Back to Browse

Kabuken Mcp Plugin MCP Server

Developer ToolsLow Risk10.0MCP RegistryRemote
Free

Server data from the Official MCP Registry

EDINET filings of Japanese stocks: financial statements, segments, shareholders. No stock prices.

About

EDINET filings of Japanese stocks: financial statements, segments, shareholders. No stock prices.

Remote endpoints: streamable-http: https://kabuken.intellics.ai/mcp

Security Report

10.0
Low Risk10.0Low Risk

Valid MCP server (1 strong, 1 medium validity signals). No known CVEs in dependencies. Imported from the Official MCP Registry.

Endpoint verified · Requires authentication · 1 issue found

Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.

Permissions Found in Source Code

Found by scanning the linked source code. This listing connects to a hosted endpoint, so none of this runs on your machine: it describes what the server software does where it is hosted.

HTTP Network Access

Connects to external APIs or services over the internet.

How to Connect

Remote Plugin

No local installation needed. Your AI client connects to the remote endpoint directly.

Add this to your MCP configuration to connect:

{
  "mcpServers": {
    "io-github-intellics-ai-kabuken": {
      "url": "https://kabuken.intellics.ai/mcp"
    }
  }
}

Documentation

View on GitHub

From the project's GitHub README.

Kabuken: EDINET MCP server for Japanese stocks (Claude and ChatGPT)

mcptry

Kabuken is an MCP server for Japanese stocks (日本株) built on EDINET, Japan's disclosure system. It gives Claude, ChatGPT, Cursor and other MCP clients the financial statements, segment breakdowns and major shareholders of Japanese listed companies, taken from their official filings, including the annual securities reports (有価証券報告書). Each figure comes with the filing it was taken from and the period it covers, so you can check it against the original document.

Kabuken does not provide stock prices, market data or investment advice. It answers questions about what a company reported. Connect your client to https://kabuken.intellics.ai/mcp (Streamable HTTP). An account is required: Claude and ChatGPT connect with OAuth sign-in, and other MCP clients can use an API key. Kabuken returns individual XBRL facts with taxonomy labels and calculation-linkbase trees.

Kabukenは、EDINETをもとにした日本株向けのMCPサーバーです。Claude、ChatGPTなどの MCPクライアントから、日本の上場企業が提出した有価証券報告書などの財務諸表、 セグメント情報、大株主を取得できます。各数値には出典となる提出書類と対象期間を 示します。株価、市場データ、投資助言は提供しません。接続先は https://kabuken.intellics.ai/mcp です。

EDINET MCP guide: English · 日本語

What Kabuken provides

  • Source filing and period with each figure. Each value names the EDINET filing it comes from and the period it covers, so you can check it against the original document.
  • Calculation trees. get_calculation_tree returns the XBRL calculation linkbase of a filing as a tree, so you can see how a total breaks down into its components and their weights.
  • Segment breakdowns. get_segment_breakdown returns business, geographic and consolidation-scope figures by dimension axis and member.
  • Ownership. get_major_shareholders returns large-shareholding reports (大量保有報告書), and from the latest annual securities report the top shareholders (大株主の状況), the owner categories (所有者別状況) and the policy holdings (政策保有株式). See Ownership.
  • Officers and human capital. get_company_financials returns the officers, officer pay, AGM candidates and 人的資本 metrics of the latest annual securities report. See Include values.
  • One fact at a time. get_financial_facts finds one figure in a filing by keyword, or step by step from the filing outline down to the fact.
  • OAuth sign-in for Claude and ChatGPT. Claude and ChatGPT connect with OAuth sign-in, with no API key to copy. MCP clients without OAuth can connect with an API key.
  • Skill pack. This repository is a plugin for Claude Code and a plugin package for ChatGPT and Codex, with skills for common tasks (company snapshot, peer comparison, segment breakdown, finding a fact, people and governance, ownership).

Install

This plugin declares a remote MCP server in .mcp.json (https://kabuken.intellics.ai/mcp, streamable HTTP). Enable the plugin, then see SETUP.md or ask Claude "set up Kabuken" to authenticate.

Claude Code without the plugin:

claude mcp add --transport http kabuken https://kabuken.intellics.ai/mcp

ChatGPT (developer mode, beta)

  1. Download the latest plugin package: kabuken-plugin.zip.
  2. Open chatgpt.com/plugins, select +, then Create custom MCP server.
  3. Upload the ZIP.
  4. Sign in with Google when ChatGPT asks you to connect Kabuken.

The same repository is also an Agent Plugins package for ChatGPT and Codex: plugin.json and mcp.json at the root. Claude Code reads .claude-plugin/plugin.json and .mcp.json. See Plugin package.

Tools

Read-only tools, grouped by purpose. None write or modify data.

Company and industry discovery

  • search_companies — search Japanese listed companies by name (EN or JA, partial match)
  • get_company — full company record by any identifier (entity code, ticker, name). With include_sites: true, it also returns a summary of the company's major facilities from its latest annual report: counts by country and by prefecture, with the source filing.
  • list_industries — TSE industry classification taxonomy

Filings

  • list_documents — EDINET filing list for a company, with submission dates, period coverage, and XBRL/PDF availability
  • get_filing_text — narrative sections of an annual securities report (risk factors, management discussion) as filed, in Japanese, without AI processing

Financial facts

  • get_financial_facts — structured XBRL facts for a single filing. Find one fact step by step: outline: true lists the sections, section with outline: true lists its headings (100 per page), section with parent returns the children with values (context: "primary" keeps only facts with no dimension member and not non-consolidated); every outline node has a next field with the arguments of the next call. query searches labels and concept names. Sections: BalanceSheet, IncomeStatement, CashFlows, ChangesInEquity, ComprehensiveIncome, Notes, Other, CoverPage, Unclassified; document-entity (jpdei_cor) facts are not returned
  • get_calculation_tree — XBRL calculation linkbase as a tree (how totals decompose into components)
  • get_segment_breakdown — segment/geography/consolidation-scope dimensional data, axis and member labels
  • get_company_financials — headline figures and a fiscal-year series by default; full statements with include: ["statements"]; officers and human-capital metrics with include: ["officers"] and ["human_capital"] (see Include values); detail: "summary" (default) or "full"

Comparison and screening

  • compare_companies — side-by-side financial matrix for 2-5 companies from their latest annual securities report
  • screen_companies — filter companies by financial ratio (ROE, ROA, operating margin, current ratio, debt-to-equity); no price-based screens
  • get_industry_overview — mean/median/count per ratio for an industry, plus top/bottom 3 companies

Ownership and risk

  • get_major_shareholders — large-shareholding report (大量保有報告書) data: holder, percentage, shares, filing date; with include, also the top shareholders, owner categories and policy holdings of the latest annual securities report (see Ownership)
  • get_risk_context — BOJ policy-rate sensitivity and METI export-control classification for a company

AI-powered analysis

  • get_document_summary — AI-generated summary of a filing
  • analyze_document — free-text Q&A grounded in a specific filing

Data quality

  • report_data_issue — report a figure that looks wrong, with the filing it came from

Account

  • get_account_quota — caller's current daily quota usage, limit, and reset time; does not itself consume quota

Include values

get_company_financials takes include, a list of sections beyond the headline figures. An explicit list replaces the default ["indicators"].

ValueWhat it adds
indicatorsThe 主要な経営指標等の推移 figures per fiscal year (default)
statementsIncome statement, balance sheet and cash flow per period
omitted_conceptsStatement concepts with no consolidated current-period value
human_capital人的資本 metrics of the latest annual report: female managers ratio; male childcare-leave ratio for all, regular and non-regular employees, by legal basis (male_childcare_leave_ratio, male_childcare_and_childcare_purpose_leave_ratio, male_childcare_leave_ratio_womens_act); gender wage gap. For the reporting company and each consolidated subsidiary row (up to 100 rows, with the filed company name)
officers役員 of the latest annual report: name_ja, title_ja, role (director_or_auditor, executive_officer, director_and_executive_officer), in_officer_table, individually disclosed pay and shares held; total and paid_only_count; AGM candidates (the officers expected after the AGM, as filed); pay by officer category with head counts (unmatched_person_counts); board gender composition

detail: "summary" (default) keeps every figure and moves its source (doc_id, concept, context) up to the section and block level; long lists are tables (columns, rows). detail: "full" puts the source on every figure and is several times larger. Ratios are fractions as filed (0.04 is 4%). A filed 0 is 0; a blank cell is null.

Ownership

get_major_shareholders takes include:

ValueWhat it returns
large_holdingsLarge-shareholding reports (大量保有報告書), newest first (default)
top_holders大株主の状況: rank, holder name and address as filed, shares held, shareholding ratio
holder_categories所有者別状況: shareholder count, units held and ratio for the seven EDINET owner categories, per share class
policy_holdings政策保有株式: 特定投資株式 and みなし保有株式 rows with issuer name, shares held and book value for the current and prior year end, holding purpose; holder_scope and scope_counts separate the company's own holdings from those of its largest holding subsidiaries

policy_holdings pages at most 40 rows; send next_cursor back as cursor for the next page. Cursor pages return only the paged lists, so read top_holders and holder_categories from the first page. Rows with held_at_year_end: false were no longer held at year end; scope_counts gives held_specified_count and held_deemed_count. A year that the filer marked '*' (below the disclosure threshold) carries not_disclosed_below_threshold: true with null figures. Names are as filed.

Account

Get an account and a kbk_ API key (or use OAuth) at kabuken.intellics.ai. See SETUP.md for the connection walkthrough.

Slash commands

  • /kabuken:company-snapshot <company> — revenue, income, assets, equity, and risk context for one company
  • /kabuken:peer-comparison <company, company, ...> — side-by-side financials for 2-5 companies
  • /kabuken:segment-breakdown <company> — business/geographic segment breakdown for a filing

The filing-text skill loads when you ask for risk factors, management discussion or the original filing text; it reads them as filed with get_filing_text.

These skills load when the question matches (English or Japanese):

  • find-a-fact — one line item, note figure or cover-page item of a filing, by keyword or step by step with get_financial_facts
  • people-and-governance — officers, officer pay, AGM candidates, board gender mix and human-capital metrics with get_company_financials
  • ownership — large-shareholding reports, top shareholders, owner categories and policy holdings with get_major_shareholders

Attribution

EDINET content (filings, facts, dimensions) is used under Japan's Public Data License 1.0 (PDL 1.0):

Source: EDINET (https://disclosure2.edinet-fsa.go.jp/), PDL 1.0 (https://www.digital.go.jp/resources/open_data/public_data_license_v1.0). Data is processed by Kabuken, not raw unprocessed FSA data.

The EDINET Taxonomy (concept labels, calculation-linkbase relationships, dimension axis/member labels) is excluded from PDL 1.0 and separately licensed under the FSA EDINET Taxonomy Legal Statement (https://www.fsa.go.jp/search/EDINET_Taxonomy_Legal_Statement.html), which requires the notice "© Copyright 2014 Financial Services Agency, The Japanese Government" on redistribution. Tools that surface taxonomy content (get_calculation_tree, get_segment_breakdown) carry this notice.

Figures returned by screen_companies, get_industry_overview, compare_companies, and get_company_financials are calculated by Kabuken from EDINET filings, not reported directly by EDINET. Text from get_filing_text is reproduced verbatim from the filing; the filing company holds the rights to its text. Output from analyze_document is AI-generated and may contain errors; it is not investment advice.

Privacy policy

https://kabuken.intellics.ai/privacy

Documentation

https://kabuken.intellics.ai/docs

Plugin package

scripts/build-package.sh builds dist/kabuken-plugin-<version>.zip with plugin.json at the ZIP root, plus mcp.json, skills/ (without the Claude Code-only kabuken-setup skill), assets/ and LICENSE. README.md is not packaged. scripts/validate-package.sh checks the manifests, skills, README and SETUP.md, and scripts/tests/run-tests.sh tests those checks. The Plugin package workflow runs both on every pull request and push to main, and attaches the ZIP to a GitHub release when a v* tag is pushed. The tag must match the version in plugin.json.

Versioning

One version number covers the Claude plugin (.claude-plugin/plugin.json), the ChatGPT/Codex package (plugin.json) and the MCP Registry entry (server.json). scripts/validate-package.sh fails if the three differ. To release: bump all three to the same X.Y.Z, merge to main, push tag vX.Y.Z, then run the Publish to MCP Registry workflow manually from that tag. The workflow refuses to publish unless tag v<server.json version> is on the checked-out commit.

Registry manifest

server.json describes the hosted Kabuken MCP server (https://kabuken.intellics.ai/mcp) in the official MCP registry format and is published from this repo under the io.github.intellics-ai/kabuken namespace. The server's own source runs in a separate, private repository; this public repo is the registry's companion listing and the home for the plugin package documented above. Publishing runs via .github/workflows/publish-registry.yml (manual workflow_dispatch, GitHub OIDC authentication, no stored secrets).

Reviews

No reviews yet

Be the first to review this server!