Epoch Ai Models MCP server

@pipeworx/epoch-ai-models

AI model facts — organization, release date, parameter count, training-compute (FLOP) estimate, hardware, accessibility — looked up by name, searched by organization/domain/year/compute threshold, or aggregated into a yearly training-compute trend.

Part of Pipeworx — an MCP gateway connecting AI agents to 1800+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

training-compute estimate, hardware and accessibility. Resolves dated variants (a query for "GPT-4" matches the dataset's "GPT-4 (Mar 2023)" row). An unmatched name returns found:false with the closest names in the dataset, never an empty result.

• ai_model(name) — one model's organization, release date, parameter count,

— filter the dataset by organization, domain (e.g. "Language", "Vision"), publication year, and/or a minimum training-compute (FLOP) threshold. Newest-first, capped at limit (default 50, max 200) with count_matching/truncated so a large match set is never silently cut.

• aimodelssearch(organization?, domain?, year?, min_compute?, query?, limit?, offset?)

compute estimate and the largest training run (FLOP) that year, optionally filtered by domain and a starting year.

• aicomputetrend(domain?, from_year?) — per-year count of models with a

Auth

Keyless.

Data sources

learning models and their organization, release date, parameters, training compute, hardware and accessibility.

• Epoch AI, "Data on AI models" — Epoch AI's dataset of notable machine

Licence: Epoch AI publishes this data under CC BY — "free to use, distribute, and reproduce provided the source and authors are credited under the Creative Commons Attribution license." Every tool response carries that attribution plus dataasof (when this isolate last pulled the dataset from Epoch AI).

Notes

"GPT-4 (Mar 2023)", "GPT-4 Turbo (Nov 2023)"). ai_model strips that qualifier to resolve a bare "GPT-4"-style query to the canonical release; when more than one dated variant shares a base name, it picks the earliest one that carries a training-compute estimate.

• Epoch AI names dated variants with a trailing parenthetical (e.g.

Organization categorization are comma-separated multi-value columns upstream (a model can list more than one organization or domain); every tool returns these as arrays and filters by substring/membership rather than exact string equality.

• Organization, Country (of organization), Domain and

entries are notable for other reasons (benchmark results, accessibility) and leave those fields blank upstream. aimodelssearch's mincompute filter and aicompute_trend both treat a blank estimate as "excluded," not zero.

• Not every row carries a training-compute or parameter estimate — many

Quick Start

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

{
  "mcpServers": {
    "epoch-ai-models": {
      "url": "https://gateway.pipeworx.io/epoch-ai-models/mcp"
    }
  }
}

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/epoch-ai-models/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — askpipeworx, discovertools, 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.

Shortened. The full README is on GitHub.