com.hangingcontext由 hangingcontext.com 發布官方發布者v2.0.2更新於 Oct 26, 2026
Fresh context for agents. Ask, search or follow stories. Each fact cites a Synorb Manifest.
Hanging Context 提供近 24 小時的新聞故事，每項事實都連回來源，讓助理可以提問、搜尋並追蹤新故事。
Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。
把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。
閱讀 https://sourceweft.com/mcp/com.hangingcontext%2Fmcp/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。把它新增到你客戶端的 mcpServers 設定中。
{
"mcpServers": {
"hanging-context-news-for-agents": {
"type": "http",
"url": "https://hangingcontext.com/mcp"
}
}
}Fresh, cited context from the last 24 hours for AI agents. Every fact links to its source. Free, no key.
Or connect any MCP client to https://hangingcontext.com/mcp (Streamable HTTP, no authentication).
Small read-only clients for JavaScript and Python. No key, no dependencies.
Each client has ask, latest, story and topics. See js/README.md and python/README.md.
js/: the npm package hanging-context.python/: the PyPI package hanging-context.skills/hanging-context/SKILL.md: when to use Hanging Context and how to call it.plugin.json and mcp.json: an Agent Plugin that bundles the skill and the MCP server.AGENTS.md: rules for agents that edit this repository.Hanging Context is built by Synorb.
來源：README.md，提交 e530277
Ask a question
Answer a question from recent stories. Ranks stories by keyword match and copies the best key facts word for word. Returns up to 5 facts, each with its story URL and Manifest ids, and up to `limit` matched stories. If nothing matches, returns no_match true and suggestions. It does not use an LLM. Use it when the user asks a question about recent news.
dayslimittopicquestion必填Get the latest stories
Get the latest stories, newest first. Filter by topic or beat. Returns up to 20 stories with headline, dek, topic, URL and Manifest ids.
beatlimittopicGet new stories since last check
Get only the stories that are new since your last call. Send the cursor from the last response. If you send no cursor, the call returns the current cursor and no stories. Returns up to 50 stories with next_cursor and has_more.
limittopiccursorSearch stories
Search recent stories by keyword. The ranking uses keyword match only. Returns up to 20 stories with headline, dek, topic, URL, Manifest ids and score.
limitquery必填topicsince_hoursRead a story
Read one story. Use format `brief` for the headline, dek and key facts. Use format `full` for the whole story as Markdown. Use format `claims` for key facts and paragraphs as JSON, each with its Manifest ids. Returns the story in that format and up to 3 related stories.
slug必填formatShow a story's sources
Show where a story gets its facts. Returns each source with its title, source name, original URL and date, and which facts and paragraphs use it. Also returns the trust label.
slug必填List topics
List the topics. Returns each topic with its title, beats, sources and story count for the last 24 hours. Also returns not_covered, a list of things this server does not cover. Call this first to get valid topic and beat ids for hc_latest, hc_search and hc_since.
無需輸入參數。
About Hanging Context
Explain Hanging Context. Returns what it is, the checks on each story, the reuse rules, and how to read or receive stories.
無需輸入參數。
已滿足適用檢查項的 100%
該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。
npx skills add Synorb/hanging-contextnpm install hanging-context # JavaScript, Node 18+pip install hanging-context # Python 3.9+import { ask } from "hanging-context";const answer = await ask("What did central banks say this week?");import hanging_context as hcanswer = hc.ask("What did central banks say this week?")hanging-context ask "central bank rates"hanging-context latest --topic artificial-intelligencehanging-context story 2026-10-16 robot-world-models-week --md