`ai_models_search`

Pack: epoch-ai-models · Connect: https://pipeworx.io/mcp (see Connect below for a single-pack URL)

No MCP client? Call it directly: GET https://gateway.pipeworx.io/v1/tools/ai_models_search for the schema, then POST the same URL with its arguments for the data.

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.

Parameters

Name	Type	Required	Description
`organization`	string	no	Case-insensitive substring filter on organization name, e.g. “OpenAI”
`domain`	string	no	Case-insensitive substring filter on domain, e.g. “Language”, “Vision”, “Speech”
`year`	number	no	Restrict to models published in this calendar year
`min_compute`	number	no	Minimum training compute in FLOP, e.g. 1e25
`query`	string	no	Case-insensitive substring filter on model name
`limit`	number	no	Max rows to return, default 50, max 200
`offset`	number	no	Row offset for paging, default 0

Example call

Arguments

{
  "organization": "OpenAI",
  "limit": 5
}

curl

curl -X POST https://gateway.pipeworx.io/epoch-ai-models/mcp \
  -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"ai_models_search","arguments":{"organization":"OpenAI","limit":5}}}'

TypeScript (@pipeworx/sdk)

import { Pipeworx } from '@pipeworx/sdk';
const pipeworx = new Pipeworx();

const result = await pipeworx.call('ai_models_search', {
  "organization": "OpenAI",
  "limit": 5
});

Connect

Add this to your MCP client config — every tool in the catalog, including this one — or use one-click install buttons:

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

Connect to just the epoch-ai-models pack

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

See Getting Started for client-specific install steps.

ai_models_search