Tender MCP

io.github.OjasKordPublished by GitHub account OjasKordv1.2.25Updated Oct 25, 2026

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

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingBusiness & Commerce

Overview

AI-generated overview

Searches UK, EU and US government tenders and returns award history and daily digests, so an assistant can surface procurement opportunities for bid decisions.

What you can do
Search active government tenders across UK Contracts Finder, EU TED and US SAM.gov, with normalised results including source URL and check time, filtered by keyword, source and age in days. Retrieve tender intelligence such as award history and a daily digest of new opportunities. The README also lists tender detail, AI fit scoring against a company profile, and paid-only digest and award-history tools, but only search and intelligence tools are declared.
When to use it
Useful when an assistant helps a business that sells to government find and triage procurement opportunities, or when a bid/no-bid decision needs sector award history before committing proposal resources.
Requirements
A remote endpoint at the given Railway URL, or the npm package tender-mcp over stdio. The free tier needs no API key; the ANTHROPIC_API_KEY environment variable is declared as a required secret for AI-powered tender scoring. Network access to the server and the government portals it queries.
Before you install
The declared ANTHROPIC_API_KEY secret is passed for AI scoring, so treat it as sensitive. Paid bundles are sold for higher search volumes, and some README tools are marked paid only. Results are informational; the README advises verifying deadlines and details with the contracting authority before bidding.

Installation

In SourceWeft

  1. Open Tender MCP in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.OjasKord%2Ftender-mcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "tender": {
      "type": "http",
      "url": "https://tender-mcp-production.up.railway.app/"
    }
  }
}

README

[smithery badge]

Tender MCP — Government Opportunity Intelligence for AI Agents

[ToolRank]

Find, score, and monitor government contract opportunities across UK, EU, and US. AI-powered relevance scoring so your agent surfaces the right opportunities — not just keyword matches.

Free tier: 10 searches/month. No API key required. Just connect and go.

Quick Start

json
{  "tender": {    "url": "https://tender-mcp-production.up.railway.app"  }}

Or via Smithery:

bash
npx -y @smithery/cli@latest mcp add OjasKord/tender-mcp

Harness Integration

Claude Code / Claude Desktop (.mcp.json)

json
{  "mcpServers": {    "tender": {      "type": "http",      "url": "https://tender-mcp-production.up.railway.app"    }  }}

LangChain (Python)

python
from langchain_mcp_adapters.client import MultiServerMCPClientclient = MultiServerMCPClient({    "tender": {        "url": "https://tender-mcp-production.up.railway.app",        "transport": "http"    }})tools = await client.get_tools()

OpenAI Agents SDK (Python)

python
from agents import Agent, HostedMCPToolagent = Agent(    name="Assistant",    tools=[HostedMCPTool(tool_config={        "type": "mcp",        "server_label": "tender",        "server_url": "https://tender-mcp-production.up.railway.app",        "require_approval": "never"    })])

LangGraph

Same as LangChain above — langchain-mcp-adapters works with LangGraph natively.

Why Use This

Any business that sells to government needs to monitor tender opportunities. But searching three separate government portals daily, reading hundreds of notices, and manually judging relevance takes hours. Tender MCP does it in seconds — search UK, EU, and US simultaneously, then let AI score which opportunities actually match your capabilities.

Tools

search_tenders

Search active government tenders across UK Contracts Finder, EU TED, and US SAM.gov simultaneously. Returns normalised results with source_url and checked_at.

json
{ "keyword": "cybersecurity", "sources": ["uk", "eu"], "days_old": 14 }

get_tender_detail

Full details for a specific tender — complete description, all deadlines, contact details, award criteria.

json
{ "tender_id": "ocds-h6vhtk-...", "source": "uk" }

score_tender_fit (AI-powered — NOT a keyword match)

AI scores each tender 0-100 against a company capability profile. Returns BID/INVESTIGATE/SKIP recommendation with specific reasons. Saves hours of manual review.

json
{  "tenders": [...],  "company_profile": "We are a 50-person UK cybersecurity firm specialising in penetration testing and SOC services for public sector clients. We hold SC clearance.",  "min_score": 60}

get_daily_digest (Paid only)

All new tenders published in the last 24 hours matching your keywords. Run daily as a morning briefing.

json
{ "keywords": ["cybersecurity", "managed SOC", "penetration testing"] }

get_award_history (Paid only)

Past award winners for a keyword. Use for competitive intelligence before bidding.

json
{ "keyword": "cybersecurity", "sources": ["uk"] }

Recommended Workflow

Find and score opportunities (3 calls):

  1. search_tenders — find active tenders matching your sector
  2. score_tender_fit — AI ranks by relevance, filters noise
  3. get_tender_detail — full details on top matches

Daily monitoring (1 call):

  • get_daily_digest — new tenders every morning before competitors see them

Data Sources

SourceCoverageUpdate Frequency
UK Contracts Finder (contractsfinder.service.gov.uk)All UK public sector contractsReal-time
EU TED (ted.europa.eu)All EU member state procurementReal-time
US SAM.gov (sam.gov)All US federal opportunitiesDaily

Every response includes source_url and checked_at.

Pricing

PlanSearchesPrice
Free10/monthNo API key required
Starter500-call bundle$8
Pro2,000-call bundle$28

Upgrade at kordagencies.com

Reliability

  • Uptime monitored every 5 minutes
  • Version history in CHANGELOG.md
  • Health endpoint: GET /health
  • Note: Government portal APIs experience occasional downtime — errors include explanation and retry guidance

Legal

Tender data sourced directly from official government portals. We do not log or store your query content. Always verify tender deadlines and details directly with the contracting authority before submitting a bid — deadlines change. Results are for informational purposes only. Maximum liability limited to 3 months subscription fees. Full terms: kordagencies.com/terms.html

Connect

Source: README.md at commit 85f1266

Tools

2

search_tenders

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.

Parameterslimitkeywordrequiredsourcesdays_oldmin_scorecompany_profile

get_tender_intelligence

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.

Parametersmoderequiredlimitkeywordsourceskeywords

Version history

1
  1. v1.2.25LatestSep 16, 2026

Score

100% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts