New:Microsoft Teams Notifications Are Now Available in Socket.Learn more
Get Started

@aimodelwatch/mcp

Package Overview
Dependencies
Maintainers
1
Versions
3
Alerts
File Explorer

Advanced tools

Socket logo

Install Socket

Detect and block malicious and high-risk dependencies

Install

@aimodelwatch/mcp

MCP server for AI Model Watch — prices, context windows, lifecycle status and deprecation dates for 270+ AI/LLM models, from official provider pages, refreshed daily. Read-only, no key.

latest
Source
npmnpm
Version
2.0.1
Version published
Weekly downloads
4
-33.33%
Maintainers
1
Weekly downloads
 
Created
Source

@aimodelwatch/mcp

MCP server for AI Model Watch: prices per 1M tokens, context windows, lifecycle status and provider-declared retirement dates for 270+ AI/LLM models across 12 providers, compiled daily from official provider pages. Read-only, no key, no signup.

It is a thin client over the public feed (/api/models.json, /api/deprecations.json), cached in memory for 15 minutes. A null field means the provider does not publish that value — never a guess. Every row carries the source_url it was read from.

Install

Run on demand (nothing to install):

npx -y @aimodelwatch/mcp

Claude Code

claude mcp add aimodelwatch -- npx -y @aimodelwatch/mcp

Claude Desktop / Cursor / Windsurf / any MCP client

Add to claude_desktop_config.json, .cursor/mcp.json, or your client's MCP config:

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

Transport is stdio. Requires Node.js 20+.

Tools

All tools are read-only and return JSON (as text and as structuredContent, with a published outputSchema). Field names are exactly those of the feed — see the API reference and the OpenAPI spec.

ToolWhat it doesArguments
list_modelsFiltered, paginated summary rowsprovider, status (ga/preview/beta/deprecated/retired, or active = the first three), open_weight, modality, query (id/name/api_string), limit (≤500, default 100), offset
get_modelFull row for one model, incl. notes and source_url; on a miss returns found: false + similar idsid (id or api_string, case-insensitive)
search_modelsFree-text search that also looks inside notes (batch prices, cache tiers, hosting)query, limit
compare_modelsSide-by-side rows plus blended priceids (2–6)
cheapest_modelsN cheapest by blended price (mean of input/output)count, modality, status (default active), provider
check_model_statusIs this id safe to pin? Lifecycle, dates, days to retirement, stated replacement (with its row)id
list_deprecationsEvery provider-declared deprecation/retirement, upcoming or past relative to as_ofprovider, when, after, before, as_of, limit, offset
models_changed_sinceLifecycle events (released / deprecated / retired) dated on or after a date, newest first; future-dated retirements (retires) only with include_scheduledsince, provider, include_scheduled, limit
feed_freshnessThe catalog's updated date, its age in days, counts, providers, feed URLs and this server's cache state

models_changed_since is built from the dated fields on each row; the feed has no per-field modification timestamps, so price changes are not visible there — check updated and the changelog.

Resources

URIContent
aimodelwatch://modelsThe full /api/models.json feed, verbatim (application/json)
aimodelwatch://deprecationsThe full /api/deprecations.json feed, verbatim

Examples

Ask your agent:

  • "Is gpt-4o still safe to pin? What replaces it?"
  • "Cheapest GA model with vision under $1 per 1M tokens"
  • "What Anthropic models were released or deprecated since September 1st?"
  • "Which models retire in the next 90 days?"
  • "How old is the AI Model Watch data right now?"

Attribution and User-Agent

The data is MIT-licensed and free to use; attribution ("Data by AI Model Watch — https://aimodelwatch.dev") is appreciated. This server identifies itself to the feed as aimodelwatch-mcp/<version> (+https://aimodelwatch.dev). If you build something else on the feed, please send an identifiable User-Agent too — the project's only success metric is distinct machine consumers, and an anonymous UA is invisible to it.

Development

cd mcp-server
npm install        # also builds dist/ (prepare)
npm test           # unit + in-process MCP round-trip tests against a fixture snapshot of the feed
npm run smoke      # spawns dist/index.js over stdio and calls the LIVE feed (needs network)

Tests run with node --test on Node 22.18+/24 (native TypeScript type stripping). The fixture in test/fixtures/ is a verbatim snapshot of the live feed; refresh it when the schema changes.

server.json is the MCP Registry manifest; mcpName in package.json is the registry's npm ownership check. Publishing (npm and registry) is a maintainer action: npm publish --access public, then mcp-publisher login github and mcp-publisher publish.

License

MIT

Keywords

mcp

FAQs

Package last updated on 20 Sep 2026

Related posts