Tender MCP

io.github.OjasKord由 GitHub 账号 OjasKord 发布v1.2.25更新于 Oct 25, 2026

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

已验证Streamable HTTP可网页运行网页搜索与抓取商业与电商

概览

AI 生成的概览

搜索英国、欧盟和美国的政府招标,并返回中标历史和每日摘要,帮助助手发现采购机会以支持投标决策。

可以做什么
跨英国 Contracts Finder、欧盟 TED 和美国 SAM.gov 搜索在招政府招标,返回含来源链接和核查时间的规范化结果,可按关键词、来源和天数筛选。获取招标情报,包括中标历史和每日新机会摘要。README 还列出招标详情、按公司能力画像进行 AI 匹配评分,以及仅限付费的摘要和中标历史工具,但仅声明了搜索和情报两个工具。
适用场景
适合助手协助面向政府销售的企业发现和筛选采购机会,或在决定是否投标前需要了解该领域中标历史时使用。
运行要求
使用给定的 Railway 远程端点,或通过 stdio 运行 npm 包 tender-mcp。免费套餐无需 API 密钥;ANTHROPIC_API_KEY 环境变量被声明为 AI 招标评分所需的密钥。需要能访问该服务器及其查询的政府门户。
安装前请注意
声明的 ANTHROPIC_API_KEY 密钥用于 AI 评分,应视为敏感信息。更高搜索量需购买付费套餐,README 中部分工具标注为仅限付费。结果仅供参考,README 建议投标前直接向采购机构核实截止日期和详情。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Tender MCP,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Web executable,通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体,或 SourceWeft 对话中。智能体会读取该服务器的安装指南,先向你展示发布者、端点和登录方式,经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/io.github.OjasKord%2Ftender-mcp/install.md,并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前,先告诉我它的发布者、端点和登录方式,等我确认。不要把 API 密钥写进命令或我会提交的文件;问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "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

来源:README.md,提交 85f1266

工具

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.

输入参数limitkeyword必填sourcesdays_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.

输入参数mode必填limitkeywordsourceskeywords

版本历史

1
  1. v1.2.25最新Sep 16, 2026

评分

已满足适用检查项的 100%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分