mcpField
D
Dol M1

Dol M1

Remote
pipeworx.ioLegal & Government0Updated 4d ago

About Dol M1

An MCP server for U.S. Department of Labor Form M-1 filings by MEWAs and association health plans. It supports benefits researchers and compliance analysts with filing searches across several criteria and complete filing histories for a filer.

Key features

  1. 01Search by plan year and filer
  2. 02Filter by EIN, headquarters, and coverage state
  3. 03Filter by filing type and insurance status
  4. 04Retrieve a filer's complete filing history

Use cases

  1. 01Research MEWA and AHP filings
  2. 02Find plans offering coverage in a state
  3. 03Check a filer's records across years

MCP support

Provides Form M-1 filing search and filer-history tools to MCP clients through Pipeworx or local stdio.

Configuration

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

Endpointhttps://gateway.pipeworx.io/dol-m1/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

@pipeworx/dol-m1 — Form M-1 (MEWA/AHP) filings

U.S. Department of Labor Form M-1 filings — the federal report filed by multiple employer welfare arrangements (MEWAs) and association health plans (AHPs) that pool health coverage across unrelated employers. form5500 already covers annual plan/pension financial returns, and ebsa covers EBSA's own civil-penalty enforcement record against deficient Form 5500 filers — this is a third, unrelated filer population and form.

Part of Pipeworx — an MCP gateway connecting AI agents to 1878+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

ToolAnswers
dol_m1_searchSearch filings by plan year, MEWA/sponsor name, EIN, headquarters state, state(s) where coverage is offered, filing type, stop-loss, fully-insured
dol_m1_filerFull filing history (every plan year filed) for one named MEWA/sponsor or EIN

Auth

Keyless. No login, no API key, no approval step.

Data sources

  • U.S. Department of Labor, Employee Benefits Security Administration — Form M-1 Filings Database. 17,313 filings live as of 2026-10-18, plan years 2003-2025.

Gotchas

  • Reverse-engineered, not documented. This is a public search tool, not a published REST API — the endpoint shape came from the search page's own bundled JavaScript (m1search.build_url), not from any API docs. It is still a plain, publicly reachable GET with no auth; nothing here needs a browser or a session.
  • The dropdown filters do not accept an empty string the way a free-text field does. Plan year and filing type default to "ALL", and the stop-loss/fully-insured flags default to "0" ("Any") in the real form. Sending "" for any of those four throws an unhandled server exception — the endpoint answers HTTP 500 with a full HTML error page, not a structured error. This pack always sends the correct default.
  • Headquarters state and coverage state are different facets, not aliases. hq_state filters where the MEWA is based; coverage_state filters where it offers coverage — a MEWA headquartered in New Jersey can show up filtered by coverage_state: "NY" with hq_state: "NJ" on its own row. Verified live.
  • limit has an undocumented cap of 100, and it does not clamp or error past that — it silently resets to a 25-row default. Measured live: limit=100 returns 100 rows, limit=101 returns 25. This pack clamps its own limit argument to 1-100 before calling, so a caller's limit: 500 cannot trigger the silent fallback.
  • A zero-match query is a clean HTTP 200 with {"total":0,"rows":[]} — not an error. This pack turns that into { found: false, reason: "no_matching_filings", filters_applied: {...} } rather than passing through a bare [].
  • The FilingType field on each returned row does not reliably reflect the filing_type request filter — every row observed across every filing-type query (Amended, Extension, Regular Filing, Registration) came back FilingType: 0. The request-side filter itself works (verified live: filtering narrows the total count correctly per type); only the echoed field is unreliable, so it is left out of the shaped output.
  • The administrator/sponsor name can be an individual, not a business. For small MEWAs the Form M-1 administrator of record is sometimes a natural person's own name — this is the DOL's own mandatory public-filing field, passed through exactly as the federal filing discloses it, the same way form5500 and ebsa already pass through their own sponsor fields.

Quick Start

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

{
  "mcpServers": {
    "dol-m1": {
      "url": "https://gateway.pipeworx.io/dol-m1/mcp"
    }
  }
}
What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/dol-m1/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 1878+ 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/dol_m1_search \
  -H 'Content-Type: application/json' \
  -d '{"hq_state":"TX","plan_year":2024,"limit":5}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/dol_m1_search. 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": {
    "dol-m1": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-dol-m1"]
    }
  }
}

Or run it directly to confirm it starts:

npx -y @pipeworx/mcp-dol-m1

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 Dol M1 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.