Skip to main content

tdnet-disclosure-mcp

CI PyPI version Python 3.10+ License: Apache-2.0

Model Context Protocol (MCP) server for TDNET timely disclosures (適時開示) from the Tokyo Stock Exchange (JPX/TSE). Access earnings reports (決算短信), dividend announcements, buyback disclosures, forecast revisions, and more — no API key required.

Part of the Japan Finance Data Stack: edinet-mcp (securities filings) | tdnet-disclosure-mcp (timely disclosures) | estat-mcp (government statistics) | stockprice-mcp (stock prices & FX)

Features

  • 4 MCP Tools: get_latest_disclosures, search_disclosures, get_company_disclosures, get_disclosures_by_date
  • No authentication required - uses free public API
  • Auto-categorization: earnings (決算短信), dividends, forecast revisions, buybacks, governance
  • CLI: latest, search, company, by-date, test, serve

Installation

pip install tdnet-disclosure-mcp

Configuration

No API key required. Add to Claude Desktop config:

{
  "mcpServers": {
    "tdnet": {
      "command": "uvx",
      "args": ["tdnet-disclosure-mcp", "serve"]
    }
  }
}

CLI Usage

# Get latest disclosures
tdnet-disclosure-mcp latest
tdnet-disclosure-mcp latest --limit 50

# Search disclosures
tdnet-disclosure-mcp search "トヨタ"
tdnet-disclosure-mcp search "決算短信"

# Get company disclosures
tdnet-disclosure-mcp company 7203

# Get disclosures by date
tdnet-disclosure-mcp by-date 2026-02-14

# Test API connection
tdnet-disclosure-mcp test

# Start MCP server
tdnet-disclosure-mcp serve

MCP Tools

get_latest_disclosures

Get the most recent TDNET disclosures.

Parameters:

  • limit: Maximum results (1-300, default: 50)

search_disclosures

Search by keyword (company name, stock code, or title).

Parameters:

  • keyword: Search keyword
  • limit: Maximum results (1-100, default: 20)

get_company_disclosures

Get disclosures for a specific company.

Parameters:

  • code: 4-digit stock code
  • limit: Maximum results (1-300, default: 50)

get_disclosures_by_date

Get all disclosures for a specific date.

Parameters:

  • target_date: Date in YYYY-MM-DD format

Disclosure Categories

Category Japanese Examples
earnings 決算短信 Quarterly/annual earnings reports
dividend 配当 Dividend changes
forecast_revision 業績予想修正 Earnings forecast revisions
buyback 自社株買い Share buyback announcements
offering 増資/新株 Stock offerings
governance ガバナンス Corporate governance, board changes
other その他 Other disclosures

Data Attribution & Disclaimer

Data provided by Yanoshin Web API. Not affiliated with JPX/TSE or Yanoshin. Verify against official TDNET sources.

License

Apache-2.0

Metadata

Release files for tdnet-disclosure-mcp 0.2.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for tdnet-disclosure-mcp 0.2.1
File Size Uploaded Provenance Actions
tdnet_disclosure_mcp-0.2.1.tar.gz 133.1 kB With provenance Details for tdnet_disclosure_mcp-0.2.1.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for tdnet-disclosure-mcp 0.2.1
File Interpreter ABI Platform Actions
tdnet_disclosure_mcp-0.2.1-py3-none-any.whl Python 3 none any Details for tdnet_disclosure_mcp-0.2.1-py3-none-any.whl

Total release size: 149.7 kB

Release files / tdnet_disclosure_mcp-0.2.1.tar.gz

Download URL tdnet_disclosure_mcp-0.2.1.tar.gz
Size 133.1 kB
Tags Source
SHA-256 checksum
How to use checksums
62a0ba6c79aa88f60b47ed7c2594fe84a54b61a9c23a5076ca57c131be0e4d95
BLAKE2b-256 checksum
How to use checksums
627ae49545d91acdedac58b7d39234d8b67651681491f0e1a10247a400c668d5
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 23, 2026.

Transparency log

Release files / tdnet_disclosure_mcp-0.2.1-py3-none-any.whl

Download URL tdnet_disclosure_mcp-0.2.1-py3-none-any.whl
Size 16.5 kB
Tags Python 3
SHA-256 checksum
How to use checksums
fb508baadcd3678f1e91b75db84b4be87edaa3b2e7c3c6db8080dfd8aa094685
BLAKE2b-256 checksum
How to use checksums
41fc1e6b6502932cf8d494813afce4db6d08a92fb60379132059fe441a26f9e8
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 23, 2026.

Transparency log

Security for tdnet-disclosure-mcp 0.2.1

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Full provenance

All 2 files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for tdnet_disclosure_mcp-0.2.1.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 23, 2026.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page