
Connects to the EPA's Enforcement and Compliance History Online (ECHO) web services, giving you programmatic access to environmental compliance and enforcement data for facilities across the United States. The source doesn't list specific tools, but ECHO APIs typically cover facility searches, inspection records, violation histories, and enforcement actions. No authentication required. Useful when you need to check a company's environmental compliance track record, research pollution data for a geographic area, or pull enforcement histories for due diligence. Part of the Pipeworx gateway, so you can use their ask_pipeworx wrapper to query in plain English instead of learning the EPA's parameter structure.
The U.S. Environmental Protection Agency's Enforcement and Compliance History Online (ECHO). Facility-level compliance status, inspection history, formal and informal enforcement actions, permit data (Clean Air Act, Clean Water Act, RCRA, etc.). The authoritative source for "is this facility in trouble with EPA?" Free, no auth.
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
For environmental risk assessment, regulatory due diligence, and ESG analysis, EPA ECHO is the primary source for what's actually happening with EPA enforcement. Self-reported emissions data is one thing; ECHO tells you when the EPA actually showed up and took action.
Common flows:
echo_facility_search({name: "X"}) → matching facilities with their EPA Registry IDs, compliance status, recent enforcement.Used by the environmental_risk recipe alongside GHG emissions and TRI data.
None. ECHO is fully public and free. Pipeworx forwards a polite User-Agent.
| Program | What it covers |
|---|---|
| CAA (Clean Air Act) | Major emitters, NSPS standards, NESHAP toxic air pollutants |
| CWA / NPDES | Water discharge permits, effluent limits, biosolids |
| RCRA | Hazardous waste generators, transporters, treatment/storage/disposal facilities |
| SDWA | Public water systems |
| TRI | Toxic Release Inventory reporters (separate tri_facility_releases tool) |
A single facility can be regulated under multiple programs; ECHO surfaces all.
| Status | Meaning |
|---|---|
| In compliance | No active violations |
| Significant Violator | Major program-level violation |
| High Priority Violator (HPV) | Air-program-specific severe non-compliance |
| Formal action issued | EPA or state has filed a legal action |
| Informal action | Warning letter, notice of violation |
| Active enforcement | An enforcement case is open |
For risk-tier assessment, "Significant Violator" + "Active enforcement" is High; clean record + closed historical violations is Low.
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"epa-echo": {
"url": "https://gateway.pipeworx.io/epa-echo/mcp"
}
}
}
tools/list at https://gateway.pipeworx.io/epa-echo/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 1476+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
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 Echo data" })
The gateway picks the right tool and fills the arguments automatically.
MIT