epa-mcp-server

Search TRI Releases by Region

epa_tri_search_releases

Read-onlyIdempotent

TRI: Search Toxic Release Inventory data across facilities in a state or county, for one reporting year or, without year, every available year newest first. Returns facility name and county, TRI facility ID, chemical name, and the one-time / non-routine release quantity; set include_release_breakdown to add routine on-site releases by medium (air, water, land, and underground-injection), at the cost of a slower call. Quantities are in pounds; dioxin and dioxin-like compounds, which TRI has facilities report in grams, are converted and marked with reportedUnit. Use to identify top polluters in an area or build an environmental exposure profile. Use epa_tri_get_facility_releases for detailed release records for a single facility. TRI data lags ~18 months from the current calendar year.

Input Schema

Name	Required	Description
`year`	No	Reporting year. Omit to search every available year in the state, newest reporting year first, so limit keeps the most recent filings. TRI data lags ~18 months.
`limit`	No	Maximum number of release records to return (1–200)
`state`	Yes	2-letter US state abbreviation (required, e.g. "WA", "TX")
`county`	No	County name to narrow results within the state, e.g. "King". Case-insensitive partial match on the bare name, so a short name can also match a longer one (LAKE matches LAKE OF THE WOODS; check countyName on each record); a trailing "County", "Parish", or "Borough" is dropped before matching. Punctuation is matched as written ("Prince George's").
`chemical_name`	No	Optional filter to restrict results to a specific chemical (partial match, case-insensitive). Commas, apostrophes, brackets, and Greek letters are matched as written, e.g. "4,4'-Methylenedianiline".
`include_release_breakdown`	No	Add routine on-site releases by medium (air, water, land, underground injection) to each record. Costs one extra upstream request, which can add about 20 seconds when EPA has not cached it.

Output Schema

Name	Required	Description
`cap`	No	The limit that was applied. Present only when truncated.
`error`	No	Present when the call failed. Absent on success.
`shown`	No	Number of release records returned. Present only when truncated.
`state`	No	State queried
`notice`	No	Present when a punctuated county or chemical_name filter read its page limit before finding limit matches spelled as given, so more matching records may exist.
`message`	No	Recovery hint when no releases are found. Absent when releases are returned.
`releases`	No	TRI release records for facilities in the queried state and filters
`truncated`	No	True when the result list was capped at the limit — more records may exist. Absent below the limit.

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 24, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already cover read-only/idempotent safety, and the description adds material behavior beyond them: an ~18-month data lag, the ~20-second latency cost of include_release_breakdown when uncached, unit handling (pounds, grams conversion for dioxins marked via reportedUnit), and newest-first ordering. This is exactly the extra context annotations cannot supply.

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 what the tool returns before branching into the include_release_breakdown tradeoff and alternative-tool routing, so an agent can stop reading once it has what it needs. It is dense and slightly long, but nearly every clause carries information rather than filler.

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?

Given six parameters, an output schema, and read-only annotations, the description supplies everything an agent needs: return fields, unit conventions, latency tradeoff, data staleness, and sibling routing. Nothing required to call it correctly is missing.

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 baseline is 3, but the description adds meaning the schema lacks: quantities are in pounds, dioxin-like compounds are converted from grams and flagged with reportedUnit, and time-related defaults (newest-first so limit keeps recent filings). It stops short of documenting every parameter but meaningfully enriches the key ones.

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 (Search) and resource (Toxic Release Inventory data) with clear scope: facilities in a state or county, for one year or all years newest-first. It explicitly distinguishes itself from the sibling epa_tri_get_facility_releases, so the boundary is unambiguous.

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

Usage Guidelines5/5

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

Names concrete use cases (identify top polluters in an area, build an environmental exposure profile) and the alternative tool with its selecting condition ('for detailed release records for a single facility'). When-to-use and when-to-use-something-else are both explicit.

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

All epa-mcp-server tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.