Edinet MCP
Access Japanese financial disclosures (EDINET).
Connector by ajtgjmdjp · GitHub account verified by the MCP Registry
Chalk Labs
Need help deploying Edinet MCP?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.
npx agentmarket install connector/ajtgjmdjp-edinet-mcp
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 25, 2026.
- Tools
- 11 read · 0 write · 0 deleteRead-only
- Secrets
- 1 (API keys, tokens or passwords)
- Install scripts
- None found
- Runs as
- Python package
Tools by what they do 11
Read from the source code; the running server may list different tools.
Read 11 · Look things up without changing anything.
compare_financial_periodsdiff_financial_statementsget_company_infoget_filingsget_financial_metricsget_financial_statementsget_narrativeget_receiptslist_available_labelsscreen_companiessearch_companies
Secrets and settings it asks for
Secrets: values you paste in that let it act as you.
EDINET_API_KEY
Network hosts it talks to 6
api.edinet-fsa.go.jp· found in codedisclosure.edinet-fsa.go.jp· found in codedisclosure2dl.edinet-fsa.go.jp· found in codegithub.com· found in codeglama.ai· found in codexbrl.org· found in code
Files it touches
- Your home directory (~)
~/.cache/edinet-mcp
Tools (11)
Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].
compare_financial_periodsCompare financial data between current and previous periods. Returns year-over-year changes (増減額 and 増減率) for all items that have both 当期 and 前期 data. Example: compare_financial_periods("E02144") → { "changes": [ {"科目": "売上高", "当期": 45095325, "前期": 37154298, "増減率": "+21.38%"}, ... ] }
diff_financial_statementsCompare financial statements for the same company across two periods. Calculates changes (増減額) and growth rates (増減率) for each line item in the income statement, balance sheet, and cash flow statement. Useful for analyzing year-over-year performance changes. Example: diff_financial_statements("E02144", "2024", "2025") → { "edinet_code": "E02144", "company_name": "トヨタ自動車株式会社", "period1": "2024", "period2": "2025", "diffs": [ {"statement": "income_statement", "科目": "売上高", "増減額": 7941025000000, "増減率": "+21.38%"}, ... ], "summary": {"total_items": 45, "increased": 30,…
get_company_infoGet detailed information about a company by EDINET code.
get_filingsList financial filings for a company within a date range. Returns filing metadata including doc_id, filing date, and document type. To retrieve the actual data, call get_financial_statements with the edinet_code and the filing year as period (doc_id is informational).
get_financial_metricsCalculate key financial metrics (ROE, ROA, profit margins, etc.). Returns profitability ratios, stability ratios, and cash flow summary computed from the company's financial statements. Example: get_financial_metrics("E02144") → { "profitability": {"営業利益率": "11.87%", "ROE": "12.50%", ...}, "stability": {"自己資本比率": "41.60%", ...}, "cash_flow": {"営業CF": 5000000, "フリーCF": 3000000, ...} }
get_financial_statementsRetrieve and parse financial statements (BS, PL, CF) for a company. Returns normalized financial data. With language='ja' (default), each line item has 科目 (label), 当期 (current) and 前期 (previous) values. With language='en', rows use English keys and line item names. Example response (ja): income_statement: [{"科目": "売上高", "当期": 45095325, "前期": 37154298}, ...] Example response (en): income_statement: [{"label": "Revenue", "current": 45095325, "prior": 37154298}, ...] Note: with language='en', only normalized rows are translated. Rows that were not normalized (the 'summary' statement, or fi…
get_narrativeGet a qualitative narrative section from a company's annual report. Extracts sections like 事業等のリスク or MD&A from the 有価証券報告書 as plain text. Annual reports (有価証券報告書) only. Long sections are paged: if 'truncated' is true, call again with offset='next_offset' to continue reading.
get_receiptsGet machine-verifiable evidence receipts for key financial figures. Each receipt binds a number to the exact byte range of the original EDINET filing (source hash + locator + content-hash id, er/0.2 schema). Receipts can be independently verified with the xbrl-facts verifier — tampering with either the source or the claim fails verification. Requires the optional dependency: pip install edinet-mcp[receipts]
list_available_labelsList all available financial line item labels for a statement type. Use this to discover which labels (科目) are available when accessing financial data via get_financial_statements. Returns labels in display order with Japanese and English names.
screen_companiesCompare financial metrics across multiple companies. Fetches financial statements for each company, calculates key metrics (ROE, ROA, profit margins, etc.), and returns a comparison table. Useful for sector analysis, portfolio comparison, and screening. Maximum 20 companies per request (rate limit constraint). Example: screen_companies(["E02144", "E01777"]) → { "results": [ {"edinet_code": "E02144", "company_name": "トヨタ...", "profitability": {...}, ...}, {"edinet_code": "E01777", "company_name": "ソニー...", "profitability": {...}, ...} ], "errors": [], "count": 2 }
search_companiesSearch for Japanese companies registered in EDINET. Examples: - search_companies("トヨタ") → Toyota Motor Corporation - search_companies("7203") → Toyota (by ticker) - search_companies("E02144") → Toyota (by EDINET code)
Signals
- Stars
- 19
- Forks
- 7
- Open issues
- 6
- Weekly downloads
- 243
- Last commit
- Aug 23, 2026 (2 months ago)
- Last release
- Aug 23, 2026 (2 months ago)
- Last package publish
- Aug 23, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026) and the package registry.
Details
- Registry name
io.github.ajtgjmdjp/edinet-mcp- Version
- 0.4.1
- Auth
- API key
- Packages
- pypi edinet-mcp
- License
- Apache-2.0
- Repository
- github.com/ajtgjmdjp/edinet-mcp
- First seen
- Oct 24, 2026
- Last checked
- Oct 25, 2026
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get Edinet MCP running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
Edinet MCP. Agent Mart. https://agentmart.dev/connectors/ajtgjmdjp-edinet-mcp (last updated 2026-10-25)