About Rockmoon Financial Data
Rockmoon Financial Data is an MCP server for AI agents that need financial data across the US, Japan, and Korea, including statements, valuation, prices, segments, and ownership. Its unified schema and filing-level provenance make values traceable to SEC, EDINET, or DART filings.
Key features
- 01Company search and profiles across US, Japan, and Korea
- 02Financial statements and segment data
- 03Valuation metrics and historical data
- 04Cross-market screening, comparison, and prices
- 05Shareholder, insider, and institutional holdings
- 06Values traceable to source filings
Use cases
- 01Compare financial metrics across US, Japanese, and Korean companies
- 02Screen companies using valuation or quality criteria
- 03Review historical changes in a company's segment revenue
MCP support
Rockmoon exposes 18 financial-data tools to MCP clients. It connects over Streamable HTTP, and the same API key works with its REST and MCP interfaces.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://mcp.rockmoon.ai/mcpclaude mcp add --transport http rockmoon https://mcp.rockmoon.ai/mcp{"mcpServers":{"rockmoon":{"type":"http","url":"https://mcp.rockmoon.ai/mcp"}}}Open in Cursor{"servers":{"rockmoon":{"type":"http","url":"https://mcp.rockmoon.ai/mcp"}}}Open in VS Code{"mcpServers":{"rockmoon":{"type":"http","url":"https://mcp.rockmoon.ai/mcp"}}}{"mcpServers":{"rockmoon":{"serverUrl":"https://mcp.rockmoon.ai/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
https://mcp.rockmoon.ai/mcpAuth requiredTools
18| Parameter | Type | Required | Description |
|---|---|---|---|
| limit | integer | No | |
| query | string | Yes |
Details
From the project READMERockmoon — Cross-Market Financial Data for AI Agents (MCP)
Rockmoon is an MCP server that gives your AI agent clean, cross-market (US / Japan / Korea) financial data — financials, segments, ownership, valuation metrics and prices — where every value traces back to its source filing (SEC / EDINET / DART).
One API key works for both REST and MCP. Built MCP-native, so Claude, Cursor, and any MCP client can call it directly.
- Endpoint:
https://mcp.rockmoon.ai/mcp(Streamable HTTP) - Auth:
X-API-Key: <your key>header (also acceptsAuthorization: Bearer <key>) - Get a key: https://rockmoon.ai
- Official MCP registry:
ai.rockmoon/financial-data
Why Rockmoon
| Rockmoon | Typical "global" data APIs | |
|---|---|---|
| Asia depth (JP / KR) | Deep, cleaned, filing-grade | Shallow / auto-aggregated |
| Provenance | Every value traces to the source filing | Rarely |
| MCP-native | Yes — agents call it directly | Mostly REST-only |
| Cross-market comparability | One canonical 80-field schema | Per-vendor mess |
Most "global" data is wide but shallow in Asia. Rockmoon is the opposite: deep, clean, comparable Asia + US data your agent can cite.
Quickstart
Add to your MCP client config (Claude Desktop, Cursor, etc.):
{
"mcpServers": {
"rockmoon": {
"type": "http",
"url": "https://mcp.rockmoon.ai/mcp",
"headers": { "X-API-Key": "<YOUR_ROCKMOON_API_KEY>" }
}
}
}
Then just ask:
- "Compare gross margins of AAPL, 7203 (Toyota) and 005930 (Samsung)."
- "Screen US semiconductors by ROE."
- "Show Toyota's revenue by segment over the last 5 years."
Capabilities — 18 tools
Discovery & profile
| Tool | What it does |
|---|---|
search_companies | Resolve a ticker or name to a company across US / JP / KR |
get_company | Company profile — name, exchange, industry, GICS sector/group, regulator id |
Financials — canonical 80-field schema, traceable to filings
| Tool | What it does |
|---|---|
get_financials | Full statements bundle |
get_income_statement | Income statement, by period |
get_balance_sheet | Balance sheet, by period |
get_cash_flow | Cash-flow statement, by period |
get_segments | Revenue by product / geography / business segment |
get_segments_trend | Segment revenue over time |
Valuation & screening
| Tool | What it does |
|---|---|
get_metrics | Latest valuation + quality metrics (PE, PB, PS, EV/EBITDA, ROE, ROA, margins, market cap) |
get_metrics_history | Historical TTM metrics per period |
screen_companies | Cross-market screener — valuation/quality filters plus GICS sector / industry-group |
compare_metrics | Side-by-side metrics across tickers (cross-market) |
get_prices | Price history |
Ownership & insiders
| Tool | What it does |
|---|---|
get_major_shareholders | Major shareholders |
get_director_holdings | Director / officer holdings |
get_insider_trades | Insider transactions |
get_institutional_holdings | Institutional holdings |
get_large_holdings_events | Large-holding change events |
Provenance you can cite
Every financial value is backed by raw XBRL provenance with ASC / IFRS / Reg S-X citations, exposed via the REST /v1/trace/ surface — so an agent can show exactly where a number came from. No black-box numbers.
Links
- Website / get an API key — https://rockmoon.ai
- Official MCP registry —
ai.rockmoon/financial-data
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.