suparich
Buffett-style value investing analysis as an MCP server for Claude Desktop.
Ask Claude to analyze any stock using a disciplined framework based on Warren Buffett and Charlie Munger's principles. It screens for earnings yield, ROIC, and classifies opportunities into four actionable lists.
Install
pip install suparich
Configure Claude Desktop
Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"suparich": {
"command": "suparich"
}
}
}
Restart Claude Desktop. You'll see the tools available in the MCP toolbar.
Tools
| Tool | What it does |
|---|---|
analyze_stock |
Full analysis: earnings yield + ROIC + classification + guidance |
calculate_earnings_yield |
3-year avg operating income / enterprise value (threshold: >10%) |
calculate_roic |
5-year average ROIC (>15% good, >25% wonderful) |
classify_investment |
Assigns stock to List 1-4 based on quality + price |
get_framework |
Returns the complete investing framework reference |
The Framework
Stocks are classified into four lists:
- List 1 - Good business at wonderful price (ROIC 15-25%, earnings yield >10%). Classical Graham value play, 3-5 year hold.
- List 2 - Wonderful business at fair price (ROIC >25%, fair valuation). Buy and hold forever, let quality compound.
- List 3 - FAT PITCH: wonderful business at wonderful price (ROIC >25%, earnings yield >10%). Rare. Size aggressively.
- List 4 - Wonderful business, overvalued (ROIC >25%, earnings yield <10%). Study now, buy when price drops.
If a stock doesn't pass both screens (ROIC >15% and earnings yield >10%), it's a pass.
Usage
Just ask Claude naturally:
"Analyze Apple as a value investment. Use their last 3 years of operating income and 5 years of ROIC data."
Claude will pull the financial data (via SEC EDGAR or other sources), feed it through the framework, and give you a classification with actionable guidance.
Development
git clone https://github.com/Owen-x-tech/suparich.git
cd suparich
pip install -e .
suparich # starts the MCP server (waits for stdio input)
Disclaimer
This is an educational tool implementing a value investing framework. It is not financial advice. Always do your own research before making investment decisions. Past performance does not guarantee future results.
License
MIT
Metadata
Release files for suparich 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| suparich-0.1.0.tar.gz | 7.6 kB | With provenance | Details for suparich-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| suparich-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for suparich-0.1.0-py3-none-any.whl |
Total release size: 16.2 kB
Release files / suparich-0.1.0.tar.gz
| Download URL | suparich-0.1.0.tar.gz |
|---|---|
| Size | 7.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
b23c2e39b3b9c3198f33cd92c0e7e87cf951148f517554c539b889a19c042bfa
|
|
BLAKE2b-256 checksum How to use checksums |
b1dcf6529bcd7f875d7a994bde09f775066b607cdc4b57df7fce2935d6d0d1ef
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Feb 23, 2026.
Transparency logRelease files / suparich-0.1.0-py3-none-any.whl
| Download URL | suparich-0.1.0-py3-none-any.whl |
|---|---|
| Size | 8.6 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
a9afd3756451f7d311794d6cfddadcb278cbd6f53edf63114857d977141cbd6b
|
|
BLAKE2b-256 checksum How to use checksums |
73ebd90e34db5f43a19428acdd87654b72dcf6038ae064801a5e26e8e38f1d0e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Feb 23, 2026.
Transparency logSecurity for suparich 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
Both files in this release have been uploaded with provenance metadata.
Attestation for suparich-0.1.0.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Feb 23, 2026.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.