mcpField
E
Epa Emissions

Epa Emissions

Remote
pipeworx.ioScience & Education0Updated 3d ago

About Epa Emissions

Epa Emissions exposes EPA emissions data as MCP tools for researchers and analysts examining US greenhouse-gas and toxic releases. It supports queries by state, sector, facility, or chemical, as well as historical trend analysis.

Key features

  1. 01Rank greenhouse-gas facilities by state
  2. 02Aggregate greenhouse-gas emissions by sector
  3. 03Find toxic-release facilities by state and county
  4. 04View chemical releases by medium
  5. 05Analyze trends by state or chemical

Use cases

  1. 01Compare major emitters within a state
  2. 02Identify sectors with high emissions
  3. 03Find TRI facilities and chemicals in a county
  4. 04Track multi-year changes in chemical releases

MCP support

It provides emissions-query tools to MCP clients through the Pipeworx gateway or as a local stdio MCP server.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://gateway.pipeworx.io/epa-emissions/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

mcp-epa-emissions

EPA Emissions MCP — wraps EPA Envirofacts REST API (free, no auth)

Part of Pipeworx — an MCP gateway connecting AI agents to 1879+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

ToolDescription
ghg_facility_emissionsThe biggest greenhouse-gas-emitting facilities in a US state (EPA GHGRP), ranked by total CO2-equivalent emissions. Returns each facility's name, location, industry sector(s), and total metric tons CO2e. State-scoped (pass a state). Data lags ~1.5 years — latest full year is auto-selected (currently 2023) unless a year is given.
ghg_emissions_by_sectorTotal greenhouse-gas emissions by INDUSTRY SECTOR within a US state (EPA GHGRP) — answers 'which sectors emit the most in '. Sectors: Power Plants, Refineries, Chemicals, Metals, Minerals, Pulp and Paper, Petroleum and Natural Gas Systems, Waste, etc. Returns each sector's total metric tons CO2e and facility count, ranked. State-scoped (pass a state); data lags ~1.5y so the latest full year (~2023) is auto-selected unless year is given.
tri_facility_releasesSearch EPA TRI toxic chemical release facilities by state, and optionally by COUNTY — "what toxic releases are reported in Harris County, Texas" is the shape these questions usually take. Returns facility location, county, type, and chemicals released with quantities in pounds.
tri_chemical_releasesTrack toxic chemical releases by chemical name and state. Returns quantities released to air, water, and land broken down by year.
tri_trendsAnalyze toxic release trends over time by state or chemical. Returns historical release data across years to identify patterns and changes.

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "epa-emissions": {
      "url": "https://gateway.pipeworx.io/epa-emissions/mcp"
    }
  }
}
What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/epa-emissions/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — ask_pipeworx, discover_tools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask_pipeworx, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}

Both URLs reach the same gateway and the same 1879+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

curl -X POST https://gateway.pipeworx.io/v1/tools/ghg_facility_emissions \
  -H 'Content-Type: application/json' \
  -d '{"state":"Texas"}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/ghg_facility_emissions. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.

Standalone (no gateway account)

This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:

{
  "mcpServers": {
    "epa-emissions": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-epa-emissions"]
    }
  }
}

Or run it directly to confirm it starts:

npx -y @pipeworx/mcp-epa-emissions

It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call for only this pack's tools — none of the shared meta-tools the gateway connection above adds. Same source, same tools, no ask_pipeworx routing.

Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:

ask_pipeworx({ question: "your question about Epa Emissions data" })

The gateway picks the right tool and fills the arguments automatically.

More

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.