Tender MCP

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

我该使用它吗

质量与安全性

A
描述质量
100%
模式完整度
100%
命名质量
100%
投毒风险
100%
权限匹配度
100%
协议合规性
100%

基于对工具定义和协议合规性的自动分析。

上下文开销

~1,138token 数(工具定义)
~4.9 KB典型响应大小
对注意力有中等影响(占 128k 上下文窗口的 0.89%)

这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高,可用于其他任务的注意力就越少。

安装

一键安装

将以下内容添加到你的 `claude_desktop_config.json` 文件中:

{
  "mcpServers": {
    "tender-mcp": {
      "command": "npx",
      "args": [
        "tender-mcp"
      ]
    }
  }
}

可运行的软件包

npmtender-mcp1.2.25stdio

远程端点

https://tender-mcp-production.up.railway.appstreamable-http

它能做什么

工具清单

工具(2)

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢search_tenders(keyword, company_profile, sources, limit, days_old, ...)

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.

输入模式

{
  "type": "object",
  "properties": {
    "keyword": {
      "type": "string",
      "description": "Search keyword — company capability, product type, or service (e.g. \"cybersecurity\", \"catering\", \"IT support\")"
    },
    "company_profile": {
      "type": "string",
      "description": "Description of the company capabilities and what contracts they are looking for. Used for AI fit scoring. More detail = better scores. If omitted, results are returned unscored."
    },
    "sources": {
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "uk",
          "eu",
          "us"
        ]
      },
      "description": "Which sources to search. Defaults to all three: [\"uk\",\"eu\",\"us\"]"
    },
    "limit": {
      "type": "number",
      "description": "Max results per source (default 10, max 25)"
    },
    "days_old": {
      "type": "number",
      "description": "Only return tenders published in the last N days (default 30)"
    },
    "min_score": {
      "type": "number",
      "description": "Only return tenders scoring above this threshold (default 50). Only applies when company_profile is provided."
    }
  },
  "required": [
    "keyword"
  ]
}

输出模式

{
  "type": "object",
  "properties": {
    "keyword": {
      "type": "string"
    },
    "total_found": {
      "type": "integer"
    },
    "sources_searched": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "tenders": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "id": {
            "type": "string"
          },
          "title": {
            "type": "string"
          },
          "description": {
            "type": "string"
          },
          "contracting_authority": {
            "type": "string"
          },
          "value": {
            "type": [
              "string",
              "number",
              "null"
            ]
          },
          "source": {
            "type": "string"
          },
          "ai_score": {
            "type": [
              "number",
              "null"
            ],
            "description": "Present only when company_profile was provided"
          },
          "recommendation": {
            "type": [
              "string",
              "null"
            ],
            "enum": [
              "BID",
              "INVESTIGATE",
              "SKIP",
              null
            ]
          },
          "fit_summary": {
            "type": "string"
          },
          "reasons": {
            "type": "array",
            "items": {
              "type": "string"
            }
          }
        }
      }
    },
    "scoring": {
      "type": [
        "object",
        "null"
      ],
      "description": "Present only when company_profile was provided"
    },
    "errors": {
      "type": "array",
      "items": {
        "type": "object"
      }
    },
    "checked_at": {
      "type": "string",
      "format": "date-time"
    },
    "_disclaimer": {
      "type": "string"
    },
    "_intelligence": {
      "type": "object",
      "description": "Always-present upsell hook -- not gated by tier"
    }
  },
  "required": [
    "keyword",
    "total_found",
    "sources_searched",
    "tenders",
    "checked_at",
    "_disclaimer"
  ],
  "additionalProperties": true
}
🟢get_tender_intelligence(mode, keywords, keyword, sources, limit)

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.

输入模式

{
  "type": "object",
  "properties": {
    "mode": {
      "type": "string",
      "enum": [
        "DAILY_DIGEST",
        "AWARD_HISTORY"
      ],
      "description": "DAILY_DIGEST: new tenders in last 24hrs. AWARD_HISTORY: past contract winners."
    },
    "keywords": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Keywords to monitor or search (e.g. [\"cybersecurity\", \"cloud infrastructure\"]). Required for DAILY_DIGEST."
    },
    "keyword": {
      "type": "string",
      "description": "Keyword for award history search. Required for AWARD_HISTORY."
    },
    "sources": {
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "uk",
          "eu",
          "us"
        ]
      },
      "description": "Sources to search. Defaults to all three."
    },
    "limit": {
      "type": "number",
      "description": "Max results per source for AWARD_HISTORY (default 10)"
    }
  },
  "required": [
    "mode"
  ]
}

输出模式

{
  "type": "object",
  "properties": {
    "mode": {
      "type": "string",
      "enum": [
        "DAILY_DIGEST",
        "AWARD_HISTORY"
      ]
    },
    "status": {
      "type": "string",
      "description": "Present on the free-tier preview path"
    },
    "message": {
      "type": "string"
    },
    "upgrade_url": {
      "type": "string"
    },
    "checked_at": {
      "type": "string",
      "format": "date-time"
    },
    "_disclaimer": {
      "type": "string"
    }
  },
  "required": [
    "mode"
  ],
  "description": "Shape varies by mode (DAILY_DIGEST/AWARD_HISTORY) and tier (free preview vs paid full access) -- fields below are the common envelope.",
  "additionalProperties": true
}

社区

评价此服务器

证据

最近观测

已验证未记录版本2 个工具
已验证未记录版本2 个工具