China News MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_API_KEY | No | Bearer key for the HTTP MCP endpoint. Required when running in HTTP mode; not needed for stdio mode. | |
| ENABLE_GDELT | No | Enable GDELT as a news source. Default is true. | true |
| X_BEARER_TOKEN | No | Bearer token for the official X API. Required only if using X trends. | |
| X_TRENDS_WOEID | No | WOEID for X trends; 1 means worldwide. Default is 1. | 1 |
| ENABLE_X_TRENDS | No | Enable X official trends API. It is automatically enabled when X_BEARER_TOKEN is set. | |
| NEWS_USER_AGENT | No | User-Agent used when fetching news sources and robots.txt. Default is ChinaNewsMCP/0.3 (see README). | ChinaNewsMCP/0.3 |
| CUSTOM_RSS_FEEDS | No | Custom RSS feeds as a JSON array of feed objects. | |
| TOTAL_TIMEOUT_MS | No | Total timeout budget for one aggregation request in milliseconds. Default is 15000. | 15000 |
| MCP_ALLOWED_HOSTS | No | Comma-separated allowed external Host headers for HTTP mode. Needed when behind a reverse proxy or using a domain. | |
| ARTICLE_TIMEOUT_MS | No | Timeout for article content requests in milliseconds. Default is 10000. | 10000 |
| MAX_RESPONSE_BYTES | No | Maximum response size accepted from an upstream source. Default is 2097152. | 2097152 |
| STALE_CACHE_TTL_MS | No | How long stale search cache can be used when upstream fails, in milliseconds. Default is 1800000. | 1800000 |
| ENABLE_HTML_SOURCES | No | Enable People's Daily and Xinhua public page discovery. Default is true. | true |
| MCP_ALLOWED_ORIGINS | No | Comma-separated allowed browser Origins for HTTP mode. Required when requests come from browsers. | |
| PROVIDER_TIMEOUT_MS | No | Timeout per individual provider in milliseconds. Default is 8000. | 8000 |
| SEARCH_CACHE_TTL_MS | No | In-memory cache TTL for search results in milliseconds. Default is 300000. | 300000 |
| DEFAULT_ARTICLE_CHARS | No | Default maximum characters returned for article extraction. Default is 12000. | 12000 |
| ENABLE_BAIDU_TRENDING | No | Enable Baidu trending topics. Default is true. | true |
| ENABLE_WEIBO_TRENDING | No | Enable Weibo trending topics. Default is true. | true |
| TRENDING_CACHE_TTL_MS | No | Cache TTL for trending topics in milliseconds. Default is 120000. | 120000 |
| TRENDING_STALE_TTL_MS | No | How long stale trending cache can be used on failure, in milliseconds. Default is 600000. | 600000 |
| ENABLE_TOUTIAO_TRENDING | No | Enable Toutiao trending topics. Default is true. | true |
| ENABLE_INTERNATIONAL_NEWS | No | Enable NPR, France 24, and Sky News international RSS sources. Default is true. | true |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_china_newsA | 按关键词、分类、来源和时间范围查询中国相关中文新闻，返回规范化、去重且可引用的结果。 |
| aggregate_china_newsA | 查询新闻并按相似标题、关键词和时间邻近度形成事件簇；不生成无法追溯的事实。 |
| search_international_newsB | 查询 NPR、France 24、Sky News 和 GDELT 等国际来源，支持英文或中文结果，并返回规范化、去重且可引用的新闻。 |
| aggregate_international_newsA | 查询国际新闻并按相似标题、关键词和时间邻近度形成可追溯事件簇。 |
| get_news_articleA | 提取已注册来源或近期搜索结果页面的正文，遵守 robots.txt，且不绕过登录或付费墙。 |
| get_trending_topicsA | 查询微博热搜、今日头条热榜、百度热搜，保留各平台排名和热度，并识别跨平台相似话题。热度值仅能在同一平台内解释。 |
| list_news_sourcesA | 列出已配置新闻来源、热榜来源、支持分类和最近一次运行状态。 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
The domestic/international and search/aggregate splits are mostly clear, but search_china_news and aggregate_china_news both begin with a news query and could be confused by an agent wanting a simple result list. get_trending_topics, list_news_sources, and get_news_article are all clearly distinct.
All tools use lowercase snake_case with a clear verb prefix and a descriptive object or domain suffix. The repeated search_ and aggregate_ pattern for China and international news makes the naming highly predictable.
Seven tools is well-scoped for news discovery, aggregation, trending topics, source listing, and article extraction. Each tool adds a distinct capability without redundancy.
The tool surface covers the main news workflow: discover trending topics, search national and international sources, aggregate into event clusters, and extract article body text. Missing source configuration or update tools are a minor gap, but the server appears intentionally read-only.