japanfinance-agent
Compound MCP agent that integrates EDINET, TDNET, e-Stat, and stock price sources for comprehensive Japanese company analysis, macro economic snapshots, and earnings monitoring through a single interface.
README
japanfinance-agent
Status: Maintenance mode — This project is stable and functional but not actively developed. Issues and PRs are welcome.
Compound MCP agent that combines Japan finance data sources into high-value analysis tools. Instead of calling each source individually, get comprehensive company analysis, macro snapshots, and earnings monitoring in a single request.
Part of the Japan Finance Data Stack: edinet-mcp (securities filings) | tdnet-disclosure-mcp (timely disclosures) | estat-mcp (government statistics) | stockprice-mcp (stock prices)
Why?
Each Japan finance MCP provides focused data from one source. But real analysis needs multiple sources combined:
| What you want | Without japanfinance-agent | With japanfinance-agent |
|---|---|---|
| Company analysis | 3 sequential MCP calls (EDINET → TDNET → stock) | analyze 7203 |
| Macro overview | e-Stat search + result aggregation | macro -k GDP |
| Earnings watchlist | N × TDNET calls for N companies | monitor 7203 6758 6861 |
Installation
# Core only (brings no data sources)
pip install japanfinance-agent
# With all data sources
pip install "japanfinance-agent[all]"
# Pick specific sources
pip install "japanfinance-agent[edinet,tdnet,news]"
Available extras: edinet, tdnet, estat, stock, all
Configuration
Add to Claude Desktop config:
{
"mcpServers": {
"japanfinance": {
"command": "uvx",
"args": ["japanfinance-agent[all]", "serve"],
"env": {
"EDINET_API_KEY": "your_edinet_key",
"ESTAT_APP_ID": "your_estat_app_id"
}
}
}
}
Then ask: "トヨタの財務分析をして" or "日本のGDP関連の最新データを見せて"
MCP Tools
| Tool | Description |
|---|---|
analyze_japanese_company |
企業の包括分析(EDINET財務 + TDNET開示 + 株価) |
get_macro_snapshot |
マクロ経済スナップショット(e-Stat 政府統計) |
monitor_earnings |
複数企業の決算・開示モニタリング |
check_data_sources |
データソースの接続状況を確認 |
CLI Usage
# Analyze a company (EDINET + TDNET + stock)
japanfinance-agent analyze 7203
japanfinance-agent analyze 7203 -e E02144 -p 2025 --json-output
# Macro economic snapshot (e-Stat)
japanfinance-agent macro
japanfinance-agent macro -k CPI
# Monitor earnings for a watchlist
japanfinance-agent monitor 7203 6758 6861
# Check which data sources are available
japanfinance-agent test
# Start MCP server
japanfinance-agent serve
Architecture
japanfinance-agent
├── analyze_company(code) → EDINET + TDNET + stock (parallel)
├── macro_snapshot(keyword) → e-Stat government statistics
├── earnings_monitor(codes[]) → TDNET × N companies (parallel)
└── check_data_sources() → connectivity status
Adapters (graceful degradation — missing packages return empty results):
├── edinet-mcp → Financial statements, metrics, company search
├── tdnet-mcp → Timely disclosures (earnings, dividends, buybacks)
├── estat-mcp → Government statistics (GDP, CPI, employment)
└── stockprice-mcp → Stock prices & FX (via yfinance)
Data Sources
| Source | Auth | Data |
|---|---|---|
| EDINET | API key (free) | Securities filings, XBRL financial statements |
| TDNET | None | Timely disclosures (earnings, dividends) |
| e-Stat | App ID (free) | Government statistics (GDP, CPI, employment) |
| yfinance | None | Stock prices & market data |
License
Apache-2.0
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.