Bosco Labs data

io.github.Bosco-Labs由 GitHub 帳號 Bosco-Labs 發布v0.2.3更新於 Nov 7, 2026

Sanctions screening, company checks, EU tenders and law, SEC filings, insider trades

已驗證Streamable HTTP可網頁執行網頁搜尋與抓取金融商業與電商

概覽

AI 產生的概覽

為助理提供官方來源的公司與財務資料:免費的 LEI 與 SEC 公司查詢,以及付費的 SEC 文件、內部人交易、歐盟標案與公司帳目。

可以做什麼
  • 辨識法律實體與美國上市公司:LEI、法定名稱、狀態、管轄區、CIK、股票代號、交易所與 SIC 產業
  • 規劃付費資料查詢:把自然語言問題轉成帶輸入、理由與最高價格的型別化呼叫,並說明任一工具的輸入結構、範例與每列價格
  • 取得付費紀錄:SEC 文件與內部人交易、美國眾議員股票交易、歐盟公共標案、五角大廈與聯邦合約授予、歐盟/英國上市公司財務資料,以及英國、丹麥、挪威公司帳目
  • 回傳精簡的 JSON 列,每列附上來源連結
適用情境
當助理需要可查證的公司身分資訊,或官方文件、內部人交易、標案、合約授予、歐洲公司帳目資料,並希望得到規模小、有定價、附來源連結的結果,而非大範圍網頁擷取時適用。
執行需求
可作為遠端端點執行,也可透過 uvx 作為本機 Python 套件執行(需安裝 uv)。兩個免費工具不需帳號或金鑰。付費工具需在 APIFY_TOKEN 提供 Apify API 權杖;遠端端點需在 Authorization 標頭提供預付的 Bosco Labs API 金鑰。需能連線 GLEIF、SEC 與 Apify。
安裝前請注意
付費工具依回傳列數計費到你自己的 Apify 帳戶,遠端端點則消耗預付額度,使用即產生費用;執行前請確認每列價格與 max_results。APIFY_TOKEN 與 Authorization 金鑰屬機密,勿放入共用設定。查詢為唯讀,但資料來自第三方來源(GLEIF、SEC、TED、USAspending、各國登記機關),應透過每列的來源連結標註出處。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Bosco Labs data,將其新增到工作區。
  2. 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/io.github.Bosco-Labs%2Fbosco-labs-data/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": {
    "bosco-labs-data": {
      "type": "http",
      "url": "https://api.boscolabs.dev/mcp/free"
    }
  }
}

README

Bosco Labs data: MCP server

One MCP server that gives AI agents official-source data: free company lookups (LEI, SEC), plus SEC insider trades and filings, US House members' stock trades, Pentagon contract awards, EU public tenders and the financials of European companies. The paid tools each run one of the Bosco Labs Apify Actors with your own Apify token. Every tool returns a short JSON list with a source link on every row.

Free tools (no token)

These two tools call the open official APIs directly: no Apify token, no key, no cost.

ToolData (source)Example question
lei_lookupLEI, legal name, status, jurisdiction, registration number and ultimate parent of any legal entity (GLEIF, CC0 open data)"What is Heineken N.V.'s LEI and is it active?"
sec_company_lookupCIK, official name, tickers, exchanges, SIC industry and state of incorporation of SEC-registered companies (SEC EDGAR)"What is Alphabet's CIK and on which exchange does it trade?"
bash
claude mcp add bosco-labs-data -- uvx bosco-labs-data-mcp   # no token needed for these# ask: "Look up the LEI of ASML" -> lei_lookup {"query": "ASML"}

Each result has a next_steps list: the paid call that gives the full picture (filings, insider trades or financials), with its tool and arguments on the remote MCP server (https://api.boscolabs.dev/mcp) and the HTTP API, and stdio_tool / stdio_arguments for this package.

Paid tools

ToolData (source)Price per rowExample question
eu_annual_report_financialsAudited financials of EU/UK listed companies (ESEF reports, filings.xbrl.org)$0.05 + $0.01 per call"Compare ASML's and Heineken's latest revenue and operating margin."
european_company_accountsAccounts of UK, Danish and Norwegian companies, incl. private (Companies House, Erhvervsstyrelsen, Brønnøysund)$0.04"What were the revenue and equity of Danish company CVR 24256790 in recent years?"
sec_insider_tradesForm 4 insider purchases and sales since 2006, cluster buys and sells (SEC EDGAR)$0.0018"Have NVIDIA insiders bought or sold shares in the last month?"
sec_filingsAny EDGAR filing since 1994: 8-K items, 10-K, 10-Q, earnings release times (SEC EDGAR)$0.001"When did Apple last release earnings, and was it after the close?"
us_house_stock_tradesSTOCK Act trades of House members since 2014 (Clerk of the House)$0.0018"What stocks did Nancy Pelosi trade this year?"
eu_public_tendersEU/EEA public tenders and contract awards (TED)$0.002"Find open IT-services tenders in Germany and the Netherlands from this week."
dod_contract_awardsDoD (or any federal agency) contract awards since FY2008, with winner tickers (USAspending.gov)$0.005"Which Pentagon contracts did Kratos win this year?"

Every tool has a max_results parameter with a small default (3 to 25 rows) and a hard maximum, so one call costs cents. dod_contract_awards can take a minute or more.

Two other Bosco Labs Actors are not tools here because they work on your own Apify datasets or Google credentials: Dedup & Merge Datasets and Google Sheets Export. Use them on Apify directly.

Pricing

The free tools cost nothing. For the paid tools you pay Apify per row returned, with your own token, at the prices above (the free Apify plan includes monthly credit). The server itself is free; it only calls Apify (paid tools), GLEIF and the SEC (free tools).

Install

  1. For the paid tools, get an Apify API token: https://console.apify.com/settings/integrations (skip this for the free tools only).
  2. Install uv.
  3. Add the server to your client (below). Once the package is on PyPI the command is uvx bosco-labs-data-mcp. Until then, run it from this folder: uvx --from /path/to/bosco-labs-data/mcp bosco-labs-data-mcp.

Claude Desktop

claude_desktop_config.json (Settings -> Developer -> Edit Config):

json
{  "mcpServers": {    "bosco-labs-data": {      "command": "uvx",      "args": ["bosco-labs-data-mcp"],      "env": { "APIFY_TOKEN": "apify_api_..." }    }  }}

Cursor

~/.cursor/mcp.json (or .cursor/mcp.json in a project): the same mcpServers block as above.

Claude Code

bash
claude mcp add bosco-labs-data -e APIFY_TOKEN=apify_api_... -- uvx bosco-labs-data-mcp

Without a token, leave out the env block (or -e APIFY_TOKEN=...): the free tools work and the paid tools reply that a token is needed.

Alternative: Apify's hosted MCP server

Without installing anything, you can use the same Actors through Apify's own MCP server (OAuth or your token; each Actor becomes a tool with its full input):

https://mcp.apify.com?tools=Bosco_labs/esef-annual-reports,Bosco_labs/company-accounts,Bosco_labs/sec-insider-trades,Bosco_labs/sec-filings-feed,Bosco_labs/us-house-trades,Bosco_labs/eu-tenders,Bosco_labs/dod-contract-awards

This server is the lighter option: typed parameters, small defaults and compact results.

Development

bash
uv run --with pytest pytest -q    # from this folder; Apify, GLEIF and SEC are mocked, plus a stdio smoke test

Source and releases: https://github.com/Bosco-Labs/bosco-labs-data (folder mcp/). Releases are published to PyPI and the official MCP Registry by the publish-mcp.yml GitHub Actions workflow; see PUBLISHING.md.

來源:mcp/README.md,提交 159f11f

工具

4

plan_official_records_query

Plan an official-records query

Free, no key needed. Turns a question in plain words into the exact typed Bosco Labs calls that answer it: tool, input, why, and the maximum price of each step, plus what is not covered. Pass the user's question verbatim AND the entities you extracted from it (company_names, tickers, identifiers, countries, dates, law references...): the planner trusts your entities over its own parsing and puts them in the right input fields. The plan echoes them in entities_used and lists in `missing` what to pass for a better plan. Deterministic (rules and examples, no LLM): the same question and entities on the same day give the same plan_id. Run it with run_official_records_plan (paid, max_usd) or call the listed tools directly. Low confidence returns the top 3 candidate tools instead.

輸入參數lawdate_topackagetickersentitieskeywordsproductsquestion必填addressescountriesdate_fromamount_min另有 3 個

describe_official_records_tool

Describe an official-records tool

Free, no key needed. One Bosco Labs tool's input schema, example input, example rows, output fields, price per row, caps and sources. Takes the tool name (eu_tenders or eu-tenders); an unknown name returns the closest names.

輸入參數name必填

lei_lookup

LEI lookup (GLEIF, free)

Free, no API token needed. Legal Entity Identifier (LEI) lookup in the official GLEIF register: about 2.9 million companies, funds and other legal entities worldwide (source: GLEIF API, CC0 open data). Use it to identify a company: its exact legal name, LEI, whether it is active, its jurisdiction and country, its local registration number and its ultimate parent company. Pass an LEI (exact record) or a company name (best matches first; check `legal_name`). Returns one row per entity: lei, legal_name, entity_status (ACTIVE/INACTIVE), registration_status (ISSUED, LAPSED, ...), jurisdiction, legal_address_country, legal_address_city, headquarters_country, registered_as (local registry number), ultimate_parent (lei, legal_name; when reported), source_url (the GLEIF record; cite it) and next_steps (the paid Bosco Labs call for this company's financials: tool and arguments on the remote MCP server and HTTP API, stdio_tool in this package).

輸入參數query必填max_results

sec_company_lookup

SEC company lookup: ticker to CIK (free)

Free, no API token needed. Identify a US-listed (SEC-registered) company: CIK, official name, ticker(s), exchange(s), industry (SIC code) and state of incorporation (source: SEC EDGAR company tickers file and submissions API). Use it to turn a ticker or name into the CIK that SEC tools take, or to check which exchange a stock trades on. Pass a ticker, a CIK or part of the name (best matches first, then by company size; check `name`). A name search covers companies with a listed ticker (about 10,000); a CIK also finds filers without one. Returns one row per company: cik, name, tickers, exchanges, sic, sic_description, state_of_incorporation, fiscal_year_end (MMDD), source_url (the EDGAR company page; cite it) and next_steps (the paid Bosco Labs calls for its filings and insider trades).

輸入參數query必填max_results

版本歷史

1
  1. v0.2.3最新Nov 7, 2026

評分

已滿足適用檢查項的 90%

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。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分

    請在儲存庫或註冊中心條目中宣告授權條款。