Skip to main content

Fintools

PyPI version License: MIT

Fintools gives AI assistants a local market-analysis toolbelt: computed quotes, trend context, technical levels, screens, options context, sizing math, candidate ranking, and repeatable playbooks.

The public package in this repository is a lightweight connector and documentation hub. It lets Claude, Codex, Cursor, or another MCP-compatible assistant prove that Fintools can run locally and fetch basic quote data. The full Fintools MCP package is a paid local download that contains the complete read-only market-analysis desk.

Fintools is not a broker, signal service, hedge fund, raw-data vendor, or investment adviser. It does not place trades. The point is simple: the AI writes around tool output instead of inventing market numbers.

What Fintools MCP Includes

The paid Fintools MCP package includes the full local toolbelt:

Area Tools
Market / price context get_stock_quote, get_market_snapshot
Technical analysis get_technical_indicators, get_trend_score, get_support_resistance
Screening / ranking screen_stocks, find_breakouts, winner_similarity_scan, compare_tickers
Options context analyze_options_chain, get_option_quote
Risk / sizing calculate_position_size, calculate_atr_position
Trade analytics analyze_trades
Ops / data source get_data_source_stats

The buyer package also includes playbooks, sample reports, setup notes, guardrails, and report structure so the assistant gives useful market context with explicit caveats.

Get Fintools MCP:

https://whop.com/fintools/fintools-mcp/

Founding code:

FOUNDING

Public Connector Quick Start

The public connector is useful for testing MCP wiring before buying or installing the full package.

pip install fintools-mcp

Add it to Claude Code:

claude mcp add fintools -- uv run --from fintools-mcp fintools-mcp

Ask:

Check the Fintools connection.

Then ask:

Get a basic quote for SPY.

If you ask the public connector for the full market-analysis toolbelt, it returns upgrade_required instead of pretending to compute something it does not include.

Docs

Page What it covers
Introduction What Fintools is, what it is not, and why it exists
Quick Start Install the public connector, connect an MCP client, and verify the setup
Paid Package What ships in the paid Fintools MCP package
Guardrails Read-only design, no trade recommendations, and "not checked" caveats
MCP Setup Claude Code, Claude Desktop, Cursor-style MCP config, and reload checks
Media Kit Screenshot and demo-clip checklist for GitHub, Whop, and launch posts

Guides

Guide What it shows
Market Health Check Asking about broad market context without hallucinated numbers
Candidate Scan Finding and triaging names with Fintools MCP workflows
Watchlist Review Reviewing existing names and surfacing what changed
Options Context Separating market setup from options-chain context

Broker Boundary

Fintools is broker-agnostic. Users can layer their own broker API, broker MCP, or account system into the same AI assistant workflow for live account data, positions, executable quotes, options-chain vetting, order routing, fills, and realized P&L. That broker layer is separate from Fintools.

Use Fintools for market context and research. Use your broker API/MCP or account system for broker truth and any execution workflow. Fintools itself remains read-only and does not place trades.

Development

git clone https://github.com/slimbiggins007/fintools-mcp.git
cd fintools-mcp
uv sync
uv run python -m fintools_mcp
uv run pytest

License

The public connector in this repository is MIT licensed. The paid Fintools MCP package is distributed separately.

Metadata

Release files for fintools-mcp 0.6.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for fintools-mcp 0.6.2
File Size Uploaded Provenance
fintools_mcp-0.6.2.tar.gz 346.8 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for fintools-mcp 0.6.2
File Interpreter ABI Platform
fintools_mcp-0.6.2-py3-none-any.whl Python 3 none any Details

Total release size: 356.6 kB

Release files / fintools_mcp-0.6.2.tar.gz

Download URL fintools_mcp-0.6.2.tar.gz
Size 346.8 kB
Tags Source
SHA-256 checksum
How to use checksums
91395ffa6732702b5de9a93576dfb7552d9698797783ceb011c86d4daaf68c44
BLAKE2b-256 checksum
How to use checksums
8d80dc2bd95f4c269a4858d240e4c805ab245037cba8c411974af6fcca873786
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.11.14 {"installer":{"name":"uv","version":"0.11.14","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

Release files / fintools_mcp-0.6.2-py3-none-any.whl

Download URL fintools_mcp-0.6.2-py3-none-any.whl
Size 9.8 kB
Tags Python 3
SHA-256 checksum
How to use checksums
b38d7a9c23acda63a87d8a4f4298a13b01e7479b60c95595c7158d7d6acf9089
BLAKE2b-256 checksum
How to use checksums
2c54faff831951acf98526fe6838ad9ad050a798e738587b1fe8a9c055e093ea
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.11.14 {"installer":{"name":"uv","version":"0.11.14","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

Security for fintools-mcp 0.6.2

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.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A 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.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page