Boothcheck

com.boothcheck由 boothcheck.com 發布官方發布者v1.5.0更新於 Oct 25, 2026

What a stock price is betting on: implied growth, duration, and margin, read from SEC filings.

已驗證Streamable HTTP可網頁執行網頁搜尋與抓取金融資料與分析

服務詳細資訊

識別碼: com.boothcheck/boothcheck
傳輸: Streamable HTTP
執行環境: Web executable
信任: Verified
發布於: Sep 16, 2026

安全提示

MCP 服務會接收對話中的工具呼叫請求，並可能執行外部操作。啟用前請先了解該服務能做什麼，並只授予它所需的權限。

註冊中心已驗證此服務的命名空間屬於 boothcheck.com，且該網域同時執行其端點。這可以確認發布者，但並不代表該服務的工具是安全的。

SourceWeft 的檢查只涵蓋條目是否完整、端點是否回應；不審查伺服器的程式碼，也不審查其工具的行為。

在 README 中新增徽章

向讀者展示該 MCP 服務已收錄於 SourceWeft，徽章連結到本頁。

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/com.boothcheck%2Fboothcheck.svg)](https://sourceweft.com/mcp/com.boothcheck%2Fboothcheck?utm_source=readme&utm_medium=badge)

概覽

AI 產生的概覽

Boothcheck 依 SEC EDGAR 文件，把美股價格反推為隱含的成長率、持續年數與利潤率，讓助理說明價格在押注什麼。

可以做什麼: 將單一股票價格反推為隱含營業利潤成長率、持續年數與利潤率，並並排比較兩檔股票價格所含的假設，另可依已反映於價格的成長排序、列出涵蓋清單與報告重點（免金鑰工具）。對某公司最新財報做語意搜尋、跨公司年報語意搜尋、列出 SEC 申報清單、讀取管理層財測次數（免費 API 金鑰）。取得完整敘述報告章節、結構化價格反推紀錄、分部快照、同業組、風險因素變化、內部人登記與 13F 持有人（Research 方案）。產生多公司標準化對照表與研究簡報（Analyst/API 方案）。
適用情境: 當你希望助理解釋某檔美股目前價格對未來成長與利潤率的假設、依價格隱含預期篩選或比較股票，或調取 SEC 申報、財測、內部人與持有人資訊時使用。它著重研究與資訊參考，而非取得投資建議。
執行需求: 遠端 HTTP 端點，不需本機執行環境。免金鑰端點提供五項工具，不需帳號。更多工具需 boothcheck 方案：設定檔用戶端以 Authorization Bearer 標頭攜帶 API 金鑰，或在使用驗證端點時透過 OAuth 2.1 瀏覽器登入。需要網路連線。

安裝前請注意

輸出僅供資訊與研究參考，不構成投資建議；提供者聲明其非註冊投資顧問，且不傳回公允價值、目標價或評等。API 金鑰僅顯示一次並以雜湊儲存，請妥善保管。資料由 SEC EDGAR 預先計算並附截止日期，涵蓋範圍有限，空結果即為答案而非錯誤。

安裝

在 SourceWeft 中

開啟儀表板中的 Boothcheck，將其新增到工作區。
為需要使用其工具的對話啟用該服務。

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。

交給代理程式安裝

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.boothcheck%2Fboothcheck/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。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "boothcheck": {
      "type": "http",
      "url": "https://boothcheck.com/api/mcp"
    }
  }
}

README

boothcheck MCP server

Ask any AI assistant what a stock's price is actually betting on.

boothcheck inverts a US stock's market price into the bet it implies: the operating-income growth rate, the years it must be sustained, and the operating margin the price assumes, measured against what the company has actually delivered. Every number traces to SEC EDGAR filings through a reverse-DCF read (expectations investing). It never returns a fair value, a price target, or a buy/sell rating. It shows the bet, so you can judge it.

This MCP server exposes that decomposition for about 2,000 US tickers, plus the SEC filing search, financials, and ownership records behind it. Read-only. Five tools work with no account at all; the rest come with a boothcheck plan.

most_stretched is an implied-expectations screen, not a strategy, signal, or stock-selection feed. boothcheck's strategy and signal research is internal and is not served here (since v1.5.0).

Connect

The setup walkthrough, with one-click installers for Cursor and VS Code, lives at https://boothcheck.com/connect. It covers everything below and fills in the URL for you.

There are two endpoints, and they are not interchangeable.

Endpoint	Auth	What you get
`https://boothcheck.com/api/mcp`	none, or `Authorization: Bearer bck_...`	Keyless: the five free tools. With an API key: everything on that plan.
`https://boothcheck.com/api/mcp-auth`	OAuth 2.1	Sign in through the browser once. Everything on your plan, tokens refresh themselves.

A keyless client pointed at /api/mcp-auth gets a 401, so pick the one that matches how you want to authenticate.

Claude and Claude Desktop. Settings, then Connectors, then Add custom connector. Paste an endpoint. For the OAuth one, choose Connect and approve the read-only permission. Then switch boothcheck on under Search and tools in a conversation.

ChatGPT. Settings, then Apps and Connectors, then Advanced, and turn on developer mode. Create a new connector with the endpoint. The server ships an Apps SDK widget, so results render as an inline priced-in card.

Claude Code

Any MCP client (JSON config)

A config-file client cannot run the OAuth browser step, so use the keyless endpoint and attach an API key. Create one in account settings; keys are shown once and stored hashed.

json

{  "mcpServers": {    "boothcheck": {      "type": "http",      "url": "https://boothcheck.com/api/mcp",      "headers": { "Authorization": "Bearer bck_YOUR_KEY" }    }  }}

{  "mcpServers": {    "boothcheck": {      "type": "http",      "url": "https://boothcheck.com/api/mcp",      "headers": { "Authorization": "Bearer bck_YOUR_KEY" }    }  }}

Tools

Free and keyless. No account, nothing to approve.

Tool	What it does
`whats_priced_in`	Invert one ticker's price into implied growth, duration, and margin, against what the company earns today.
`most_stretched`	Rank stocks by how much growth is already baked into their price.
`compare_priced_in`	Side by side of the assumptions embedded in two prices.
`list_coverage`	The coverage inventory: every ticker with a live record and its resolution level.
`get_report_summary`	Bullet takeaways of a boothcheck research report. Public reports keyless; the full library needs a Research key.

With a free API key

Tool	What it does
`search_filings`	Semantic vector search inside one company's latest annual or quarterly filing, identical to the live stock-page search, with a clearly labeled SEC full-text fallback.
`discover_filings`	Cross-universe semantic search across companies' latest indexed annual filings, identical to Discover across filings on the Research page.
`list_filings`	A company's SEC filing inventory, filterable by form and year, with accession numbers and primary-document links.
`get_guidance_ledger`	Management guidance behavior from 8-K filings: lifetime counts of raises, cuts, initiations, withdrawals, and reaffirmations. A Research key adds the per-year history and the scored delivery record.

With a Research plan

Tool	What it does
`get_report`	Full narrative report sections: valuation, bull case, bear case, takeaways, catalysts.
`get_iee_record`	The full structured price inversion: solved variables, held parameters, discount basis, sensitivity, plausibility panel.
`get_segments`	Clean reportable-segment snapshots from the latest 10-K segment note.
`get_peer_cohort`	The peer cohorts we compare a company against, per segment, with how each was matched. Cohort multiple medians are not served; they are computed inside the engine per valuation line, not stored as standalone facts.
`get_risk_factor_deltas`	Risk factors added to the latest 10-K versus the prior year, as verbatim Item 1A headings.
`get_insider_signals`	The current insider register from Forms 3/4/5: officers and directors, their current reported stakes, and lifetime filing counts. Current facts only, no performance claims.
`get_holders`	The current 13F institutional holders register: fund families, concentration, positions opened and closed.

With an Analyst/API plan

The same data is served as plain REST at https://boothcheck.com/api/v1, with an OpenAPI 3.1 spec at https://boothcheck.com/api/v1/openapi.json generated from the same registry that runs the endpoints. Docs: https://boothcheck.com/developers

Example prompts once connected:

"What is NVDA's price betting on?"
"Which stocks are priced for the most right now?"
"Compare what AMD and NVDA prices each assume."
"Which companies disclose supply-chain exposure to Taiwan in their latest 10-K?"
"What does AAPL's latest annual filing say about China demand?"

What you get back

Plain-language reads like:

NVIDIA Corp (NVDA), as of 2026-06-28: At today's price, NVDA is priced for growth of +30.8% sustained for about 5.6 years. The more the price assumes beyond what the company has delivered, the more has to go right to justify it.

plus structured fields (impliedGrowthPct, impliedDurationYears, impliedMarginPct, currentMarginPct, characterization) and a link to the full report with the bull case, bear case, and valuation X-ray.

A price does not always resolve to a single number. Where the engine cannot solve one defensibly it says so in words rather than returning a point, and those reads are labelled as bounds, not estimates.

Rules of the road

No fair values, no price targets, no ratings. Describe output as "what the price implies," not as a recommendation.
For informational and research purposes only. Not investment advice. boothcheck is not a registered investment adviser.
Data is precomputed from SEC EDGAR filings and refreshed on boothcheck's regen cadence; each response carries its as-of date.
Coverage is roughly 2,000 US tickers and grows filing by filing. Some tools cover fewer names than others. When a tool returns nothing for a ticker, that is the answer, not an error to retry.

Registry

Published in the Official MCP Registry as com.boothcheck/boothcheck (see server.json). Aggregators like PulseMCP ingest from there. The listed remote is the keyless endpoint, so a registry install works with no account.

工具

whats_priced_in

What's priced into a stock

Invert a US stock's current price into the bet it implies: the operating-income growth rate, how many years it must be sustained, and (where the route holds one as an input) the terminal operating margin assumption, versus what the company has actually delivered (from SEC EDGAR filings, reverse-DCF). boothcheck does not return a Boothcheck house fair value, price target, or buy/sell rating — it shows what the price assumes so the user can judge the bet. Covers about 2,000 US tickers.

輸入參數ticker必填

most_stretched

Most stretched bets

Rank US stocks by how much growth is already baked into their price (implied operating-income growth from a reverse-DCF read of the current price). Returns the top N with the growth and duration each price assumes (plus any held margin input). Not a sell list — a ranking of where the bar to clear is highest.

輸入參數limit

compare_priced_in

Compare what two prices assume

Side-by-side of what two US stock prices are each betting on: implied growth and duration (plus any held margin input) from a reverse-DCF inversion of each price. No Boothcheck house fair value or rating — a comparison of the assumptions embedded in the two prices.

輸入參數tickerA必填tickerB必填

list_coverage

Coverage list

Inventory of US tickers with an implied-expectations model record, with its resolution level (whole-company, segment, financials, REIT, and kin). Model-record coverage does not guarantee a published priced-in decomposition or completed narrative report. Paginated at 100; inventory cached for up to one hour.

輸入參數page

get_report_summary

Report summary

The bullet takeaways of a boothcheck narrative research report plus which sections exist. Public reports are summarized keylessly; a signed-in Founding Access account key opens the full cached library. Never a fair value, target, or rating.