FinanceToolkit
Enables engineering teams building fintech products or financial systems to integrate transparent, auditable financial calculations without building custom l…
Python toolkit that calculates 200+ financial ratios, indicators, and performance measurements from 30+ years of financial statements, with transparent, open-source calculation methods. Also ships an official MCP server so Claude and other MCP clients can query the same 200+ metrics in plain English — hosted (OAuth, nothing to install) or run locally, plus an MCPB bundle for Claude Desktop.
- Generate financial ratios and metrics from raw balance sheet data automatically
- Ask Claude to explain what declining cash flow trends mean for your business
- Analyze historical stock performance and valuation multiples in seconds
Enables engineering teams building fintech products or financial systems to integrate transparent, auditable financial calculations without building custom libraries from scratch, reducing time-to-market and compliance risk.
Financial software engineers and data teams building analytics dashboards or transaction processing systems requiring standardized, reproducible financial computations.
https://github.com/JerBouma/FinanceToolkit
By JerBouma
How to Get It
pip install financetoolkit -U # Python library; MCP server (local): uvx --from "financetoolkit[mcp]" financetoolkit-mcp-setup; or connect hosted: https://financetoolkit.jeroenbouma.com/mcp
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
After installing, paste this into Claude:
Help me generate financial ratios and metrics from raw balance sheet data automatically
Trust Signals Auto-scanned
Community Pulse Growing
Discussed on Hacker News
- Work with First, Second and Third Order Greeks Through the Finance Toolkit — Hacker News · 2 pts
- Get Financial Data of 345 Companies Within 40 Seconds with the FinanceToolkit — Hacker News · 1 pts
- Factor Investing now available within the Finance Toolkit for FREE — Hacker News · 1 pts
3 mentions across 1 sources
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 4,991 GitHub stars; contributors unknown; last commit 0d ago; license MIT.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 4,991 GitHub stars; contributors unknown; last commit 0d ago; license MIT.