WorldQuant BRAIN MCP Server
Minimal MCP server for WorldQuant BRAIN platform integration with Claude Code.
Features
- Complete BRAIN platform API integration (alphas, simulations, data)
- Forum access (glossary, search, posts)
- Biometric authentication support
- Browser automation for complex workflows
- Flexible credential management (env vars or system keyring)
Setup
1. Install Package
pip install -e .
# Install Playwright browser
python3 -m playwright install chromium
2. Configure Credentials
The server checks credentials in this order:
- Environment variables (
WQB_EMAIL,WQB_PASSWORD) - System keyring (macOS Keychain / Windows Credential Locker)
Choose one of the following methods:
Method 1: Environment variables via claude mcp add (recommended)
This registers the server and configures credentials in one step:
claude mcp add wqb-mcp -e WQB_EMAIL=you@example.com -e WQB_PASSWORD=yourpass -- python3 -m wqb_mcp.server
Method 2: System keyring
wqb-mcp-setup
3. Register MCP Server
Only needed if using Method 2 (Method 1 already registers the server).
Note: Use
python3(notpython) to ensure the correct interpreter is used when Claude Code spawns the process. Shell aliases don't work in non-interactive subprocesses.
claude mcp add wqb-mcp -- python3 -m wqb_mcp.server
4. Verify & Restart
# Check server connects
claude mcp list
# Restart Claude Code
exit
claude
Package Structure
wqb-mcp/
├── src/
│ └── wqb_mcp/
│ ├── __init__.py
│ ├── server.py # Entry point (auto-prompts setup on first run)
│ ├── setup.py # CLI credential setup
│ ├── models.py # Pydantic models
│ ├── config.py # Credential management (env vars + keyring)
│ ├── forum.py # Forum scraper (Playwright)
│ ├── client/
│ │ ├── __init__.py # BrainApiClient (composed from mixins)
│ │ ├── auth.py # Authentication
│ │ ├── simulation.py # Simulations
│ │ ├── alpha.py # Alpha management
│ │ ├── correlation.py # Correlation checks
│ │ ├── data.py # Datasets & datafields
│ │ ├── diversity.py # Diversity scoring
│ │ ├── community.py # Events, competitions
│ │ ├── user.py # Profile, messages, pyramids
│ │ ├── operators.py # Operators & selection
│ │ └── platform_config.py # Platform settings
│ └── tools/
│ ├── __init__.py # FastMCP instance
│ ├── auth_tools.py
│ ├── simulation_tools.py
│ ├── alpha_tools.py
│ ├── correlation_tools.py
│ ├── data_tools.py
│ ├── community_tools.py
│ ├── user_tools.py
│ ├── forum_tools.py
│ └── operators_tools.py
├── pyproject.toml
├── requirements.txt
└── README.md
Usage
Once configured, the MCP server provides tools for:
- Alphas: Create, simulate, submit
- Data: Fetch market data, fundamentals
- Simulations: Run backtests, analyze results
- Forum: Search docs, get glossary terms
- Account: Manage profile, settings
Troubleshooting
MCP shows "failed" status
- Check credentials are configured (see step 2 above)
- Make sure you used
python3notpythoninclaude mcp add - Run debug mode to see errors:
claude --debug
Playwright errors
Reinstall browser:
python3 -m playwright install chromium
Metadata
Release files for wqb-mcp 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 | |
|---|---|---|---|
| wqb_mcp-0.1.0.tar.gz | 36.0 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| wqb_mcp-0.1.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 81.7 kB
Release files / wqb_mcp-0.1.0.tar.gz
| Download URL | wqb_mcp-0.1.0.tar.gz |
|---|---|
| Size | 36.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
9c10c337d12a69519c5ab786137403a889a01df4c05b7d7c958b97640c2719af
|
|
BLAKE2b-256 checksum How to use checksums |
95997f60f5632da231aaf62525ee69472ff7a5750656b3cd785d059bd75fec40
|
| 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 14, 2026.
Transparency logRelease files / wqb_mcp-0.1.0-py3-none-any.whl
| Download URL | wqb_mcp-0.1.0-py3-none-any.whl |
|---|---|
| Size | 45.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
b4f7d64496a331b62304025395d9ca71474833280fa996bc24b91ef6597b0c31
|
|
BLAKE2b-256 checksum How to use checksums |
61b795a5ebd3b24d3baaee282d0ad9158c38a050907e4b0dcee64b2abbf60e64
|
| 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 14, 2026.
Transparency log