MCP MeasureMCP Measure

index observed

x-news-digest

X 资讯检索：零配置免 Key 的 X/Twitter 资讯检索，账号池扫描/关键词搜索/热度排序/智能去重，输出中文日报

Should I use this

Quality & Safety

B
Description quality
84%
Schema completeness
70%
Naming quality
92%
Poisoning risk
100%
Permission match
100%
Protocol compliance
100%

Findings (2)

  • LOWTool 'get_post' description lacks action verbin get_post
  • LOWTool 'reset_seen' description lacks action verbin reset_seen

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~683Tokens (tool definitions)
~686 BTypical response size
Moderate attention impact (0.53% of 128k context)

This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.

Install

One-Click Install

Add this to your `claude_desktop_config.json` file:

{
  "mcpServers": {
    "x-news-digest": {
      "url": "https://x-news-digest-mcp.aiones.cc/mcp"
    }
  }
}

Remote endpoints

https://x-news-digest-mcp.aiones.cc/mcpstreamable-http

What it can do

Tool inventory

Tools (5)

🟢 Read-only🟡 Write🔴 Delete⚪ Unknown
⚪scan_accounts(accounts, hours, top, min_heat, mark_seen)

扫描一批 X 账号近 N 小时的帖子，按热度排序输出中文资讯日报（核心工具）。accounts 支持逗号分隔账号或预设包名（ai_llm/ai_dev/tech_news/crypto），可混合。

Input Schema

{
  "type": "object",
  "properties": {
    "accounts": {
      "default": "ai_llm",
      "description": "账号列表或预设包名，如 'OpenAI,dotey' 或 'ai_llm'",
      "type": "string"
    },
    "hours": {
      "default": 24,
      "description": "时间窗口（小时）",
      "type": "number"
    },
    "top": {
      "default": 10,
      "description": "最多返回条数",
      "type": "number"
    },
    "min_heat": {
      "default": 0,
      "description": "最低热度分门槛（热度=赞+转×3+藏×2+评×0.5）",
      "type": "number"
    },
    "mark_seen": {
      "default": true,
      "description": "是否记入已见库（下次自动跳过）",
      "type": "boolean"
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}
🟢search_x_news(query, hours, count)

按关键词搜索 X 帖子并按热度排序。注意：免费镜像搜索索引较浅，空结果不代表没有内容，主通道请用 scan_accounts。

Input Schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "搜索关键词，支持 'AI agent'、'from:OpenAI' 等"
    },
    "hours": {
      "default": 24,
      "description": "只保留近 N 小时的结果",
      "type": "number"
    },
    "count": {
      "default": 20,
      "description": "抓取条数",
      "type": "number"
    }
  },
  "required": [
    "query"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}
🟡get_post(url_or_id)

读取单条 X 帖子详情（含 views/媒体信息），接受帖子 URL 或数字 id。

Input Schema

{
  "type": "object",
  "properties": {
    "url_or_id": {
      "type": "string",
      "description": "帖子链接或 id"
    }
  },
  "required": [
    "url_or_id"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}
🟢list_presets

列出内置精选账号包（scan_accounts 可直接引用包名）。

Input Schema

{
  "type": "object",
  "properties": {},
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}
⚪reset_seen

清空已见去重库（下次扫描会把时间窗内命中帖当新帖再推一遍，慎用）。

Input Schema

{
  "type": "object",
  "properties": {},
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

Community

Rate this Server

Evidence

Recent observations

verifiedversion not recorded5 tools