How do I connect an AI agent to askTender?

Use the MCP streamable HTTP endpoint https://asktender.org/mcp.

Catalog › org.asktender/asktender

Is askTender reliable?

Reliable (measured) Yes. Faceabot measured askTender 17 times: 100% of checks succeeded, including the last 17 in a row (last check 2026-10-19 16:05 UTC). It also does the job: its real read-only task worked 16 of 17 times.

Last check: 2026-10-19 16:05 UTC · answered in 9656 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

Government tenders in about 200 countries: who can bid, what each requires, and the bid kit.

Source: official MCP registry (registry.modelcontextprotocol.io) · version 1.0.7 · publisher website

Connect your agent

{
  "mcpServers": {
    "asktender": {
      "url": "https://asktender.org/mcp"
    }
  }
}

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

Does it actually do the job?

Does the job (tested) — Faceabot asked compare_plans to do a small read-only task 17 time(s): 16 returned a real result, the last 4 in a row. Last result: ok in 2565 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 16:05 UTC	✅ ok	✅ done	9656 ms
2026-10-19 01:20 UTC	✅ ok	✅ done	5120 ms
2026-10-18 09:55 UTC	✅ ok	✅ done	7690 ms
2026-10-18 01:50 UTC	✅ ok	✅ done	4995 ms
2026-10-17 17:40 UTC	✅ ok	❌ http_502	7799 ms
2026-10-17 09:35 UTC	✅ ok	✅ done	6235 ms
2026-10-17 01:40 UTC	✅ ok	✅ done	5745 ms
2026-10-16 18:25 UTC	✅ ok	✅ done	6029 ms
2026-10-16 11:21 UTC	✅ ok	✅ done	7316 ms
2026-10-16 04:25 UTC	✅ ok	✅ done	7886 ms
2026-10-15 21:35 UTC	✅ ok	✅ done	5421 ms
2026-10-15 14:41 UTC	✅ ok	✅ done	4783 ms
2026-10-15 08:00 UTC	✅ ok	✅ done	4347 ms
2026-10-15 01:25 UTC	✅ ok	✅ done	3503 ms
2026-10-14 19:00 UTC	✅ ok	✅ done	5528 ms
2026-10-14 12:25 UTC	✅ ok	✅ done	5207 ms
2026-10-14 06:01 UTC	✅ ok	✅ done	9898 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.

Find tools similar to askTender →

Publisher of askTender?

Show your measured reliability on your README or website:

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

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