Wfgy Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Wfgy Mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Real $1M-level reasoning through MCP protocol integration with Augment
This repository contains an enhanced version of the WFGY (What's For Generating You) project with full Model Context Protocol (MCP) integration for Augment compatibility.
Access to 16 structured WFGY problems with specific fixes:
| # | Problem | Category | Modules | Status |
|---|---|---|---|---|
| 1 | Hallucination & Chunk Drift | IN | BBCR, BBMC | ✅ Stable |
| 2 | Interpretation Collapse | RE | BBCR | ✅ Stable |
| 3 | Long Reasoning Chains | RE | BBMC, Tree | ✅ Stable |
| 4 | Bluffing / Overconfidence | RE | BBCR, λ_observe | ✅ Stable |
| 5 | Semantic ≠ Embedding | IN | BBMC, BBAM | ✅ Stable |
| 6 | Logic Collapse & Recovery | RE | BBCR, BBPF | ✅ Stable |
| 7 | Memory Breaks Across Sessions | ST | Tree, BBMC | ✅ Stable |
| 8 | Multi-Agent Role Drift | ST | BBCR, BBPF | ✅ Stable |
# Clone your repository
git clone https://github.com/YOUR_USERNAME/WFGY-MCP.git
cd WFGY-MCP
# Start the MCP server
docker compose up -d
# Server runs on http://localhost:8052Add to your Augment MCP configuration:
{
"mcpServers": {
"wfgy": {
"command": "docker",
"args": ["exec", "wfgy-wfgy-1", "python", "-m", "wfgy_mcp.server"],
"env": {}
}
}
}# Example: Diagnose AI problems
wfgy_problemmap_diagnose(symptoms="hallucination and wrong content")
# Example: Analyze workflow stability
wfgy_bbpf_analyze(workflow="data input -> processing -> output")
# Example: Compute semantic residue
wfgy_bbmc_process(text="The universe is expanding", context="cosmology")# Install dependencies
pip install -r requirements.txt
# Run tests
pytest tests/
# Start development server
python -m wfgy_mcp.serverwfgy_mcp/
├── server.py # Main MCP server
├── schemas.py # Pydantic schemas
├── wfgy_integration.py # WFGY SDK integration
└── problemmap.py # ProblemMap data access
docker/
├── run_uvicorn.sh # Docker startup script
└── Dockerfile.mcp # MCP server container
tests/
├── contract/ # MCP contract tests
└── test_*.py # Unit testsThis repository builds on the original WFGY project with:
Based on the original WFGY project. Enhanced with MCP integration.
Ready to unlock $1M-level AI reasoning in Augment! 🚀
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.