Context7
Up-to-date docs for AI agents
作者提供的说明(英文原文)
8-agent research committee, live analysis and scored news on US stocks and crypto, for any agent.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
Authorization标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
这个地址需要在请求的 header 中放入密钥,而添加连接器的菜单无法设置。请改用 Claude Code、Cursor 或 VS Code。
在终端中运行这条命令
claude mcp add --transport http simianx https://service.simianx.ai/v1/mcp --header 'Authorization: Bearer {api_key}'运行前请先填写空着的值。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"simianx": {
"url": "https://service.simianx.ai/v1/mcp",
"headers": {
"Authorization": "Bearer {api_key}"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"simianx": {
"type": "http",
"url": "https://service.simianx.ai/v1/mcp",
"headers": {
"Authorization": "Bearer {api_key}"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个地址需要在请求的 header 中放入密钥,而添加连接器的菜单无法设置。请改用 Claude Code、Cursor 或 VS Code。
你的选择通过 Cookie 保存在这台设备上,无需账户。
Authorization 机密 必填 HTTP header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。
工具名称和描述与服务器在 2026年11月6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。
quick_readRun SimianX's four live AI agents once on a US stock or a crypto pair: Fundamental reads the business or the coin, Indicator the chart, Intelligence the news flow, and Decision turns it into a call with entry, stop and target and the next candle close. Returns a run id right away
get_quick_readStatus and results so far of a quick read. Pass wait (up to 25 s): the answer returns as soon as one more agent has finished; call again while status is queued or running, relaying each new agent.
start_live_sessionWatch a symbol while the user talks to you: the four live agents run at every candle close of the timeframe and report fundamentals, technicals, news flow and the decision with the next run time, for as long as you keep following (get_updates every 10 s, or the WebSocket). The se
list_live_sessionsThe account's live analysis sessions: symbol, timeframe, since when, next run, last decision.
get_live_sessionOne live analysis session: status, next run time and the latest results.
stop_live_sessionEnd a live analysis session.
get_updatesEvery update of this key the user has not been told: finished analysis steps, decisions (with the question to ask), matched news. Relay each `say` (and `ask`) in order, then call again with ack set to the last id you relayed; unacked updates come back until you do. Use wait (up t
run_live_analysisDeprecated, sunset 2026-12-01: the same one-pass run as quick_read under its old name. Use quick_read. (uses points, metered on the models used like the website; deprecated (use /v1/analysis/quick))
get_live_analysisDeprecated, sunset 2026-12-01: status and results of a run started with run_live_analysis. Use get_quick_read. (deprecated (use /v1/analysis/quick/{id}))
get_newsThe scored news stream behind Market Pulse: every article tagged with the symbols it moves, its value (low, medium, high) and its sentiment. Newest first. Use since to fetch only what is new, cursor for older pages. (0.5 points per call)
get_news_articleOne article from get_news with its text, symbols, value and sentiment. (0.2 points per call)
watch_newsKeep matching scored news for symbols server side, also while you are offline; each matching story arrives in get_updates with a sentence to relay (high-value ones ask whether to run a quick read). Several sources of one story arrive once. (needs the starter plan or above)
list_news_watchesThe key's news watches. (needs the starter plan or above)
stop_news_watchStop matching news for a watch. (needs the starter plan or above)
list_webhooksWebhooks that receive this account's updates.
create_webhookPOST every update (or the kinds listed) to a URL, signed with HMAC-SHA256 (X-SimianX-Signature), with retries. For the user's own code; an agent that reads get_updates does not need one.
delete_webhookRemove a webhook.
test_webhookPOST a signed test event to the webhook now.
get_pulse_eventsMarket Pulse events on US stocks and crypto: sudden price moves and other market events, each with a severity from 1 to 4. Newest first; delayed on lower plans. (0.3 points per call)
get_pulse_summaryA 24-hour overview of Market Pulse. (0.2 points per call)
start_deep_analysisStart the deep research committee on a stock or a coin: four analysts (fundamentals, market, news, and timing for stocks or derivatives for crypto), a bull and a bear researcher, a research manager and a risk manager, ending in a verdict with entry, stop and target and a PDF. Tak
get_deep_analysisState, verdict and trade plan of a deep research run. Poll until status is done.
list_deep_analysesThe account's recent deep research runs.
ask_deep_analysisAsk a follow-up question about a finished deep research run; read the answers with get_deep_thread. (uses points, metered on the models used like the website)
get_deep_threadQuestions asked about a deep research run and the committee's answers.
search_instrumentsFind the symbol to use: US stocks, ETFs and crypto pairs matching a name or ticker.
get_crypto_quotesLatest prices for up to 120 coins. (0.1 points per call)
get_crypto_candlesOHLCV candles for a coin or pair. (0.2 points per call)
get_crypto_indicatorsIndicator snapshot (trend, momentum, levels) for a coin or pair. (0.3 points per call)
list_sectorsSectors under watch with headline stats and the event types they use. (0.2 points per call)
get_sectorOne sector: stats, the coming catalysts, recent events and the largest companies. (0.3 points per call)
get_sector_calendarDated catalysts in a sector (for biopharma: PDUFA dates, advisory committees, trial readouts, conferences). (0.3 points per call)
get_sector_eventsEvents in a sector taken from primary sources, with severity 1-4. (0.3 points per call)
list_autopilotsThe account's autopilots: the four live agents running on a schedule.
create_autopilotRun the four live agents on a symbol on a schedule, optionally letting the Decision agent manage a paper position. Runs server side, also while you are offline; every analysis, decision and position change lands in get_updates and the event log (get_autopilot_events). After start
get_autopilotStatus and configuration of one autopilot, with its event cursor.
update_autopilotChange models, intervals, language, the timing gate or AI position control. Changing the timeframe or switching AI control off closes the paper position first.
start_autopilotRestart a stopped autopilot. (uses points, metered on the models used like the website)
stop_autopilotStop an autopilot's schedule.
get_autopilot_eventsThe autopilot's event log: analyses, signals, position changes, actions. Without after you get the latest events and a cursor; pass that cursor as after (and wait, up to 25 s) to get only what happens next.
get_autopilot_positionsThe autopilot's paper positions and their operations.
autopilot_actionChange the autopilot's paper position by hand, always at the server's price: open, add, reduce, close, set_levels, place_order, replace_order, cancel_order, set_timeframe. Stocks are long only, and intraday stock entries need the market open.
run_autopilot_agentRun one of the autopilot's agents now, outside its schedule; the result lands in the event log. (uses points, metered on the models used like the website)
get_accountThe account behind the API key: plan, limits and the key's budgets (points figures are for your own pacing; do not read them to the user unless asked).
list_modelsModels that can be set per agent, with their rates and the typical points of a live call.
send_feedbackTell the SimianX team about a bug, missing data or an idea. Read by people; not answered.
pricing_getPrices in points, plans and limits (machine readable)
skill_getSkill and API versions, changelog, deprecations (read at the start of a session)
usage_getUsage by key and endpoint
feedback_listYour last 20 feedback messages (status only; we do not reply)
quote_postPoints a call would cost, no execution
market_statusUS equity market window
sectors_stocksConstituent stocks of a sector (0.3 points per call)
sectors_stockOne company inside the sector: profile, tracked assets, calendar (from 90 days back), events, market-cap peers (0.3 points per call)
sectors_eventOne event in full (summary, facts, calendar item, readiness) with related events (0.2 points per call)
sectors_assetsTracked assets (drugs, products) of a sector (0.3 points per call)
sectors_assetOne asset: links, trials, readiness checklist, its events and calendar, the company behind it (0.3 points per call)
sectors_followsThe account's follows in this sector and its subscription (needs the starter plan or above)
sectors_followFollow a stock, asset or calendar item (the first follow in a sector creates an email subscription) (needs the starter plan or above)
sectors_unfollowRemove a follow by id or by target key (stock:SMMT, asset: , calendar: ) (needs the starter plan or above)
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7日
注册名称已通过 GitHub 账户 SimianX-AI 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
在 736 毫秒内响应(HTTP 200)
无需登录
已读取 60 个工具描述,未发现针对 AI 的隐藏指令
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 3 项适用的基础检查中通过了 3 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。
你需要填写:Authorization
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–,最新版本(1.0.7)于6天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。
同一分类中有:Context7, Codebase Memory, Exa
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ 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
Up-to-date docs for AI agents
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
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。
SimianX AI for AI agents
Give any AI agent a full research desk. With SimianX AI your agent can convene an 8-agent research committee on any US stock or crypto pair and question it afterwards, get a live four-agent read with entry, stop and target, and keep a scored news stream open on your symbols. One skill and a remote MCP server for Claude Code, Codex, Cursor, Muse, Grok Bot, dots and every other agent.
simianx.ai/agents · SKILL.md · INSTALL.md · OpenAPI · Changelog
English · Português · Español · हिन्दी · Bahasa Indonesia · Tiếng Việt · ไทย · 简体中文 · 繁體中文 · 日本語 · 한국어 · Filipino · Русский · Français · Deutsch · Türkçe
Ask an agent on its own *"Should I buy NVDA for a swing trade?"* and it searches the web, summarises headlines that may be days old and gives one model's opinion. It has no live chart, nobody arguing the other side, and it stops when the chat ends.
With SimianX the same agent:
| On its own | With SimianX AI | |
|---|---|---|
| Who works on it | One model | An 8-agent committee: four analysts, a bull and a bear researcher, a research manager, a risk manager |
| What it reads | Web search results | Live candles, filings, insider trades, the news flow; on-chain and derivatives data for a coin |
| What you get | An opinion | A verdict with entry, stop and target, and a PDF report |
| Afterwards | Starts over | Puts follow-up questions to the same committee, or sets an autopilot to keep watching |
Once the skill is in, ask in your own words:
Free accounts can try the committee on popular symbols such as NVDA, AAPL, TSLA, BTC and ETH.
Two things do most of the work.
Also there when you need it:
Markets: 13,000+ US stocks and ETFs on 1m to 1mo candles, and 4,000+ crypto pairs, spot and perpetual, on 1m to 1D. → Stock analysis · Crypto analysis
Paste this to your agent:
Install the SimianX skill from https://www.simianx.ai/INSTALL.md and sign me in.
It puts the skill where your agent looks for skills, then signs you in: you approve a link in your browser, or type the 6-digit code we email you. A new address gets an account on the spot. The agent ends up with an API key of its own in SIMIANX_API_KEY and never with your website login.
From a terminal instead:
npx skills add SimianX-AI/simianx-skills
gh skill install SimianX-AI/simianx-skills simianx
The command and the directory for each agent (Claude Code, Codex, Cursor, Copilot, Gemini CLI, Windsurf, Amp, Cline and the rest) are in INSTALL.md.
Agents that run on their own cloud computer read the same sentence. They connect over MCP or build a connector from the OpenAPI document, sign you in, keep the key in their own credential store and save SimianX as a skill. The exact words for Muse, Grok Bot and dots are in INSTALL.md.
AI agents that speak MCP can use SimianX as tools without installing the skill. Add the remote server once with your key:
claude mcp add --transport http simianx https://service.simianx.ai/v1/mcp --header "Authorization: Bearer $SIMIANX_API_KEY"
The same for Claude Desktop, Cursor, Codex, VS Code, Windsurf, Gemini CLI, Grok Bot and Muse is in INSTALL.md. Registry name: io.github.SimianX-AI/simianx.
| What | Call | Reference |
|---|---|---|
| Live analysis session (every candle close) | POST /v1/live/sessions → the WebSocket, or GET /v1/updates?wait=30 | live |
| Quick read, once | POST /v1/analysis/quick → GET /v1/updates?wait=30 | quick |
| Everything the user has not heard | GET /v1/updates?ack= &wait=30 | following |
| News on your symbols | GET /v1/news?symbols=NVDA&min_value=medium | news |
| News as it lands | GET /v1/news/stream (server-sent events, resumable) | news |
| Market Pulse | GET /v1/pulse/events | data |
| Deep research | POST /v1/analysis/deep → /events · /ask · /pdf | deep |
| Sector Watch | GET /v1/sectors/{sector}/calendar · /events | sectors |
| Autopilots | POST /v1/autopilots → GET /v1/autopilots/{id}/events?after= &wait=30 | autopilots |
Base URL https://service.simianx.ai/v1, header Authorization: Bearer $SIMIANX_API_KEY. The same calls as shell scripts are in examples/curl.
Free, Starter, Plus and Pro, see pricing. Agent calls use your plan's points at the same rates as the website. The news stream is live on Plus and Pro; below Plus, news runs 30 minutes behind. Answers come in 16 languages.
You can use SimianX's API to connect its analysis and signals to your own trading system and place real orders through a broker or exchange you authorize. Positions recorded inside SimianX are simulated; your integration submits and manages real orders in your own account.
SIMIANX_API_KEY. The skill never writes it into a repository, a log or a prompt.The skill sends its version in the X-SimianX-Skill header. When a version is retired, the API answers 426 with the URL to re-read, and GET /v1/skill shows the current and minimum versions. Update with your agent's own command or paste the sentence above again. What changed is in the changelog.
skills/simianx/SKILL.md the skill (Agent Skills format)
skills/simianx/references/ following · live · quick · deep · news · autopilots · data · sectors · developers · billing INSTALL.md agent-readable install guide (also at simianx.ai/INSTALL.md) scripts/install.{sh,py,ps1} installer for every agent; check_version.py · check_readmes.py examples/curl · examples/runner the first calls in curl; an always-on runner for autopilots .claude-plugin · .agents/plugins · .cursor-plugin · plugin.json · gemini-extension.json manifests so marketplaces and plugin commands find the skill server.json MCP Registry entry for the remote MCP server (service.simianx.ai/v1/mcp) README. .md this page in the 16 languages SimianX speaks
POST /v1/feedback.Read CONTRIBUTING.md before opening a pull request, and SECURITY.md to report a vulnerability.
MIT for everything in this repository. Use of the SimianX API is governed by the Terms of Service. SimianX analyses are information, not investment advice.