epoch-ai-models 3 tools

MCP server exposing 3 tools for epoch-ai-models.

Endpoint

This URL is a JSON-RPC 2.0 endpoint over HTTP. Issue POST requests with a JSON-RPC body. Browsers and search crawlers land here on GET.

POST https://gateway.pipeworx.io/epoch-ai-models/mcp
Content-Type: application/json

{"jsonrpc":"2.0","id":1,"method":"tools/list"}

ai_model — Look up one AI model in Epoch AI's models database by name — organization, release date, parameter count, training-compute (FLOP) estimate, hardware, accessibility. Resolves dated variants (e.g. "GPT-4" matches Epoch AI's "GPT-4 (Mar 2023)" row). An unmatched name returns found:false with the closest names in the dataset, never an empty result.
ai_models_search — Search/filter Epoch AI's models database by organization, domain (e.g. "Language", "Vision", "Multimodal"), publication year, and/or a minimum training-compute (FLOP) threshold. Returns newest-first, capped at `limit` (default 50) with count/truncated so a large match set is never silently cut.
ai_compute_trend — Yearly training-compute trend from Epoch AI's models database: for each year, the number of models with a compute estimate, the largest training run (FLOP) that year, and which model set it. Optionally filtered by domain and a starting year.

Code samples (curl / TypeScript / one-click client install), schemas, and the live playground are on the pack page:
https://pipeworx.io/packs/epoch-ai-models/

Pipeworx is an open MCP gateway connecting AI agents to live data. pipeworx.io