A large Machine Learning community in Japan

<p><a href="https://www.mlt.ai/" target="_blank" rel="noopener" aria-label="MLT (opens in a new tab)">MLT</a> is a community and an award-winning nonprofit organization based in Tokyo, Japan. More than 10,000 members from all over the world. Since 2017, organized more than 300 talks, workshops, and study sessions in machine learning, deep learning, reinforcement learning, and math.</p>


large_mlt_transparent_black_font_e1571189935683_50dd637c0a.png

medium_mlt_transparent_black_font_e1571189935683_50dd637c0a.png

small_mlt_transparent_black_font_e1571189935683_50dd637c0a.png

thumbnail_mlt_transparent_black_font_e1571189935683_50dd637c0a.png

mlt_transparent_black_font_e1571189935683_50dd637c0a.png

small_mlt2_a7affc4128.webp

thumbnail_mlt2_a7affc4128.webp

mlt2_a7affc4128.webp

small_mlt4_6a49c502ea.webp

thumbnail_mlt4_6a49c502ea.webp

mlt4_6a49c502ea.webp

small_mlt1_d360bda018.webp

thumbnail_mlt1_d360bda018.webp

mlt1_d360bda018.webp

small_mlt3_dfdf9c06f5.webp

thumbnail_mlt3_dfdf9c06f5.webp

mlt3_dfdf9c06f5.webp

About

Services

Blog

Kabuken

Labs

Homepage

AI services, performance and security engineering

nav-card-services.webp

Request information, stay in touch with us

nav-card-contact.webp

Product updates, upcoming events and trending news

nav-card-news.webp

How we built a data platform on Japanese regulatory filings, from XBRL extraction to AI integration

nav-card-case-study-kabuken.webp

Kabuken now carries four more sources of context around a Japanese company's filings: maritime warnings at nine chokepoints from the US National Geospatial-Intelligence Agency, the Japan-relevant entries of the US BIS Entity List, the Ministry of Economy, Trade and Industry's monthly Middle East share of Japan's crude-oil imports, and the major sites a company lists in its annual securities report.

The layers appear on the Events page and in the `get_risk_context` and `get_company` MCP tools, each with the source attribution alongside. The blog post walks through all four.

[Read the post](/blog/post/23?utm_source=news&utm_medium=news&utm_campaign=2026-11-09-features) | [Market events guide](https://kabuken.intellics.ai/docs/en/guide/market-events/?utm_source=news&utm_medium=news&utm_campaign=2026-11-09-features)

Sources: NGA Maritime Safety Information (US government work); US Bureau of Industry and Security Entity List; Ministry of Economy, Trade and Industry (Government of Japan Standard Terms of Use); EDINET (Financial Services Agency, Japan), Public Data License 1.0. Processed by Kabuken. Kabuken does not provide stock prices or investment advice.

Kabuken adds four context layers: maritime warnings, export controls, oil dependency and company sites

Illustration: an isometric map of Japan in grey; a tanker follows an orange route through a strait past an orange buoy, container ships reach a port with cranes, and refinery tanks and factories stand on land, marked with pins

kabuken-context-layers-japan-map-strait-tanker-buoy-tile-wide.webp

kabuken-context-layers-japan-map-strait-tanker-buoy-1536w.webp

Kabuken's new `get_filing_text` tool returns the business risks (事業等のリスク) and management's analysis (MD&A) sections of an annual securities report in the company's own words, in Japanese, with the source XBRL element named.

The blog walks through one example from a 2026 annual report. Plugin 2.1.9 adds a `filing-text` skill and is available in the ChatGPT plugin directory and on GitHub; in Claude the tool works through the connector.

[Read the post](/blog/post/21?utm_source=news&utm_medium=news&utm_campaign=filing_text) | [Step-by-step guide](https://kabuken.intellics.ai/docs/en/guide/filing-text/?utm_source=news&utm_medium=news&utm_campaign=filing_text)

Source: EDINET (Financial Services Agency, Japan), Public Data License 1.0. Processed by Kabuken. Kabuken does not provide stock prices or investment advice.

Kabuken now returns a filing's risk section as written

Illustration: an open annual report on a white plinth; one paragraph block is lifted out of the page in orange and leaves an empty recess in the text

kabuken-filing-text-open-report-lifted-passage-tile-wide.webp

kabuken-filing-text-open-report-lifted-passage-1536w.webp

Kabuken, our platform for the financials of Japanese listed companies, is now published in OpenAI's ChatGPT plugin directory.

![Kabuken's panel in the ChatGPT plugin directory: the K logo, three example prompts about Toyota, Sony and Honda, and the description](/uploads/kabuken-chatgpt-plugin-directory-panel.webp)

Once the plugin is added, you can ask ChatGPT about a Japanese listed company in plain English or Japanese. Kabuken answers with figures taken from the company's EDINET filings, the disclosure system of Japan's Financial Services Agency, and names the source filing for each figure so you can check it yourself.

The data covers financial statements, business and geographic segment data and major shareholders, all taken from the filings each company has submitted. Labels are available in English and Japanese.

Kabuken is read-only. It does not provide stock prices and it does not give investment advice. It shows what a company reported, and where.

The plugin runs on the Kabuken MCP server, the same server behind our Claude connector.

[Open Kabuken in the ChatGPT plugin directory](https://chatgpt.com/plugins/plugin_asdk_app_6ac386b94a6c8191a41d8630d2c31f04?utm_source=intellics&utm_medium=news&utm_campaign=chatgpt_listing_2026_11) | [About Kabuken](https://kabuken.intellics.ai)

Source: EDINET (https://disclosure2.edinet-fsa.go.jp/), PDL1.0 (https://www.digital.go.jp/resources/open_data/public_data_license_v1.0). Processed by Kabuken.

Kabuken joins the ChatGPT plugin directory

Illustration: a shelf of grey cubes with one empty slot; the missing cube, in orange, sits on a desk and is plugged into a laptop that shows a chat

kabuken-chatgpt-plugin-cube-shelf-laptop-chat-tile-wide.webp

kabuken-chatgpt-plugin-cube-shelf-laptop-chat-1536w.webp

We have published a new article on the blog: a step-by-step comparison of four Japanese automakers (Toyota Motor, Honda Motor, Suzuki Motor and SUBARU) built only from their annual securities reports on EDINET and read through Claude with the Kabuken MCP connector.

![Kabuken financial health card for Toyota Motor: ROE and ROA bars with the company value, the industry average and the percentile](/uploads/kabuken-toyota-financial-health-roe-roa-bars.webp)

You get the prompt for each step, the Kabuken tools it calls and the resulting tables: the headline figures, three fiscal years each from its own filing, segment and regional breakdowns and, as an optional step, the large-shareholding reports. Every figure carries the EDINET document ID of the filing it came from, so you can open the filing and check it.

[Read the article](https://intellics.ai/blog/post/19)

Source: EDINET (FSA Japan), PDL 1.0. Processed by Kabuken.

New article: compare a sector from its filings with Claude and Kabuken MCP

Illustration: four sedans in a row, each in front of its own bar; the tallest bar and the car in front of it are orange

kabuken-automakers-four-cars-revenue-bars-tile-wide.webp

kabuken-automakers-four-cars-revenue-bars-1536w.webp

Kabuken is now listed on mcpservers.org, a web catalog of MCP servers.

![Kabuken's listing page on mcpservers.org: the title 'Kabuken EDINET MCP server', a one-line description and the hosted MCP server install command](/uploads/kabuken-mcpservers-org-listing-page.webp)

MCP is a standard that lets AI apps use outside tools and data. Kabuken is an MCP server for the financials of Japanese listed companies. The figures come from EDINET filings, the disclosure system of Japan's Financial Services Agency. For each figure, Kabuken returns the source filing.

You can look up financial statements, business and geographic segments, major shareholders and the filing list for a company. Labels are in English and Japanese.

The catalog shows an install line for clients such as Claude Code and Cursor:

`npx add-mcp 'https://kabuken.intellics.ai/mcp'`

The server is read-only. It does not provide stock prices or investment advice.

[See the listing on mcpservers.org](https://mcpservers.org/servers/kabuken-intellics-ai) | [Setup guide](https://kabuken.intellics.ai/docs/en/api/connecting/?utm_source=intellics&utm_medium=news&utm_campaign=mcpservers-listing)

Source: EDINET (https://disclosure2.edinet-fsa.go.jp/), PDL1.0 (https://www.digital.go.jp/resources/open_data/public_data_license_v1.0). Processed by Kabuken.

Kabuken is now listed on mcpservers.org

Illustration: an index-card cabinet with one drawer open and an orange card inside, next to a blank hexagonal signpost

kabuken-mcpservers-index-card-cabinet-signpost-tile-wide.webp

kabuken-mcpservers-index-card-cabinet-signpost-1536w.webp

Kabuken, our platform for the financials of Japanese listed companies, is listed in Anthropic's Claude connector directory. Now it can also draw.

![Kabuken income breakdown chart for Toyota Motor's annual securities report: revenue bands on the left flow into total expenses and net profit on the right](/uploads/kabuken-toyota-income-breakdown-sankey-chart.webp)

Ask Claude for the income flow diagram of a filing. A Sankey diagram appears in the chat in Claude on the web. Revenue and other income are on the left. Costs and net profit are on the right. If the company reported a net loss, the loss is on the left.

Labels follow the language of your request, English or Japanese. Under the diagram you see the EDINET filing ID, the period, the EDINET source, the PDL 1.0 licence and "Processed by Kabuken".

Kabuken is read-only. It gives no stock prices and no investment advice.

Try this prompt: "Show me an income flow diagram of the latest annual securities report of Toyota Motor."

[See the listing in the Claude directory](https://claude.ai/directory/kabuken) | [Setup guide](https://kabuken.intellics.ai/docs/en/api/connecting/) | [Kabuken](https://kabuken.intellics.ai/?utm_source=intellics_news&utm_medium=referral&utm_campaign=claude_directory_sankey)

Source: EDINET (FSA Japan), PDL 1.0. Processed by Kabuken.

Kabuken now draws a filing's income flow inside Claude

Illustration: one flow of water runs from three stacks of reports through a sluice gate and splits into basins; the smallest basin is orange

Intellics builds AI services and mission-critical software, and helps your systems run reliably, quickly and securely.

News and announcements