timesfm
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
Indian news briefs synthesised from every outlet on a story, with framing labels and source links.
作者提供的原文
教 AI 做这类工作的 Skill,可与本项一起使用
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
Open-source intelligence for the global theater. Track everything from the corporate/private jets of the wealthy, and spy satellites, to seismic events in one unified interface. Hook an AI agent up to have it parse through data and find previously unseen correlations. The knowledge is available to…
scrape data from Google Maps. Extracts data such as the name, address, phone number, website URL, rating, reviews number, latitude and longitude, reviews,email and more for each place
列表按使用分(满分 100)排序,由以下部分组成
| 热度 | 0/80 | GitHub 星标或每周下载量:较大的计 60,较小的计 20 |
|---|---|---|
| 新鲜度 | 12/12 | 30 天内有发布或代码更新得满分 |
| 仍在响应 | 8/8 | 上次检查时云端端点有响应 |
| 使用分 | 20/100 |
质量: 基础检查通过 4/4 项(仅展示,不用于排序) · 上升势头: 暂无数据 (只用于“上升中”标签)
选择你使用的 AI 应用,然后复制设置。
用一句话让 AI 帮你安装
请帮我安装 Indian Opinion。按照 https://mcp.popnx.com/i/indianopinion-news.md 操作,先把命令给我看,等我同意后再运行。粘贴到能在你电脑上工作的 AI(如 Claude Code、Cursor)。它会读取我们的步骤,先给你看命令,等你同意。无需密钥,无需注册。 · 查看 AI 会读取的全文
通过 4/4 项检查 · 你的提问会经过开发者的服务器(indianopinion.org) · ✓ 命令已检查 2026年11月20日
第一步:你用哪个 AI?
选择你用的应用,步骤会显示在下方。
可连接 Claude · 约 2 分钟
不需要密钥,不用安装程序 · 在 claude.ai 或桌面应用设置一次,即可在聊天中使用 · 免费账户可添加 1 个 · Team/Enterprise 方案由所有者(Owner)添加
CustomizeConnectors
把这里的内容复制到 Claude 中同名的输入框,然后点击 Continue
Indian Opinionhttps://indianopinion.org/mcp在 Claude 检测到的登录设置页点击 Continue · Authentication 按作者说明选择(Sign in now、Sign in when needed 或 No sign in),然后点击 Add
+ConnectorsIndian Opinion
用 Indian Opinion 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude 说正在使用 Indian Opinion,或回答中出现 Indian Opinion 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
能否连接 ChatGPT 取决于方案
完整 MCP:网页版 ChatGPT Business、Enterprise 或 Edu · Pro:以读取/获取权限连接,修改数据的工具可能用不了 · Plus:官方文档尚未确认,如果在插件页看到添加自定义 MCP 的选项可以试试 · 仅限网页
Plugins+Add custom MCP server
输入名称,在 Connection 下粘贴地址,勾选风险提示,然后点击 Create as a plugin
Indian Opinionhttps://indianopinion.org/mcp开启新聊天,输入前先从插件列表中选择 Indian Opinion
用 Indian Opinion 告诉我你能帮我做什么,然后做一件给我看✓ 如果 ChatGPT 说正在使用 Indian Opinion,或回答中出现 Indian Opinion 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 OpenAI 帮助页面核实 · 你的界面可能因版本略有不同
可连接 Claude Code · 约 2 分钟
不需要密钥,不用安装程序
Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell
claude mcp add --transport http --scope user news https://indianopinion.org/mcp应能看到 Indian Opinion 在列表中并显示已连接
用 Indian Opinion 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude Code 说正在使用 Indian Opinion,或回答中出现 Indian Opinion 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
可连接 Cursor · 约 2 分钟
不需要密钥,不用安装程序
用 Indian Opinion 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Cursor 说正在使用 Indian Opinion,或回答中出现 Indian Opinion 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Cursor 帮助页面核实 · 你的界面可能因版本略有不同
可连接 VS Code · 约 2 分钟
不需要密钥,不用安装程序
用 Indian Opinion 告诉我你能帮我做什么,然后做一件给我看✓ 如果 VS Code 说正在使用 Indian Opinion,或回答中出现 Indian Opinion 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 VS Code 帮助页面核实 · 你的界面可能因版本略有不同
其他支持 MCP 的应用(如 Windsurf、Zed、Gemini CLI)添加方式各不相同,请在应用列表中查看
通过网页连接的应用使用的地址
https://indianopinion.org/mcpJSON 设置在下方“开发者专用”中
Claude Code
claude mcp add --transport http --scope user news https://indianopinion.org/mcpCursor (~/.cursor/mcp.json)
{
"mcpServers": {
"news": {
"url": "https://indianopinion.org/mcp"
}
}
}VS Code (mcp.json)
{
"servers": {
"news": {
"type": "http",
"url": "https://indianopinion.org/mcp"
}
}
}这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。
通过互联网连接,适用于
ClaudeChatGPTGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatOpen WebUIRaycast
工具名称和描述与服务器在 2026年11月20日 报告的完全一致。这些内容由作者撰写,不是我们写的;我们以纯文本形式显示。
search_briefsSearch published Indian Opinion briefs (each one synthesised from several Indian outlets, with a corroboration count and how each outlet framed the story) by keyword, category and date window. Use it to find what we have on a story, person, place or topic. For today's curated lis
get_briefGet one published Indian Opinion brief by its URL or post id: the brief, our analysis of how outlets differed, each outlet with its framing label, and the source links. Use it after search_briefs or get_digest when you need the full text or the sources to cite. Not for searching;
signup_startStart an Indian Opinion agent account: emails a 6-digit code to the address you give (subject "NNNNNN is your Indian Opinion agent code", first line "Code: NNNNNN"). Use it only with an address whose mailbox you or your user can read, then call signup_verify. Verifying a new addr
signup_verifyFinish sign-up: trade the emailed 6-digit code for a bearer token (ioa_...). The token is shown once; store it as a secret (for example IO_TOKEN) and re-add this server with "Authorization: Bearer " to use the account tools. A newly verified address gets the daily digest and Brea
get_accountShow the signed-in agent account: kind, masked email, preferences (digest hour and format, Breaking News rule), topics followed and Breaking News emails sent in the last 24 hours. Use it to check what the account will receive before changing anything. Needs a token.
update_preferencesChange what the account receives: digest on or off, hour (7, 12, 18 or 21 local), time zone and format (text, json or html); Breaking News on or off, threshold 0.0 to 1.0, composite (min, mean, geo or breaking) and a cap of 1 to 20 emails a day; reminder emails. Send only the fie
list_topicsList the topics this account follows (with tier: instant emails or the daily roundup) and suggested topics with their keys and recent story counts. Use it before follow_topic to pick a key, or to find a topic_id for unfollow_topic. Needs a token.
follow_topicFollow a topic by free text (a place, person, organisation or issue, resolved the way the site's Track box does), by a suggestion key (t88, g1045) or by topic_id. tier "instant" sends an email when a matching brief is published (up to 3 a day); "daily" (default) adds one roundup
unfollow_topicStop following one topic by topic_id (from list_topics). Its alerts stop; other topics, the digest and Breaking News are unchanged. Unfollowing a topic not followed changes nothing. Needs a token.
get_digestGet the daily Indian Opinion digest as structured data: the same stories, in the same order, as the email of that day, each with category, outlet count, framing split, a summary and url, md_url and json_url. Use it to brief a person on the day in India. Default is the latest dige
list_breakingList the stories scored for Breaking News in the last 1 to 7 days, each with its four Jev scores (breaking, new_event, high_stakes, confirmed), the four composites, whether this account's current rule would send it, and what was actually delivered. Use it to tune the rule with up
get_breaking_eventGet one Breaking News event by event_id (from list_breaking or the json_url in a Breaking News email): headline, scores, composites, whether your rule sends it, delivery status, the brief and its sources. Needs a token.
unsubscribeStop emails to this account: "digest" (the daily digest), "breaking" (Breaking News), "topics" (every followed topic) or "all" (all of those and reminders). The account and its tokens stay, and the API keeps working. A new agent account gets the daily digest and Breaking News by
create_browser_linkCreate a one-time link (valid 10 minutes, single use) that signs a browser in to this account and opens /account/, so the human behind the agent can see or change settings on the site. Give the link only to that person. Needs a token.
close_accountClose the signed-in account: every token is revoked (this one too, so later calls fail), the digest, Breaking News, topic alerts and reminders stop, and the address can no longer sign in. This is deactivation, not deletion: the account record is kept under the privacy policy's re
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月20日
注册名称已通过域名 indianopinion.org 验证(注册中心会核实域名所有权)
代码最后更新于3天前
不适用:由 indianopinion.org 的所有者自己运行的云端服务器,你不会运行仓库里的代码
在 200 毫秒内响应(HTTP 200)
无需登录
已读取 15 个工具描述,未发现针对 AI 的隐藏指令
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/servers/indianopinion-news)提问、分享技巧或报告无法使用。按“有帮助”数量排序。
还没有评价
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 4 项适用的基础检查中通过了 4 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。
GitHub 仓库最后更新于3天前,最新版本(0.2.2)于今天进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,因此也能用于接受远程 MCP 的应用,例如网页版 ChatGPT(Business 及以上为完整 MCP;Pro 为只读)。
同一分类中有:OpenSEO, Exa, Microsoft Learn MCP, Docs, COTAL actions (cotal.ai)
同一分类、其他作者、命令已通过检查。官方的排在前面,再按星标排序。
如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Keyword research, site audits, rank tracking and AI visibility for your AI agent.
Official Exa MCP for web search, content fetching, and multi-step research.
Official Microsoft Learn MCP Server – real-time, trusted docs & code samples for AI and LLMs.
cotal.ai actions: product overview, site search, build log, feedback, Cloud waitlist, updates, calls
| 本项 Indian Opinion | OpenSEO | Exa | Microsoft Learn MCP | Docs | COTAL actions (cotal.ai) | |
|---|---|---|---|---|---|---|
| 运行位置 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 |
| 需要密钥 | 否 | 否 | 否 | 否 | 否 | 否 |
| 可在 Claude 中按 + 添加 | 否 | 是 | 是 | 是 | 否 | 否 |
| 基础检查 | 4/4 | 5/5 | 2/4 | 4/4 | 4/4 | 4/4 |
| 许可证 | MIT | MIT | MIT | CC-BY-4.0 | NOASSERTION | Apache-2.0 |
| 价格 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 |
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
The Indian Opinion MCP server gives AI agents and assistants Indian news briefs synthesised from many outlets, with corroboration counts and how each outlet framed the story, plus the daily digest, topic alerts and Breaking News for agent accounts.
| Endpoint | For |
|---|---|
https://indianopinion.org/mcp | Any MCP client over Streamable HTTP. Public tools need no sign-in; account tools take Authorization: Bearer ioa_... |
https://indianopinion.org/mcp/oauth | Clients that sign in with OAuth 2.1 (claude.ai, ChatGPT and others): the same server, with OAuth required |
This repository is the source of that server: a Cloudflare Worker that is a thin adapter over the Indian Opinion REST agent API (https://indianopinion.org/wp-json/io/v1). Every tool is one REST call made with the caller's own credentials; there is no business logic or data store here beyond the OAuth state. It also holds the OpenAPI 3.1 document, the agents.txt and the MCP server card the Worker serves, and setup guides for each client.
The command-line client and stdio bridge is IndianOpinion/cli. Until its first npm publish, install it from GitHub: npm i -g github:IndianOpinion/cli (or the site copy, npm i -g https://indianopinion.org/agents/cli/latest.tgz).
| Client | Guide | Method |
|---|---|---|
| claude.ai, Claude Desktop and mobile | docs/claude-ai.md | Custom connector, OAuth |
| ChatGPT | docs/chatgpt.md | Custom MCP server (developer mode), OAuth |
| Claude Code | docs/claude-code.md | claude mcp add --transport http |
| Cursor | docs/cursor.md | mcp.json with url |
| Grok | docs/grok.md | Custom connector in the app; remote MCP tool in the xAI API |
| OpenClaw | docs/openclaw.md | openclaw mcp add |
| Hermes Agent | docs/hermes.md | mcp_servers in config.yaml |
| Meta Muse | docs/meta-muse.md | Not verified |
| Instinct | docs/instinct.md | Not verified |
| Any other MCP client | docs/generic-mcp.md | Streamable HTTP URL |
| Agents without MCP | docs/openapi.md | OpenAPI 3.1 over REST |
Fifteen tools. Lists default to 10 items and cap at 25. Every tool sets a title, all four annotation hints (read-only, destructive, idempotent, open-world) and an outputSchema that describes its structuredContent. The server is stateless, so it advertises listChanged: false.
| Tool | Auth | What it does |
|---|---|---|
search_briefs | public | Search published briefs by text, category and date, with cursor paging |
get_brief | public | One brief by id or article URL: summary, sources, corroboration and framing |
signup_start | public | Email a 6-digit sign-in code to an address |
signup_verify | public | Exchange the email and code for an account token (ioa_...) |
get_account | account | The signed-in account: masked email, preferences, topics followed, recent Breaking News sends |
update_preferences | account | Change digest format and hour, and Breaking News settings |
list_topics | account | Topics the account follows |
follow_topic | account | Follow a topic, with an alert tier |
unfollow_topic | account | Stop following a topic |
get_digest | account | The latest daily digest, or the one for a date |
list_breaking | account | Recent Breaking News candidates and their scores |
get_breaking_event | account | One Breaking News event in full |
unsubscribe | account | Stop the digest, Breaking News, topic alerts or all emails |
create_browser_link | account | A one-time, 10-minute link that signs a browser in to the account page |
close_account | account | Close the account: tokens revoked, every email stopped, sign-in disabled (deactivation, not deletion) |
Prompts: morning_briefing, explain_framing_gap, watch_topic, tune_breaking, brief_my_human. Resources: indianopinion://about, indianopinion://brief/{id}, indianopinion://digest/{date}.
The OpenAPI operationId of each REST operation equals the MCP tool name.
search_briefs, get_brief, signup_start and signup_verify work on https://indianopinion.org/mcp with no credentials.signup_start and signup_verify (or indianopinion login in the CLI) and send the returned token as Authorization: Bearer ioa_.... Clients that can set a header use this on /mcp.https://indianopinion.org/mcp/oauth. A request without a token gets 401 with WWW-Authenticate: Bearer resource_metadata="https://indianopinion.org/.well-known/oauth-protected-resource/mcp/oauth". The server supports dynamic client registration (RFC 7591), the authorization code flow with PKCE S256, rotating refresh tokens and revocation (RFC 7009). Sign-in is the same email code; the connector then appears as a token labelled oauth on the account, where it can be revoked.Verifying a new email address switches on the daily digest and Breaking News (at most 5 a day under the default rule); unsubscribe with all stops both. close_account closes the account (with confirm: true): every token is revoked, every email stops and the address can no longer sign in. It is deactivation, not deletion: the account record is kept, deactivated, under the retention terms of https://indianopinion.org/privacy-policy/, and erasure or reopening is by email to hello@indianopinion.org. Tokens are never logged; each tool call logs only the tool name, the public token id, the outcome and the latency.
resources/read failures are JSON-RPC errors: a malformed id or date, or a missing brief or digest, is "resource not found" (-32602, as the 2026-07-28 spec requires); a missing token on indianopinion://digest/{date} is -32001.
| Scope | Limit |
|---|---|
Requests to /mcp and /mcp/oauth, per IP | 120 a minute |
search_briefs, per IP | 20 a minute |
| Account tool calls, per token | 60 a minute |
/oauth/authorize and /oauth/register, per IP | 30 a minute |
/oauth/token and /oauth/revoke, per IP | 60 a minute |
| Sign-in codes (set by the API) | 3 an hour per address, 5 an hour per IP |
| Request body | 16 KB (larger is 413) |
A limited call returns a tool error with retry_after in seconds. The REST API's own limits are authoritative; the Worker's limits sit in front of them.
| Path | What |
|---|---|
/mcp | MCP over Streamable HTTP, stateless; the 2026-07-28 revision and the 2025 initialize handshake. GET is 405. 2026-07-28 has no initialize: a client speaks it with the MCP-Protocol-Version: 2026-07-28 and Mcp-Method headers and the _meta envelope on each request. An initialize request is the 2025 handshake, so it negotiates the newest 2025 revision (2025-11-25) even when it offers 2026-07-28 |
/mcp/oauth | The same server with OAuth required |
/.well-known/mcp/server-card.json (also /.well-known/mcp-server-card, /.well-known/mcp.json) | MCP server card (draft, SEP-2127) |
/agents.txt | agents.txt (community draft) |
/agents/openapi.json | OpenAPI 3.1 of the REST API |
/agents/cli/, /agents/skill/SKILL.md | CLI downloads and the Agent Skills file |
/.well-known/oauth-protected-resource[/mcp/oauth] | RFC 9728 protected resource metadata |
/.well-known/oauth-authorization-server | RFC 8414 authorization server metadata |
/oauth/register, /oauth/authorize, /oauth/token, /oauth/revoke | OAuth 2.1 authorization server |
Node 20 or newer (engines in package.json). wrangler is a pinned devDependency, so npm run dev and npm run check need nothing else.
npm ci
npm test # Worker module in Node against a local REST stub; no network
To serve the CLI files under /agents/cli/ as well, clone IndianOpinion/cli next to this checkout as ../cli (or set IO_CLI_DIR) and run npm run build:cli; the tests then also check those files.
To run the Worker on your own Cloudflare account, copy wrangler.example.toml to wrangler.toml, fill in your account id and KV namespace id, and use npm run dev. discovery/ holds the agents.txt and server card exactly as src/discovery.js renders them (npm run discovery rewrites them); the test suite fails if they drift.
| File | Role |
|---|---|
src/index.js | Routing, guards, rate limits, MCP handler |
src/tools.js, src/prompts.js, src/resources.js | MCP tools, prompts and resources |
src/client.js | REST client |
src/auth.js | The only reader of credentials (bearer and OAuth) |
src/oauth.js | OAuth 2.1 authorization server |
src/discovery.js | Server card, agents.txt, CLI index |
src/render.js | Text rendering of briefs and digests |
test/ | Node test suites and the REST stub |
CHANGELOG.md | One entry per VERSION |
See CONTRIBUTING.md and SECURITY.md. Report vulnerabilities to hello@indianopinion.org, not in public issues.
MIT. Indian Opinion content returned by the API is not covered by this licence; see https://indianopinion.org/agents/ for its terms of use.