How do I connect an AI agent to Japan Restaurant Calories?

Use the MCP streamable HTTP endpoint https://calories.omikuji.dev/mcp.

Catalog › dev.omikuji/calories

Is Japan Restaurant Calories reliable?

Reliable (measured) Yes. Faceabot measured Japan Restaurant Calories 13 times: 100% of checks succeeded, including the last 13 in a row (last check 2026-10-19 13:20 UTC). It also does the job: its real read-only task worked 13 of 13 times.

Last check: 2026-10-19 13:20 UTC · answered in 8038 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

Nutrition facts for 24,000+ menu items of 100+ Japanese restaurant chains, with sources.

Source: official MCP registry (registry.modelcontextprotocol.io) · version 1.0.0 · publisher website

Connect your agent

{
  "mcpServers": {
    "calories": {
      "url": "https://calories.omikuji.dev/mcp"
    }
  }
}

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

Does it actually do the job?

Does the job (tested) — Faceabot asked list_chains to do a small read-only task 13 time(s): 13 returned a real result, the last 13 in a row. Last result: ok in 1438 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 13:20 UTC	✅ ok	✅ done	8038 ms
2026-10-18 21:30 UTC	✅ ok	✅ done	5691 ms
2026-10-18 07:45 UTC	✅ ok	✅ done	7096 ms
2026-10-18 00:00 UTC	✅ ok	✅ done	5472 ms
2026-10-17 15:50 UTC	✅ ok	✅ done	5830 ms
2026-10-17 07:45 UTC	✅ ok	✅ done	6873 ms
2026-10-16 23:50 UTC	✅ ok	✅ done	5274 ms
2026-10-16 16:40 UTC	✅ ok	✅ done	6889 ms
2026-10-16 09:40 UTC	✅ ok	✅ done	7220 ms
2026-10-16 02:45 UTC	✅ ok	✅ done	7610 ms
2026-10-15 19:50 UTC	✅ ok	✅ done	7400 ms
2026-10-15 13:06 UTC	✅ ok	✅ done	5572 ms
2026-10-15 06:30 UTC	✅ ok	✅ done	4510 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.

More from the same publisher

Traditional Colors Reliable (measured) · 100% over 13 checks Fails real tasks · 0/13

Traditional color names (Japanese and 10 more cultures) with hex/RGB and sources; name a hex.

MCP endpoint : https://color.omikuji.dev/mcp · website · measurements and details

Japan & World Public Holidays Reliable (measured) · 100% over 13 checks Does the job (tested) · 13/13

Public holidays, business days and long weekends for Japan (Cabinet Office) and 245 other countries.

MCP endpoint : https://holiday.omikuji.dev/mcp · website · measurements and details

Shiritori Dictionary (Japanese) Reliable (measured) · 100% over 13 checks Fails real tasks · 0/13

Play Japanese shiritori with a 90,000-word dictionary: check moves, suggest next words.

MCP endpoint : https://shiritori.omikuji.dev/mcp · website · measurements and details

Publisher of Japan Restaurant Calories?

Show your measured reliability on your README or website:

[![Measured by Faceabot](https://faceabot.com/badge/dev.omikuji/calories.svg)](https://faceabot.com/tools/dev.omikuji/calories)

Data in JSON: /api/catalog?id=dev.omikuji/calories · 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