@pipeworx/openpowerlifting

Powerlifting competition results from the OpenPowerlifting project -- a lifter's meet-by-meet history, the full results of a meet, and all-time top lifts by sex, equipment and weight class. About 4 million lifter entries across about 64,000 meets, worldwide.

Part of Pipeworx — an MCP gateway connecting AI agents to 1856+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

• opl_lifter_history(name, equipment?, limit?, offset?) -- every meet a lifter entered (most recent first) with federation, division, bodyweight, weight class, best squat / bench / deadlift, total, place and Dots / Wilks / Goodlift points, plus career bests. Same-named lifters are numbered in the data ("John Smith #2"); an ambiguous name returns the candidates rather than mixing them.

• opl_meet_results(meet_id | meet [+ federation, year], sex?, equipment?, weight_class?, division?, limit?, offset?) -- the lifters of one meet ordered by sex, equipment, division, weight class and place. A name matching several meets returns the candidate list.

• opl_records(sex, equipment?, lift?, weight_class?, federation?, age_class?, tested?, year?, event?, limit?) -- top performances by total, squat, bench, deadlift or Dots, one row per lifter (their best qualifying entry). These are the best entries in the data under the filters given, not an official federation record list.

All weights are kilograms. Every response carries source, licence and data_as_of (the release date of the loaded file).

Related MCP server: hevy-mcp-server

Auth

Keyless.

Data sources

• OpenPowerlifting (openpowerlifting.org), powerlifting meet results database.

Licence. The project dedicates the data to the public domain and waives all copyright and related rights in it; attribution is requested but not required. The results are public competition records published by the project itself.

What is in the copy, and what is not.

• The best-of-three lifts, total, place, points and the meet/lifter descriptors are kept. The individual attempts (squat 1-4, bench 1-4, deadlift 1-4, with their made/missed marks) are not.

• The file is a snapshot: new meets appear on the next reload, and the project corrects old entries over time. data_as_of is the release date of the loaded file; latest_meet_date is the newest meet in it.

• Same-name lifters. The project numbers lifters it knows share a name ("John Smith #2"), but it cannot always tell two people apart; an un-numbered name can still mix more than one person's results, so check the federations and years in career before treating a history as one person.

• place is text: a number, or DQ (disqualified), G (guest), NS (no-show), DD (doping disqualification).

• Equipment categories are the federation's category, not necessarily what the lifter wore. tested is whether the federation drug-tests.

• Total is only populated when the lifter completed all the lifts of the event; opl_records ranks total over full three-lift (SBD) entries by default.

• Weight classes are strings as recorded (83, 84+); a super-heavy class is the + form.

Updating the data

OpenPowerlifting regenerates the file daily. Reload with (needs wrangler logged in to the Pipeworx Cloudflare account):

node scripts/openpowerlifting/load-data.mjs

The loader DROPs and reloads the tables, verifies row counts against what it generated and exits non-zero on a mismatch.

Quick Start

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

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

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/openpowerlifting/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 1856+ 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/opl_lifter_history \
  -H 'Content-Type: application/json' \
  -d '{"name":"Ed Coan","limit":5}'

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

Run it from npm

@pipeworx/mcp-openpowerlifting is a local stdio bridge to the Pipeworx gateway: your MCP client starts it with npx, and it forwards every call to the same https://gateway.pipeworx.io/openpowerlifting/mcp endpoint shown above. It needs network access; there is no offline mode.

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

Without a key it calls anonymously, capped at 50 calls a day. A free account raises that to 200 a day: get a key at https://pipeworx.io/signup and add "env": { "PIPEWORX_API_KEY": "<your key>" } to the server entry. The key is sent as a Bearer token, the same way a hosted connection sends it, so calls are metered and billed exactly as they are there.

It lists only this pack's tools by default. Set PIPEWORX_META_TOOLS=1 to also list ask_pipeworx and the other gateway-wide tools.

Behind an HTTPS proxy: Node's built-in fetch does not read HTTPS_PROXY by default. Newer Node releases honour it when NODE_USE_ENV_PROXY=1 is set; check your Node version's documentation.

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 Openpowerlifting data" })

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

More

• Docs and guides

• pipeworx.io

License

MIT