edinet-mcp for Openclaw

Analyze Japanese public company financial statements from EDINET using 161 normalized XBRL labels.

ajtgjmdjp
v0.6.0
Feb 15, 2026
0
2k
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install edinet-mcp

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install edinet-mcp using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is edinet-mcp?

The edinet-mcp skill is a specialized technical bridge designed to connect AI agents with the Japanese Financial Services Agency (FSA) EDINET system. By incorporating this into your personal library of Openclaw Skills, you gain the ability to programmatically parse and analyze complex XBRL data from Japanese securities filings. This includes support for Income Statements, Balance Sheets, and Cash Flow Statements across major accounting standards such as J-GAAP, IFRS, and US-GAAP.

This skill excels at normalizing 161 distinct financial labels, ensuring that data retrieved from different companies or periods remains consistent and comparable. Whether you are conducting equity research or building automated financial monitors, this addition to your Openclaw Skills collection provides a robust interface for Japanese market intelligence.

edinet-mcp Use Cases

  • Search for any Japanese public company using its Japanese name, English name, or stock code
  • Retrieve and normalize Income Statements (PL) to analyze revenue and profit trends
  • Extract Balance Sheet (BS) data to evaluate corporate solvency and asset composition
  • Review Cash Flow (CF) statements to understand operating, investing, and financing activities
  • Screen and compare financial metrics like ROE and profit margins across a basket of up to 20 companies

How edinet-mcp Works

  1. Identify a target company by searching the EDINET database using a name or stock code to retrieve its unique EDINET code.
  2. Specify the desired filing year and statement type (Income Statement, Balance Sheet, or Cash Flow Statement).
  3. The skill fetches the raw XBRL data from the official EDINET API and applies normalization logic across 161 standard labels.
  4. Results are processed into structured JSON or CSV formats, including both current and prior period data for immediate comparison.
  5. For screening tasks, the skill aggregates data from multiple companies to provide a comparative financial overview.

edinet-mcp Setup

To use this tool within the Openclaw Skills framework, you must first obtain a free API key from the EDINET portal. Once you have the key, configure your environment and install the package:

# Set your API key
export EDINET_API_KEY='your_api_key_here'

# Install the tool using uv or pip
uv tool install edinet-mcp

Verify your connection to the EDINET servers with the test command:

edinet-mcp test

edinet-mcp Data Schema & Taxonomy

The skill organizes financial data into three main schemas with normalized taxonomies. Each record includes current and prior period values:

Schema Type Japanese Name Core Metrics Included
income_statement 損益計算書 (PL) Net Sales, Operating Profit, Net Income
balance_sheet 貸借対照表 (BS) Total Assets, Net Assets, Liabilities
cash_flow_statement キャッシュ・フロー計算書 (CF) Operating CF, Investing CF, Financing CF

Data can be exported in JSON for programmatic use or CSV for traditional data analysis workflows.

edinet-mcp Advanced Features

  • Normalization of 161 labels across J-GAAP, IFRS, and US-GAAP accounting standards
  • Automated handling of XBRL-diffs to identify changes between filing periods
  • Multi-company screening support allowing side-by-side comparison for up to 20 entities
  • Built-in rate limiting (0.5 requests per second) to ensure stable API consumption and compliance
  • Support for both Japanese and English search queries for stock discovery

SKILL.md


Loading

Related Openclaw Skills

METADATA

Requires
Bins edinet-mcp
Github Stars: 0
forks: 0

Featured*