How do I connect an AI agent to RetailIntel — Indian retail moves?

Use the MCP streamable HTTP endpoint https://retailintel.in/mcp.

Catalog › in.retailintel/retailintel

Is RetailIntel — Indian retail moves reliable?

Flaky Partly. Faceabot measured RetailIntel — Indian retail moves 16 times and only 94% of checks succeeded. Plan a fallback. It also does the job: its real read-only task worked 15 of 15 times.

Last check: 2026-10-17 05:55 UTC · answered in 4811 ms · remote (no install)

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

What it does

What moved in Indian retail: store openings, deals, results, launches, leadership, each verified.

Source: official MCP registry (registry.modelcontextprotocol.io) · version 1.1.1 · publisher website

Connect your agent

{
  "mcpServers": {
    "retailintel": {
      "url": "https://retailintel.in/mcp"
    }
  }
}

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

Does it actually do the job?

Does the job (tested) — Faceabot asked daily_brief to do a small read-only task 15 time(s): 15 returned a real result, the last 15 in a row. Last result: ok in 3791 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
2026-10-17 05:55 UTC	❌ http_405		4811 ms
2026-10-16 22:10 UTC	✅ ok	✅ done	8085 ms
2026-10-16 15:01 UTC	✅ ok	✅ done	8743 ms
2026-10-16 08:01 UTC	✅ ok	✅ done	7639 ms
2026-10-16 01:05 UTC	✅ ok	✅ done	5423 ms
2026-10-15 18:06 UTC	✅ ok	✅ done	9604 ms
2026-10-15 11:21 UTC	✅ ok	✅ done	4137 ms
2026-10-15 04:45 UTC	✅ ok	✅ done	3316 ms
2026-10-14 22:15 UTC	✅ ok	✅ done	8557 ms
2026-10-14 15:45 UTC	✅ ok	✅ done	8246 ms
2026-10-14 09:15 UTC	✅ ok	✅ done	3856 ms
2026-10-14 02:32 UTC	✅ ok	✅ done	9839 ms
2026-10-13 20:15 UTC	✅ ok	✅ done	8986 ms
2026-10-13 14:10 UTC	✅ ok	✅ done	7253 ms
2026-10-13 08:05 UTC	✅ ok	✅ done	7281 ms
2026-10-13 02:01 UTC	✅ ok	✅ done	7918 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 RetailIntel — Indian retail moves?

Show your measured reliability on your README or website:

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

Data in JSON: /api/catalog?id=in.retailintel/retailintel · 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