Financial analysis AI. Forecasting, audit prep, SOX/GAAP compliance. Accuracy compounds with use.
Breakthrough financial analysis bottlenecks. AI finance that learns YOUR business metrics.
AI-powered financial analysis, budget forecasting, compliance checking, expense categorization, and risk assessment. Free tier runs ratio analysis locally. Paid tier provides LLM-powered financial modeling with SOX and GAAP compliance tracking. Every action is governed and receipted.
This MCP server returns structured JSON for seamless integration:
financial_analysis for baseline -> budget_forecast for projections -> compliance_check for SOX/GAAP -> expense_categorize for line items -> risk_assessment for exposureComposable with any MCP client: Claude Code, Cursor, VS Code, ChatGPT Desktop, Windsurf.
npx dingdawg-finance-agent
claude mcp add finance -- npx dingdawg-finance-agent
Add to .cursor/mcp.json:
{"mcpServers": {"finance": {"command": "npx", "args": ["dingdawg-finance-agent"], "env": {"DINGDAWG_API_KEY": "your-key"}}}}
npx dingdawg-setup
| Tool | Free Tier | Paid Tier |
|---|---|---|
financial_analysis | 10/day, basic ratio analysis | Unlimited, LLM-powered with industry benchmarking |
budget_forecast | 5/day, linear projection | Unlimited, AI-powered multi-scenario modeling |
compliance_check | 5/day, checklist-based SOX/GAAP | Unlimited, deep compliance with control gap analysis |
expense_categorize | 20/day, rule-based categorization | Unlimited, AI-powered with anomaly detection |
risk_assessment | 5/day, basic risk scoring | Unlimited, Monte Carlo simulation with risk factors |
Get API key: https://dingdawg.com/developers
Every call is receipted and auditable. Financial analyses reference GAAP standards and SOX control requirements. Budget forecasts include methodology disclosure. Risk assessments include confidence intervals and assumption documentation.
Source-derived launch command. Check the maintainer’s required arguments and credentials before running:
npx -y dingdawg-finance-agentMerge this template into ~/Library/Application Support/Claude/claude_desktop_config.json. Keep existing servers. Add any arguments, credentials, and permissions required by the maintainer; this template has not been install-tested.
{
"mcpServers": {
"io-github-dingdawg-dingdawg-finance-agent": {
"command": "npx",
"args": [
"-y",
"dingdawg-finance-agent"
]
}
}
}Restart Claude Desktop completely for changes to take effect. Confirm the server appears connected in the client’s tool list, then try a read-only example from its documentation.
Claude Desktop setup referencedingdawg-finance-agentnpmio.github.dingdawg/dingdawg-finance-agent works with any MCP-compatible client. Copy the config snippet from the Configuration section above and add it to the file shown for your client, then restart the application.
~/Library/Application Support/Claude/claude_desktop_config.jsonRestart Claude Desktop completely for changes to take effect.~/.cursor/mcp.jsonRestart Cursor for changes to take effect..vscode/mcp.jsonReload VS Code window for changes to take effect.~/.codeium/windsurf/mcp_config.jsonRestart Windsurf for changes to take effect..mcp.jsonSave at the project root, then start Claude Code in that project and review the MCP server approval prompt. Keep real credentials out of shared files.