How do I connect an AI agent to Context Window Supply?

Use the MCP streamable HTTP endpoint https://contextwindowsupply.com/mcp.

Catalog › com.contextwindowsupply/store

Is Context Window Supply reliable?

Reliable (measured) Yes. Faceabot measured Context Window Supply 12 times: 100% of checks succeeded, including the last 12 in a row (last check 2026-10-19 19:50 UTC). It also does the job: its real read-only task worked 12 of 12 times.

Last check: 2026-10-19 19:50 UTC · answered in 7145 ms · remote (no install)

En français : Fiable (mesuré). Faceabot teste cet outil lui-même, en continu, sans dépendre de ce que son auteur affirme.

What it does

Browse merch for AI builders, get US shipping quotes, and create Stripe checkout links.

Source: official MCP registry (registry.modelcontextprotocol.io) · version 1.0.1 · publisher website

Connect your agent

{
  "mcpServers": {
    "store": {
      "url": "https://contextwindowsupply.com/mcp"
    }
  }
}

Or ask Faceabot first: MCP tool check_reliability {"id":"com.contextwindowsupply/store"} on https://faceabot.com/api/mcp.

Does it actually do the job?

Does the job (tested) — Faceabot asked search_products to do a small read-only task 12 time(s): 12 returned a real result, the last 12 in a row. Last result: ok in 3562 ms.

Sample input: {}. A success means a non-empty result without error; it does not certify the accuracy or safety of the content.

Faceabot measurements

When	Answers	Real task	Latency
2026-10-19 19:50 UTC	✅ ok	✅ done	7145 ms
2026-10-19 06:31 UTC	✅ ok	✅ done	9195 ms
2026-10-18 14:05 UTC	✅ ok	✅ done	8724 ms
2026-10-18 03:55 UTC	✅ ok	✅ done	6731 ms
2026-10-17 19:55 UTC	✅ ok	✅ done	6145 ms
2026-10-17 11:30 UTC	✅ ok	✅ done	7247 ms
2026-10-17 03:45 UTC	✅ ok	✅ done	8108 ms
2026-10-16 20:05 UTC	✅ ok	✅ done	7532 ms
2026-10-16 12:55 UTC	✅ ok	✅ done	6988 ms
2026-10-16 05:55 UTC	✅ ok	✅ done	5501 ms
2026-10-15 23:00 UTC	✅ ok	✅ done	7245 ms
2026-10-15 16:02 UTC	✅ ok	✅ done	9384 ms

Method: MCP initialize then tools/list from Faceabot (FaceabotProbe/1.0), plus one read-only tool call with a neutral input when the server declares one, repeated over time. This checks that the server is up and speaks MCP correctly; it does not certify the quality or safety of each tool. How measurement works.

Publisher of Context Window Supply?

Show your measured reliability on your README or website:

[![Measured by Faceabot](https://faceabot.com/badge/com.contextwindowsupply/store.svg)](https://faceabot.com/tools/com.contextwindowsupply/store)

Data in JSON: /api/catalog?id=com.contextwindowsupply/store · Stop probes: POST /api/reliability/opt-out

AI agents: all of this is available without keys over MCP https://faceabot.com/api/mcp · HTTP https://faceabot.com/api/catalog?q=… · Guide : llms.txt

Best tool by topic · Pulse: what is changing in agent commerce · Is your store ready for AI shopping agents? · State of MCP (weekly) · MCP server doctor · Reliability data · Faceabot app · Faceabot → AI assistants · What AI agents cannot find yet · Add Faceabot to your AI · Badge for tool publishers · Help · Privacy · Terms