Pbgc MCP Server

PBGC — pension plan terminations and premium filings

Whether a named pension plan was terminated and taken over by the federal pension insurer (trusteed), or is still an active plan currently paying its premiums — single-employer and multiemployer, from the regulator's own registers.

Part of Pipeworx — an MCP gateway connecting AI agents to 1837+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Why this exists alongside form5500

form5500 shows what a plan FILED with the Department of Labor each year — sponsor, participants, assets. It does not say what happened to the plan afterward. This pack answers that: did PBGC take it over because it terminated underfunded, or is it still active and paying premiums. The two registers (trusteed vs. premium-filer) are disjoint by construction — a plan is in exactly one of PBGC's own rosters, never both at once.

Tools

Auth

Keyless.

Data sources

• Pension Benefit Guaranty Corporation (PBGC), trusteed-plan register — single-employer pension plans PBGC has taken over as trustee because the plan terminated underfunded.
• Pension Benefit Guaranty Corporation (PBGC), premium-filer rosters — single-employer and multiemployer pension plans currently paying PBGC premiums (not terminated).

PBGC publishes these as periodically-updated open-government downloads rather than through a query API — its own plan-search page is server-rendered HTML with no JSON backend behind it. Routes live only in scripts/ingest-pbgc.mjs.

Why this is a mirror, and the replace semantics that matter

PBGC distributes each register as a complete current snapshot, not a delta — there is no "what changed since" feed. scripts/ingest-pbgc.mjs (scheduled weekly by .github/workflows/pbgc-refresh.yml) stamps every row it writes with that run's data_as_of and then deletes any row in the same table left over from a previous run. That matters specifically for premium filers: a plan that stops paying premiums (because it terminated, merged, or PBGC took it over) has to actually disappear from pbgc_search_premium_filers and pbgc_plan_status, not linger reading as still-active forever.

Every tool response carries data_as_of for exactly this reason — the two registers refresh on different clocks (the trusteed register roughly quarterly, the premium-filer rosters roughly monthly), so a caller comparing a plan's status across both should know which snapshot each half came from.

Schema

supabase/migrations/262_pbgc.sql — pbgc_trusteed_plans (one row per trusteed case; this table only grows, since PBGC's own register does) and pbgc_premium_filers (one row per currently-filing plan, plan_type + plan_id as the key, replaced wholesale on each refresh).

Scale (verified against the live source, 2026-10-17)

Quick Start

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

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

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/pbgc/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 1837+ 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/pbgc_plan_status \
  -H 'Content-Type: application/json' \
  -d '{"sponsor":"US Airways"}'

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

Or run it directly to confirm it starts:

npx -y @pipeworx/mcp-pbgc

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 Pbgc data" })

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

More

• Docs and guides
• pipeworx.io

License

MIT