protogrid

Search / io.github.Zachary-1012/trendhub

TrendHub

not classified

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

v2.0.4 · active · descriptor JSON · versions

Not classified yet.The remote endpoints have not been probed successfully, or the listing has nothing to connect to.
Quality82good
Trust49of 100
Uptime, 30 days97%
Latency p50272 ms

Connect

8 clients · secrets stay placeholders
{
  "mcpServers": {
    "trendhub": {
      "type": "http",
      "url": "https://trendhub-remote-production.up.railway.app/mcp"
    }
  }
}
claude mcp add --transport http trendhub https://trendhub-remote-production.up.railway.app/mcp
[mcp_servers.trendhub]
url = "https://trendhub-remote-production.up.railway.app/mcp"
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "trendhub": {
      "type": "remote",
      "url": "https://trendhub-remote-production.up.railway.app/mcp",
      "enabled": true
    }
  }
}
{
  "mcpServers": {
    "trendhub": {
      "type": "http",
      "url": "https://trendhub-remote-production.up.railway.app/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=trendhub&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vdHJlbmRodWItcmVtb3RlLXByb2R1Y3Rpb24udXAucmFpbHdheS5hcHAvbWNwIn0%3D"
}
{
  "servers": {
    "trendhub": {
      "type": "http",
      "url": "https://trendhub-remote-production.up.railway.app/mcp"
    }
  }
}
{
  "mcpServers": {
    "trendhub": {
      "httpUrl": "https://trendhub-remote-production.up.railway.app/mcp"
    }
  }
}
extensions:
  "trendhub":
    enabled: true
    name: "trendhub"
    type: streamable_http
    uri: "https://trendhub-remote-production.up.railway.app/mcp"
    timeout: 300

Quality 82 / 100good

protocol75 · weight 25
  • warn
    protocol.modernnewest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
  • n/a
    protocol.statelessonly applies to 2026-07-28 servers
  • pass
    protocol.transportstreamable HTTP
  • n/a
    protocol.list_ttlonly applies to 2026-07-28 servers
authorizationn/a · weight 15
  • n/a
    auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
  • n/a
    auth.secret_in_urlno templated URL
tool hygiene79 · weight 30
  • warn
    tools.descriptions1 of 21 tools have a description under 20 characters
  • pass
    tools.description_lengthdescriptions are concise
  • pass
    tools.schemasevery tool has an object input schema
  • pass
    tools.annotations21 of 21 tools declare readOnlyHint or destructiveHint
  • fail
    tools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: list_categories (idempotentHint); keyword_trend_curve (idempotentHint); future_signals (idempotentHint); …
  • pass
    tools.token_costabout 2,750 tokens to load every tool
  • pass
    tools.api_dumptools are not a one-to-one API dump
stability100 · weight 15
  • pass
    stability.changesno tool changes in 30 days
  • pass
    stability.rug_pullno tool changed its meaning under the same name
dependenciesn/a · weight 15
  • n/a
    deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

21 tools, about 2,750 tokens to load them all · tool set 1ce641f4cb74 · checked 2026-10-20 11:08 UTC

Tool changes

No tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 49 / 100

no-repositoryunreachable
provenance35
liveness9
freshness100
hygiene80

-unreachable(3 failures) +updated-27d-ago -no-repository

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remoteauthreachableuptime 30dp50protocollast ok
https://trendhub-remote-production.up.railway.app/mcp streamable-httpnoneno (3 failures)97%272 ms2025-11-252026-10-17

Tools (21)

analyze_topicread-only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。
benchmark_trend_leadread-only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。
cross_platform_overlapread-only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。
discover_trending_topicsread-only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)。
future_signalsread-only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。
get_content_briefread-only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。
get_templateread-only获取某个模板的完整结构(章节/目的/写作指引/填空位/checklist)。
get_trending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。
keyword_trend_curveread-only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。
list_categoriesread-only列出平台分类与内容/模板分类
list_platformsread-only列出可查询的全部热点平台(调用名、中文名、分类、数据来源)
list_templatesread-only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)。
professional_intelligenceProfessional 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。
related_queriesread-only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。
source_reliability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。
take_snapshot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)。
trend_change_alertsread-only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)。
trend_intelligence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。
upcoming_eventsread-only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。
workspace_manage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。
xhs_hot_topics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。

Schemas: list_tools.

Similar MCP servers

Official server.json
{
  "name": "io.github.Zachary-1012/trendhub",
  "title": "TrendHub",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://trendhub-remote-production.up.railway.app/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "2.0.4",
  "description": "Evidence-backed AI content studio with 21 stable trend intelligence tools."
}