Skip to content

Tender MCP

by OjasKord · remote · local (npm) · no sign-in to list tools · v1.2.25 · published by GitHub user OjasKord

Government tender search for AI agents. UK, EU and US procurement opportunities.

Final · 1
CompareRegistry entry

2 tools: 1 do something that can't be undone and 1 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http tender https://tender-mcp-production.up.railway.app

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

2 tools

Can't be undone 1Claude Code: ask
  • search_tendersSearches active government tenders across UK, EU, and US.No findings

    Why it is in this group

    • The name "search_tenders" says "search": a word for reading.
    • The description says "cannot be recovered".
    Description, as the server wrote it
    Searches active government tenders across UK, EU, and US. Call this BEFORE your agent allocates proposal resources, drafts a bid response, or routes a procurement opportunity to a human team — at the moment a keyword or sector is known and no bid decision has been made. Use this when your agent is starting a procurement discovery run and needs to know which live tenders match the company capabilities before committing any resources to a bid. Returns BID/INVESTIGATE/SKIP verdict with AI fit score 0-100, deadline, estimated value, and key requirements from UK Contracts Finder, EU TED, and US SAM.gov simultaneously. A missed tender deadline cannot be recovered. An agent that drafts a bid without checking active opportunities wastes resources on closed or mismatched contracts. Call get_tender_intelligence with mode=AWARD_HISTORY next for any tender scored BID or INVESTIGATE, before committing proposal resources to a bid.
Only reads 1Claude Code: allow
  • get_tender_intelligenceRetrieves tender intelligence including award history and daily digest.No findings

    Why it is in this group

    • The name "get_tender_intelligence" says "get": a word for reading.
    Description, as the server wrote it
    Retrieves tender intelligence including award history and daily digest. Call this BEFORE your agent bids on any contract without knowing who dominates the sector — at the moment a specific opportunity has been identified and bid/no-bid decision is pending. Use this when your agent has identified a specific tender and needs competitive context — either the history of who has won similar contracts or new opportunities since yesterday. AWARD_HISTORY: past contract winners for a keyword. DAILY_DIGEST: all new tenders last 24h for monitored keywords. Submitting a bid without AWARD_HISTORY leaves your price uninformed by what similar contracts actually paid — a mispriced bid cannot be revised after the tender submission deadline passes. Do not bid without running AWARD_HISTORY first.

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 1.2.25. Values in angle brackets are yours to fill in.

claude mcp add --transport http tender https://tender-mcp-production.up.railway.app

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__tender__get_tender_intelligence"
    ],
    "ask": [
      "mcp__tender__search_tenders"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as tender. Review it before you use it.