Skip to main content

utss-mcp

MCP (Model Context Protocol) server for building and backtesting UTSS trading strategies with Claude.

Installation

pip install utss-mcp

Usage with Claude Code

Add to your Claude Code MCP configuration:

{
  "mcpServers": {
    "utss": {
      "command": "utss-mcp",
      "args": []
    }
  }
}

Then use in Claude Code:

You: Help me build a mean reversion strategy for tech stocks

Claude: I'll help you build that strategy. Let me start the interactive builder.
        [calls build_strategy]

        What type of strategy would you like?
        1. Mean Reversion - Buy oversold, sell overbought
        2. Trend Following - Follow market direction
        3. Breakout - Trade price breakouts
        4. Calendar-based - Trade on day/week patterns

You: 1

Claude: [calls build_strategy with session_id]

        Which indicator should trigger entry?
        1. RSI - Relative Strength Index
        2. Stochastic - Stochastic Oscillator
        3. Williams %R
        ...

Available Tools

build_strategy

Build a trading strategy interactively through guided questions.

await build_strategy(
    prompt="I want a mean reversion strategy",
    session_id=None,  # Omit for new session
)

validate_strategy

Validate a UTSS strategy YAML.

await validate_strategy(strategy_yaml="info:\n  id: test\n...")

backtest_strategy

Run a backtest simulation.

await backtest_strategy(
    strategy_yaml="...",
    symbol="AAPL",
    start_date="2023-01-01",
    end_date="2024-01-01",
    initial_capital=100000,
)

list_indicators

List all supported technical indicators.

await list_indicators()

Development

# Install in development mode
uv sync

# Run tests
uv run pytest packages/utss-mcp/tests

# Run server directly
uv run utss-mcp

License

MIT

Metadata

Release files for utss-mcp 0.2.0

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

Source distribution (sdist)

Source distribution for utss-mcp 0.2.0
File Size Uploaded Provenance
utss_mcp-0.2.0.tar.gz 6.3 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for utss-mcp 0.2.0
File Interpreter ABI Platform
utss_mcp-0.2.0-py3-none-any.whl Python 3 none any Details

Total release size: 14.0 kB

Release files / utss_mcp-0.2.0.tar.gz

Download URL utss_mcp-0.2.0.tar.gz
Size 6.3 kB
Tags Source
SHA-256 checksum
How to use checksums
aa17a26e0549b11a67fcf8b798647b783fae57951819733768dd64d7beff1953
BLAKE2b-256 checksum
How to use checksums
187345e6bc6252db7efc1fa1250fc3566de31bc199a52a4517c6db6719201f4c
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.11.0

Release files / utss_mcp-0.2.0-py3-none-any.whl

Download URL utss_mcp-0.2.0-py3-none-any.whl
Size 7.6 kB
Tags Python 3
SHA-256 checksum
How to use checksums
6665d367292e7899cd09e22ebc405a224aba8e0a7b15d0d03d05771622e1d287
BLAKE2b-256 checksum
How to use checksums
b3e79351572264f589d962fe7bf7ec9a66ac3219a10f3c7d9e780a5b0ea7d6e3
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.11.0

Security for utss-mcp 0.2.0

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.

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.

Release history Release notifications | RSS feed

This release

0.2.0 This release

2 release files No provenance

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