Skip to main content
Glama
JPX Disclosures

JPX Disclosures

by pipeworx-io

@pipeworx/jpx-disclosures

Tokyo Stock Exchange timely disclosures (適時開示) by company code or across the market for a date window, plus the Japan Exchange Group listed-company record (name, market segment, sector, size class). Read live from the exchange per request; nothing is stored.

Part of Pipeworx — an MCP gateway connecting AI agents to 2016+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

  • jpx_announcements(code?, date_from?, date_to?, category?, keyword?, limit?) - disclosures newest first: date and time (JST), securities code, company, title in Japanese, a derived category (results, forecast_revision, dividend, buyback, share_issue, officers_governance, corporate_action, shareholder_meeting, correction, other), listing exchange, and links to the document (PDF) and XBRL where one exists. Up to 8 days per call (a week, both end dates included).

  • jpx_company(code? | name?, limit?) - the listed-issuer record for a 4-character securities code, or a name search in Japanese: name, market segment (Prime, Standard, Growth, ETF/ETN and others), 33-sector and 17-sector classification, TOPIX size class.

Related MCP server: kabu-mcp

Auth

Keyless.

Data sources

  • Tokyo Stock Exchange (JPX), timely disclosure service - the exchange's free public window of daily disclosure lists.

  • Japan Exchange Group, list of listed issuers - the exchange's monthly list of listed companies.

Notes for the next person:

  • The exchange's free disclosure service keeps only about the most recent month. Older dates come back as days_outside_free_window and, if nothing else matched, an empty_reason; they are never an empty success.

  • A day with no disclosures (weekend, holiday) is reported in days_with_no_disclosures. Today's list fills in through the evening (JST).

  • Company names are shown the way the service prints them (the exchange truncates long names, e.g. "トヨタ自") and are normalised from full-width to standard width. Codes are 4 characters; the service uses a 5-character form ending in 0, returned as tdnet_code.

  • Categories are derived from the Japanese title, not published by the exchange.

  • The listed-issuer list is Japanese only: no English name and no listing date, so name_en and listing_date are always null. list_as_of is the date printed on the list.

  • A filter by code reads every list page for each day in the window (100 rows a page, about 20 pages on a busy day); a call reads at most 80 pages and says so (truncated) when it stops early.

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "jpx-disclosures": {
      "url": "https://gateway.pipeworx.io/jpx-disclosures/mcp"
    }
  }
}

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/jpx-disclosures/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — ask_pipeworx, discover_tools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask_pipeworx, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}

Both URLs reach the same gateway and the same 2016+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

curl -X POST https://gateway.pipeworx.io/v1/tools/jpx_announcements \
  -H 'Content-Type: application/json' \
  -d '{"code":"7203","date_from":"2026-11-05","date_to":"2026-11-05","limit":10}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/jpx_announcements. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.

Run it from npm

@pipeworx/mcp-jpx-disclosures is a local stdio bridge to the Pipeworx gateway: your MCP client starts it with npx, and it forwards every call to the same https://gateway.pipeworx.io/jpx-disclosures/mcp endpoint shown above. It needs network access; there is no offline mode.

{
  "mcpServers": {
    "jpx-disclosures": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-jpx-disclosures"]
    }
  }
}

Without a key it calls anonymously, capped at 50 calls a day. A free account raises that to 200 a day: get a key at https://pipeworx.io/signup and add "env": { "PIPEWORX_API_KEY": "<your key>" } to the server entry. The key is sent as a Bearer token, the same way a hosted connection sends it, so calls are metered and billed exactly as they are there.

It lists only this pack's tools by default. Set PIPEWORX_META_TOOLS=1 to also list ask_pipeworx and the other gateway-wide tools.

Behind an HTTPS proxy: Node's built-in fetch does not read HTTPS_PROXY by default. Newer Node releases honour it when NODE_USE_ENV_PROXY=1 is set; check your Node version's documentation.

Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:

ask_pipeworx({ question: "your question about Jpx Disclosures data" })

The gateway picks the right tool and fills the arguments automatically.

More

License

MIT

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Provides programmatic access to Japan's EDINET system to search for listed companies and retrieve annual or quarterly financial reports. It parses XBRL filings into structured data, enabling AI assistants to analyze balance sheets, income statements, and cash flows.
      182 PyPI
      20
      Apache 2.0
    • A
      license
      B
      quality
      D
      maintenance
      Enables AI assistants to access real-time Japanese and global stock market data, including quotes, charts, technical analysis, and market screening.
      7
      12 npm
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables searching for Japanese companies and retrieving their securities filings from Japan's Financial Services Agency, including daily filing lists and historical filing ranges for specific filers.
      157 npm
      MIT