TrendHub

Evidence-backed AI content studio with 21 stable trend intelligence tools.

使うべきか

品質と安全性

B
説明の品質
60%
スキーマの完全性
88%
命名の品質
87%
ポイズニングのリスク
100%
権限の一致
100%
プロトコルへの準拠
100%

検出事項(17)

  • LOWTool 'list_platforms' description lacks action verblist_platforms 内
  • LOWTool 'list_categories' description lacks action verblist_categories 内
  • LOWTool 'get_trending' description lacks action verbget_trending 内
  • LOWTool 'xhs_hot_topics' description lacks action verbxhs_hot_topics 内
  • LOWTool 'cross_platform_overlap' description lacks action verbcross_platform_overlap 内
  • LOWTool 'discover_trending_topics' description lacks action verbdiscover_trending_topics 内
  • LOWTool 'take_snapshot' description lacks action verbtake_snapshot 内
  • LOWTool 'source_reliability' description lacks action verbsource_reliability 内
  • LOWTool 'keyword_trend_curve' description lacks action verbkeyword_trend_curve 内
  • LOWTool 'related_queries' description lacks action verbrelated_queries 内

ツール定義とプロトコルへの準拠に関する自動分析に基づいています。

コンテキストコスト

~4,624トークン数(ツール定義)
~1.0 KB一般的なレスポンスサイズ
注意への影響は大きい(128k コンテキストの 3.61%)

これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。

インストール

ワンクリックインストール

これを `claude_desktop_config.json` ファイルに追加してください:

{
  "mcpServers": {
    "trendhub": {
      "url": "https://trendhub-remote-production.up.railway.app/mcp"
    }
  }
}

リモートエンドポイント

https://trendhub-remote-production.up.railway.app/mcpstreamable-http

できること

ツール一覧

ツール(21)

🟢 読み取り専用🟡 書き込み🔴 削除⚪ 不明
🟢list_platforms

列出可查询的全部热点平台(调用名、中文名、分类、数据来源)

入力スキーマ

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢list_categories

列出平台分类与内容/模板分类

入力スキーマ

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_trending(platform, category, limit)

获取当前原始热点榜单并积累本地快照。只问“现在热什么”时使用;生命周期用 trend_intelligence,完整品牌/预测/风险机会用 professional_intelligence。

入力スキーマ

{
  "type": "object",
  "properties": {
    "platform": {
      "description": "平台调用名,多个用逗号分隔,如 weibo,zhihu,bilibili,hackernews",
      "type": "string"
    },
    "category": {
      "description": "分类:social/video/news/tech/dev/ai/global",
      "type": "string"
    },
    "limit": {
      "description": "每个平台返回条数,默认20",
      "type": "number",
      "minimum": 5,
      "maximum": 50
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}
⚪xhs_hot_topics(limit, topic_limit, with_hotlist, focus, industry_only)

小红书热点聚合(主打平台):一次性返回官方首页『热门推荐流』笔记(含封面/作者/点赞展示值/原文链接)、由热门标题词频派生的高频话题词(非官方热搜词榜)、当前会话模式(游客/登录)。配置环境变量 XHS_COOKIE 后额外返回官方『热搜词榜』。游客零配置即可用热门推荐流。

入力スキーマ

{
  "type": "object",
  "properties": {
    "limit": {
      "description": "热门笔记条数,默认30,最多40",
      "type": "number",
      "minimum": 5,
      "maximum": 40
    },
    "topic_limit": {
      "description": "派生话题词数量,默认20",
      "type": "number",
      "minimum": 5,
      "maximum": 50
    },
    "with_hotlist": {
      "description": "登录态下是否同时取官方热搜词榜,默认 true",
      "type": "boolean"
    },
    "focus": {
      "description": "品牌、Campaign、行业或话题;游客模式会据此收窄推荐流并补充行业公开证据",
      "type": "string"
    },
    "industry_only": {
      "description": "是否只保留品牌营销、商业运营、广告、媒体相关内容,默认 true",
      "type": "boolean"
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢cross_platform_overlap(keyword, platforms)

分析某个关键词/话题当前在多少个平台同时上榜(跨平台共振),给出各平台命中条目、最佳排名与共振分。用于判断一个话题是否具备全网热度。

入力スキーマ

{
  "type": "object",
  "properties": {
    "keyword": {
      "type": "string",
      "description": "关键词或话题,如 'AI眼镜'、'英伟达'"
    },
    "platforms": {
      "description": "可选,限定平台调用名,逗号分隔",
      "type": "string"
    }
  },
  "required": [
    "keyword"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢discover_trending_topics(min_platforms, platforms, topic)

无需关键词,自动聚类发现当前在多个平台共振的话题(基于标题相似度,结果需大模型复核归纳)。

入力スキーマ

{
  "type": "object",
  "properties": {
    "min_platforms": {
      "description": "至少在几个平台出现,默认2",
      "type": "number",
      "minimum": 2,
      "maximum": 6
    },
    "platforms": {
      "description": "可选,限定平台,逗号分隔",
      "type": "string"
    },
    "topic": {
      "description": "可选,按话题/关键词筛选聚类结果;支持品牌、campaign、行业议题或平台标签",
      "type": "string"
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢trend_change_alerts(platforms)

对比历史快照,输出各平台新晋上榜、排名飙升(≥3位)、掉榜的话题。需要先有两次以上快照(get_trending 会自动积累,或用 take_snapshot)。

入力スキーマ

{
  "type": "object",
  "properties": {
    "platforms": {
      "description": "可选,限定平台,逗号分隔;默认核心平台",
      "type": "string"
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}
⚪take_snapshot(platforms)

立即对各平台落一次历史快照(也可由系统定时调用以持续监测)。

入力スキーマ

{
  "type": "object",
  "properties": {
    "platforms": {
      "description": "可选,限定平台,逗号分隔",
      "type": "string"
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}
⚪source_reliability(platforms, refresh)

量化数据源稳定性:UP/DEGRADED/DOWN/AUTH_REQUIRED/RATE_LIMITED、24h/7d/30d ok/usable rate、P50/P95延迟、连续失败、schema drift 信号与历史深度。默认只读本地观测;refresh=true 时先真实刷新一次指定平台。

入力スキーマ

{
  "type": "object",
  "properties": {
    "platforms": {
      "description": "平台调用名,逗号分隔;默认核心平台",
      "type": "string"
    },
    "refresh": {
      "description": "是否先联网刷新一次,默认 false",
      "type": "boolean"
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢keyword_trend_curve(keywords, geo, timeframe)

获取关键词在 Google Trends 上的相对热度时间序列(0-100,非绝对搜索量),支持1-5个关键词对比。

入力スキーマ

{
  "type": "object",
  "properties": {
    "keywords": {
      "type": "string",
      "description": "关键词,多个用逗号分隔,如 'AI眼镜,VR头显'"
    },
    "geo": {
      "description": "地区代码,US/CN/TW/HK,留空=全球",
      "type": "string"
    },
    "timeframe": {
      "description": "如 today 1-m / today 3-m / today 12-m / now 7-d,默认 today 12-m",
      "type": "string"
    }
  },
  "required": [
    "keywords"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢related_queries(keyword, geo)

获取关键词在 Google Trends 的相关搜索词:top(长期热门)与 rising(近期飙升),用于选题与 SEO/搜索流量。

入力スキーマ

{
  "type": "object",
  "properties": {
    "keyword": {
      "type": "string"
    },
    "geo": {
      "type": "string"
    }
  },
  "required": [
    "keyword"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢future_signals(category, keyword, limit)

聚合高质量科技/AI/商业/营销信源的最新文章(未来趋势信号素材),可按分类或关键词过滤。趋势判断由调用方大模型完成。

入力スキーマ

{
  "type": "object",
  "properties": {
    "category": {
      "description": "信源分类;industry=品牌/商业/广告/媒体组合,可用 list_categories 查看;all=全部",
      "type": "string"
    },
    "keyword": {
      "description": "按关键词过滤标题/摘要",
      "type": "string"
    },
    "limit": {
      "type": "number",
      "minimum": 5,
      "maximum": 100
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢upcoming_events(days_ahead, category)

查询未来 N 天的趋势节点(科技展会/财报季/政策/电商大促/节假日),含距今天数与预热等级,用于提前布局内容。

入力スキーマ

{
  "type": "object",
  "properties": {
    "days_ahead": {
      "description": "未来天数窗口,默认90",
      "type": "number",
      "minimum": 1,
      "maximum": 365
    },
    "category": {
      "description": "节点分类,如 tech-event/earnings/ecommerce/holiday-cn/policy",
      "type": "string"
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢analyze_topic(keyword, geo, timeframe)

话题研究包:聚合当前共振、搜索曲线/动量、相关词、未来信号、节点与规则情感;需要多年度生命周期、验证预测、品牌实体或高管报告时使用 professional_intelligence。

入力スキーマ

{
  "type": "object",
  "properties": {
    "keyword": {
      "type": "string",
      "description": "要分析的话题"
    },
    "geo": {
      "description": "Google Trends 地区,留空全球",
      "type": "string"
    },
    "timeframe": {
      "description": "趋势时间窗,默认 today 3-m",
      "type": "string"
    }
  },
  "required": [
    "keyword"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}
⚪trend_intelligence(keyword, platforms, refresh)

轻量纵向 Trend Intelligence:基于本地真实历史计算生命周期、速度、持续性、扩散、Source Reliability 与确定性置信度;品牌实体、媒体、异常/预测、告警和报告请用 professional_intelligence。历史不足返回 insufficient_history。

入力スキーマ

{
  "type": "object",
  "properties": {
    "keyword": {
      "type": "string",
      "minLength": 1,
      "description": "要评估生命周期的关键词/话题"
    },
    "platforms": {
      "description": "可选平台,逗号分隔;默认核心平台",
      "type": "string"
    },
    "refresh": {
      "description": "是否先刷新当前数据,默认 true",
      "type": "boolean"
    }
  },
  "required": [
    "keyword"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢benchmark_trend_lead(keyword, reference_time, platforms)

真实场景 Lead-time Benchmark:把 TrendHub 本地历史的最早命中,与用户提供的外部事实 reference_time 对比,计算是否提前24h/72h发现。reference_time 必须来自官方公告、主流爆发点或团队约定的外部 ground truth,TrendHub 不会自己编造基准时间。

入力スキーマ

{
  "type": "object",
  "properties": {
    "keyword": {
      "type": "string",
      "minLength": 1,
      "description": "Benchmark 话题/关键词"
    },
    "reference_time": {
      "type": "string",
      "description": "外部 ground-truth ISO-8601 时间,例如 2026-09-20T09:00:00+08:00"
    },
    "platforms": {
      "description": "可选平台;默认核心平台",
      "type": "string"
    }
  },
  "required": [
    "keyword",
    "reference_time"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢list_templates(type, platform)

列出内置专家内容模板(短视频分镜脚本/小红书/微博/公众号/X线程/直播脚本/营销方案/内容日历/新品发布/标题钩子)。

入力スキーマ

{
  "type": "object",
  "properties": {
    "type": {
      "description": "script=脚本 copy=文案 plan=方案",
      "type": "string"
    },
    "platform": {
      "description": "平台,如 douyin/xiaohongshu/weibo/wechat/twitter",
      "type": "string"
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_template(id)

获取某个模板的完整结构(章节/目的/写作指引/填空位/checklist)。

入力スキーマ

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "description": "模板 id,如 short-video-script / xiaohongshu-note / marketing-plan"
    }
  },
  "required": [
    "id"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_content_brief(topic, template_id, platform, goal, audience, ...)

围绕主题聚合真实热点证据、相关搜索词、同平台样本与模板,并在内容工作台中调用使用者当前 AI 产出可编辑制品。

入力スキーマ

{
  "type": "object",
  "properties": {
    "topic": {
      "type": "string",
      "description": "创作主题/要蹭的热点"
    },
    "template_id": {
      "description": "模板 id;不传则按 platform 自动匹配",
      "type": "string"
    },
    "platform": {
      "description": "目标平台,如 douyin/xiaohongshu/weibo/wechat/twitter/douyin-live;all=通用",
      "type": "string"
    },
    "goal": {
      "description": "目标,如 涨粉/带货转化/品牌曝光/线索收集",
      "type": "string"
    },
    "audience": {
      "description": "目标人群画像",
      "type": "string"
    },
    "geo": {
      "description": "搜索趋势地区",
      "type": "string"
    },
    "open_model_review_public_titles": {
      "description": "仅在使用者要求开源模型复核时设为 true;TrendHub 自托管开放权重模型,无需使用者密钥。只处理主题和本次简报中的公开标题。",
      "type": "boolean"
    }
  },
  "required": [
    "topic"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢professional_intelligence(keyword, platforms, verticals, refresh, geo, ...)

Professional Intelligence v3:品牌、公司、商业体、产品、Campaign 的 Entity-first 决策入口。先主动检索主体相关公开证据,再结合生命周期、Source Reliability、Evidence Truth State、异常、6/24/48/72h验证预测、媒体/受众、机会风险与高管报告。品牌/实体研究优先用本工具;纯话题趋势研究才用 analyze_topic;只看当前榜单才用 get_trending。

入力スキーマ

{
  "type": "object",
  "properties": {
    "keyword": {
      "type": "string",
      "minLength": 1,
      "description": "要研究的品牌、公司、商业体、产品、Campaign 或商业主体,例如 广州太古汇 / LV / 小米 / Tesla"
    },
    "platforms": {
      "description": "可选平台调用名,逗号分隔;留空时由专业 Source Planner 自动选择零配置核心源",
      "type": "string"
    },
    "verticals": {
      "description": "可选行业/场景,逗号分隔:fashion-luxury,beauty,business-corporate,technology,automotive,finance-markets,marketing-advertising,retail-commerce,culture-entertainment",
      "type": "string"
    },
    "refresh": {
      "description": "是否先刷新当前公开数据,默认 true",
      "type": "boolean"
    },
    "geo": {
      "description": "Entity-first 搜索趋势地区,默认 CN;如 CN/HK/US",
      "type": "string"
    },
    "timeframe": {
      "description": "Entity-first 搜索趋势时间窗,默认 today 3-m",
      "type": "string"
    },
    "days_ahead": {
      "description": "未来节点窗口,默认60天",
      "type": "number",
      "minimum": 7,
      "maximum": 365
    },
    "report": {
      "description": "附带高管报告格式,默认 json",
      "type": "string",
      "enum": [
        "none",
        "json",
        "markdown",
        "csv"
      ]
    }
  },
  "required": [
    "keyword"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}
⚪workspace_manage(action, principal, workspace_id, name, member_principal, ...)

管理 TrendHub 本地工作区状态:创建/读取 workspace,维护 owner/editor/analyst/viewer 成员、watchlist、saved query、alert rule 与 audit。只写本地数据目录,不修改第三方平台、不自动上传;公网托管 Web 不暴露该变更接口。list/create 不需要 workspace_id,其余 action 必须提供 workspace_id。

入力スキーマ

{
  "type": "object",
  "properties": {
    "action": {
      "type": "string",
      "enum": [
        "list",
        "create",
        "get",
        "member_set",
        "watchlist_set",
        "query_save",
        "rule_save",
        "audit"
      ],
      "description": "操作:list/create/get/member_set/watchlist_set/query_save/rule_save/audit"
    },
    "principal": {
      "type": "string",
      "minLength": 1,
      "description": "本地身份映射,例如 local-owner 或公司 SSO 映射后的非敏感 principal"
    },
    "workspace_id": {
      "description": "工作区 ID;除 list/create 外均必填",
      "type": "string"
    },
    "name": {
      "description": "create 的工作区名,或 saved query / alert rule 的显示名",
      "type": "string"
    },
    "member_principal": {
      "description": "member_set 要新增/更新的非敏感 principal",
      "type": "string"
    },
    "role": {
      "description": "member_set 的目标角色",
      "type": "string",
      "enum": [
        "owner",
        "editor",
        "analyst",
        "viewer"
      ]
    },
    "keywords": {
      "description": "watchlist 关键词,逗号分隔",
      "type": "string"
    },
    "query": {
      "description": "query_save 时的关键词",
      "type": "string"
    },
    "platforms": {
      "description": "query_save 的平台调用名,逗号分隔",
      "type": "string"
    },
    "geo": {
      "description": "query_save 的地区/geo 过滤",
      "type": "string"
    },
    "rule_json": {
      "description": "rule_save 的 JSON 规则对象",
      "type": "string"
    },
    "enabled": {
      "description": "rule_save 是否启用,默认 true",
      "type": "boolean"
    },
    "limit": {
      "description": "audit 返回条数,默认 200,最大 1000",
      "type": "number",
      "minimum": 1,
      "maximum": 1000
    }
  },
  "required": [
    "action",
    "principal"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

コミュニティ

このサーバーを評価する

エビデンス

最近の観測

検証済みバージョンは記録されていませんツール 21 件
検証済みバージョンは記録されていませんツール 21 件