
AlphAI
io.github.makeev由 GitHub 账号 makeev 发布v0.2.0更新于 Oct 24, 2026
Financial news for AI agents: search, trending, insider, earnings reads, macro, scored 1-10.
概览
托管式财经新闻 MCP 服务器,让助手检索带评分的市场新闻、内部人申报、财报与宏观事件,覆盖美股等标的。
- 可以做什么
- 按查询词、股票代码、类别或日期搜索和获取新闻,并提供热门文章和多来源报道,附逐标的解读与 1–10 相关性评分。获取单篇文章,以及供研究类客户端使用的可引用检索与抓取结果。查看 SEC Form 4 内部人交易新闻,以及多名内部人公开市场买入的集群。阅读经申报核实的财报解读和下次报告日期,以及 CPI、FOMC 等预定宏观发布及后续报道。通过雷达跟踪市场或自选列表的新闻活跃度与语气,并列出、订阅或取消订阅标的提醒。
- 适用场景
- 适合需要获取经过筛选的实时市场新闻、内部人交易信号、财报解读或宏观日历的助手,例如用于研究简报或自选列表监控,覆盖美股、ETF、加密货币和境外上市标的。不适用于投资建议或全文获取。
- 运行要求
- 远程 Streamable HTTP 端点,无需自行部署。通过兼容客户端进行 OAuth 2.1 登录(浏览器完成,无需粘贴 API 密钥);无头客户端可在 Authorization 头中以 Bearer 方式发送 API 密钥。免费额度为每分钟 20 次、每天 100 次请求;付费档为每月 2.99 美元或 9.99 美元。
安装
在 SourceWeft 中
- 打开 控制台中的 AlphAI,将其添加到工作区。
- 连接 所需的 凭据。它们会被私密存储,绝不会在公开页面上展示。
- 为需要使用其工具的对话启用该服务。
Web executable,通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。
交给智能体安装
把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体,或 SourceWeft 对话中。智能体会读取该服务器的安装指南,先向你展示发布者、端点和登录方式,经你同意后再把它添加到你的客户端。密钥不会写进任何命令。
阅读 https://sourceweft.com/mcp/io.github.makeev%2Falphai-mcp/install.md,并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前,先告诉我它的发布者、端点和登录方式,等我确认。不要把 API 密钥写进命令或我会提交的文件;问我密钥应从哪里获取。其他 MCP 客户端
把它添加到你客户端的 mcpServers 配置中。 客户端会在首次连接时完成 OAuth 登录。
{
"mcpServers": {
"alphai": {
"type": "http",
"url": "https://mcp.alphai.io/mcp"
}
}
}README
AlphAI MCP server
[License: MIT] [Official MCP Registry] [Smithery] [mcp.so] [Glama] [Mentioned in Awesome MCP Servers]
A Model Context Protocol (MCP) server for financial
news, stock market sentiment and SEC Form 4 insider trading data — built for AI agents
and trading bots. Hosted at mcp.alphai.io, no install, OAuth (no API key to paste),
free tier 20 req/min and 100 req/day.
Every story is enriched with per-ticker analysis, a category (14 buckets), and a 1–10 relevance score, so an agent can filter to what actually matters before spending a reasoning token.
This repo is the public home +
server.jsonmanifest of the hosted AlphAI MCP server (the listing on Smithery, Glama, mcp.so, the MCP Registry and Awesome MCP Servers). The product is AlphAI — a financial-news platform built for AI agents. There is nothing to self-host: to use it, just connect tohttps://mcp.alphai.io/mcp.
Connect
The server speaks Streamable HTTP at https://mcp.alphai.io/mcp. Add it to any
OAuth-capable MCP client. Claude Code:
Connecting opens a browser for OAuth 2.1 (DCR + PKCE) — a login, no key to copy-paste. ChatGPT, Claude Desktop / claude.ai, Cursor, VS Code, Windsurf and Gemini connect the same way. Or use the one-click listing on Smithery.
JSON config clients (Cline, Cursor and similar):
Other clients
Tools (21)
MCP Server URL: https://mcp.alphai.io/mcp
alphai_news_search- Full-text + filtered news search (query, tickers, category, dates, relevance)alphai_ticker_news- Latest news for one ticker (optionally incl. insider)alphai_trending- Top articles of the last 48h by relevance, reprints collapsedalphai_stories- Stories: events two or more publishers reported, summarised from their articles;list=topranks the last 48h,list=latestpages newest-firstalphai_story- One story bystory_id(the key every news item carries): summary, key facts with sources, per-ticker read, open questions, plus the articles behind italphai_actionable_now- Breaking, decision-grade news (actionability + novelty gate)alphai_insider_news- SEC Form 4 insider-trade newsalphai_insider_clusters- Issuers where several insiders bought on the open market in one run of purchases (Form 4, labeled per buyer)alphai_pair_analysis- Two-ticker read-across (news naming both companies)alphai_article- Fetch a single article byuid(adds a structuredearningsread on SEC filings)alphai_earnings- AlphAI's filing-verified earnings reads per ticker, plus the next report datealphai_calendar- Scheduled macro releases (CPI, FOMC, jobless claims) with times and the coverage that followedalphai_macro- Macro-economy feed (prints, central banks, rates, FX, commodities)alphai_tickers- Discover supported tickers (US stocks, ETFs, crypto & foreign listings, incl. each one'snext_report_date)alphai_watchlist_brief- Recent news and filing events for your saved watchlist, on every planalphai_radar- News activity and tone across the market or your saved watchlist, with linked evidence, 4h/24h windows and snapshot-pinned paginationsearch/fetch- Citation-ready article discovery and retrieval for compatible research clientsalphai_alerts_list/alphai_alerts_subscribe/alphai_alerts_unsubscribe- Manage your own ticker alert subscriptions (Basic/Pro)
All tools are read-only except the alphai_alerts_* writes, which only ever touch the
caller's own subscriptions. Full schemas, params and defaults are advertised by the server
(annotations included) and documented at alphai.io/mcp.
Tiers
Radar refreshes each minute. Delays apply to the complete snapshot, including supporting headlines; collection and enrichment add processing time. Its descriptive scores are not predictions or confirmed alerts. Radar accepts up to 100 rows per call on every plan, with no separate ticker allowance; saved watchlists retain their existing limits (Free 10 companies, paid unlimited).
Authentication
OAuth 2.1 with Dynamic Client Registration (RFC 7591)
and PKCE per the
MCP authorization spec.
Compatible clients discover the OAuth metadata automatically — no manual API key setup.
Both tool discovery (tools/list) and calls require authentication. Headless
clients can use the same API key as the REST API in an Authorization: Bearer ak_live_… header; never put a key in the URL. OAuth and API keys have tool parity.
Ready-made Claude Code skills
Drop-in skills that drive these tools (stock brief, market pulse, insider radar, peer read-across, manage alerts): makeev/alphai-claude-skills.
Links
- Playground & docs — https://alphai.io/mcp
- REST API & SDKs (Python + TypeScript) — https://alphai.io/developers
- Smithery listing — https://smithery.ai/servers/mihail-makeev/alphai-news
- Glama connector — https://glama.ai/mcp/connectors/io.github.makeev/alphai-mcp
- MCP Registry —
io.github.makeev/alphai-mcp - Changelog — https://alphai.io/changelog
Notes
- This is a hosted server — to use it, connect to
https://mcp.alphai.io/mcp; there is nothing to self-host. This repo is the catalog home +server.jsonmanifest. - News, not advice. The tools summarize reporting; they don't give buy/sell calls.
raw_text(full article bodies) is never served — copyright. Responses carry titles, AI summaries, per-ticker analysis, categories and relevance scores.
MIT licensed. Built by AlphAI.
来源:README.md,提交 227612d
工具
0版本历史
1- v0.2.0最新Sep 16, 2026
评分
已满足适用检查项的 85%
该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。
- 近 30 天内可连通必需25 分
- 已声明认证方式必需10 分
- 已列出工具15 分
请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。
- 描述必需15 分
- 图标10 分
- 文档15 分
- 许可证10 分