'.
Default is 'PM2.5'.
start_year: Start year for the query range (e.g. 2020). Default is 2020.
end_year: End year for the query range (e.g. 2023). Default is 2023.| Name | Required | Description | Default |
|---|---|---|---|
| state | Yes | ||
| end_year | No | ||
| parameter | No | PM2.5 | |
| start_year | No |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, description carries full burden by disclosing data source (EPA AQS), return metrics (mean, max, exceedances), and geographic scope (all monitoring sites).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Well-structured with purpose front-loaded, followed by return value details, and clear Args section; every sentence provides distinct value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Comprehensive for its complexity; acknowledges output schema existence by summarizing return statistics without redundantly detailing fields.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 0% schema coverage, description excellently compensates by providing formats (two-letter abbreviation), enumerated options for pollutant, examples, and defaults for all parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Specific verb+resource ('Get annual air quality summary data') clearly distinguishes from siblings (current/forecast) by emphasizing 'annual' statistics from EPA AQS.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage is implied by 'annual' distinguishing it from real-time siblings, but lacks explicit when-to-use guidance or alternative comparisons.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_aqi_forecastAInspect
Get the air quality forecast for a ZIP code.
Returns forecast AQI values and health categories for upcoming days,
typically covering today and the next 1-2 days.
Args:
zip_code: US ZIP code (e.g. '20001').| Name | Required | Description | Default |
|---|---|---|---|
| zip_code | Yes |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses key behavioral trait not in annotations: the limited forecast window ('typically covering today and the next 1-2 days'), and notes that health categories are included in returns.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Compact and front-loaded; the 'Args:' section is slightly redundant with schema structure but necessary given the lack of schema descriptions, earning its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Appropriate for low complexity; covers input requirement, behavioral scope, and return value summary without needing to detail the output schema structure.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Excellent compensation for 0% schema description coverage by specifying 'US ZIP code' and providing a concrete example ('20001'), adding crucial semantic constraints.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clear specific verb ('Get') and resource ('air quality forecast'), and the term 'forecast' with 'upcoming days' effectively distinguishes it from 'current' and 'annual' sibling tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides implied usage through temporal context ('upcoming days', 'today and next 1-2 days') but lacks explicit guidance on when to choose this over get_current_aqi or get_annual_air_quality.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_current_aqiAInspect
Get the current Air Quality Index (AQI) for a location.
Provide either a zip_code OR latitude/longitude coordinates.
Returns AQI values, pollutant levels, and health category for
each measured pollutant at the nearest monitoring station.
Args:
zip_code: US ZIP code (e.g. '20001').
latitude: Latitude of the location (e.g. 38.9).
longitude: Longitude of the location (e.g. -77.0).| Name | Required | Description | Default |
|---|---|---|---|
| latitude | No | ||
| zip_code | No | ||
| longitude | No |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses key behavioral details not in schema: data comes from 'nearest monitoring station' and specifies return contents (pollutant levels, health categories).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Front-loaded, structured with clear Args section; every sentence conveys unique information without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Appropriately complete given output schema exists; covers input constraints and return summary, though could explicitly note that all parameters are technically optional but one location method is required.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Completely compensates for 0% schema description coverage by providing an Args section with clear examples ('20001', 38.9, -77.0) clarifying expected formats.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clear specific purpose ('Get the current AQI') with 'current' distinguishing it from forecast/annual siblings, though explicit contrast with non-AQI siblings (superfund, TRI) is absent.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides critical parameter guidance (zip_code OR lat/long) but lacks explicit when-to-use guidance versus sibling tools like get_aqi_forecast.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_superfund_sitesAInspect
Get active Superfund (National Priorities List) sites in a state.
Returns hazardous waste cleanup sites listed on the EPA's National
Priorities List, including site names, locations, and status information.
No API key required.
Args:
state: Two-letter US state abbreviation (e.g. 'NJ', 'CA').
limit: Maximum number of sites to return (default 50, max 500).| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| state | Yes |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses no authentication needed and summarizes return contents (names, locations, status), but omits rate limits, error behaviors, or data freshness given no annotations exist.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Appropriately compact with front-loaded purpose; Args section efficiently injects parameter semantics without excessive verbosity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Adequate for a simple 2-parameter tool with output schema; covers authentication, return value summary, and parameter details sufficiently.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 0% schema description coverage, the description fully compensates by providing format constraints (two-letter abbreviation), examples ('NJ', 'CA'), and limit bounds (default 50, max 500).
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states it retrieves active Superfund/NPL sites with specific resource identification, though it doesn't explicitly differentiate from sibling get_tri_facilities which also deals with hazardous waste.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Notes 'No API key required' (prerequisite) but lacks explicit guidance on when to use this versus get_tri_facilities or other environmental data tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_tri_facilitiesAInspect
Get Toxics Release Inventory (TRI) facilities in a state.
Returns facilities that report toxic chemical releases to the EPA,
including facility names, addresses, and industry information.
No API key required.
Args:
state: Two-letter US state abbreviation (e.g. 'CA', 'TX').
city: Optional city name to filter results.
limit: Maximum number of facilities to return (default 50, max 500).| Name | Required | Description | Default |
|---|---|---|---|
| city | No | ||
| limit | No | ||
| state | Yes |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses authentication requirements (none) and return payload details (names, addresses, industry info) beyond empty annotations, but omits rate limits or caching behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Well-structured with front-loaded purpose and concise Args section; no redundant sentences, though docstring formatting slightly differs from typical MCP description style.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Adequately covers the simple 3-parameter interface and references output schema existence; complete enough given the tool's limited complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Excellent compensation for 0% schema description coverage by providing clear semantics, examples (e.g., 'CA', 'TX'), and constraints (max 500) for all three parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states it retrieves TRI facilities by state and distinguishes from air-quality-focused siblings, though it could explicitly differentiate from get_superfund_sites.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Lacks explicit guidance on when to use versus alternatives (e.g., TRI vs Superfund sites) and contains no exclusion criteria or workflow context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Claim this connector by publishing a /.well-known/glama.json file on your server's domain with the following structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"maintainers": [{ "email": "your-email@example.com" }]
}The email address must match the email associated with your Glama account. Once published, Glama will automatically detect and verify the file within a few minutes.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
Discussions
No comments yet. Be the first to start the discussion!