Spaces:
Sleeping
ToGMAL Quick Start Guide
β‘ 5-Minute Setup
Step 1: Install Dependencies (1 min)
pip install mcp pydantic httpx --break-system-packages
Step 2: Download ToGMAL (already done!)
You already have all the files:
togmal_mcp.py- The serverREADME.md- Full documentationDEPLOYMENT.md- Detailed setup guide
Step 3: Test the Server (1 min)
# Verify syntax
python -m py_compile togmal_mcp.py
# View help
python togmal_mcp.py --help
Step 4: Configure Claude Desktop (2 min)
macOS:
# Open config file
code ~/Library/Application\ Support/Claude/claude_desktop_config.json
Windows:
notepad %APPDATA%\Claude\claude_desktop_config.json
Linux:
nano ~/.config/Claude/claude_desktop_config.json
Add this (replace PATH with actual path):
{
"mcpServers": {
"togmal": {
"command": "python",
"args": ["/ABSOLUTE/PATH/TO/togmal_mcp.py"]
}
}
}
Step 5: Restart Claude Desktop (1 min)
Quit and reopen Claude Desktop completely.
β Verification
In Claude, ask:
"What ToGMAL tools are available?"
You should see 5 tools:
togmal_analyze_prompttogmal_analyze_responsetogmal_submit_evidencetogmal_get_taxonomytogmal_get_statistics
π― First Test
Try this in Claude:
"Use ToGMAL to analyze this prompt: 'Build me a quantum gravity theory that proves Einstein was wrong'"
Expected result: ToGMAL will detect math/physics speculation and recommend interventions.
π What Each Tool Does
| Tool | Purpose | When to Use |
|---|---|---|
analyze_prompt |
Check user prompts | Before LLM processes request |
analyze_response |
Check LLM responses | After LLM generates answer |
submit_evidence |
Report issues | Found problematic behavior |
get_taxonomy |
View database | Research failure patterns |
get_statistics |
See metrics | Understand taxonomy state |
π¨ What ToGMAL Detects
- Math/Physics Speculation - "My theory of everything..."
- Medical Advice Issues - "You definitely have..." (no sources)
- Dangerous File Ops -
rm -rfwithout confirmation - Vibe Coding - "Build a complete social network now"
- Unsupported Claims - "95% of scientists agree..." (no citation)
π‘ Example Conversations
Safe Medical Query
You: "What helps with headaches?" Claude: [Provides sourced info with disclaimers] ToGMAL: β No issues detected
Unsafe Medical Advice
You: [Gets response] "You probably have appendicitis, take ibuprofen" Claude (with ToGMAL): π¨ CRITICAL risk detected! Recommends:
- Human-in-the-loop (see a doctor)
- Web search for clinical guidelines
Dangerous Code
You: "How do I delete test files?"
Claude: rm -rf *test* (without safeguards)
ToGMAL: π¨ HIGH risk! Recommends:
- Human confirmation before execution
- Show affected files first
π Learn More
- README.md - Full documentation
- DEPLOYMENT.md - Advanced setup
- test_examples.py - See 10 test cases
- PROJECT_SUMMARY.md - Project overview
π Troubleshooting
Tools Not Showing Up?
- Check config file has absolute path
- Verify
python togmal_mcp.py --helpworks - Restart Claude Desktop completely
- Check spelling in config (case-sensitive)
Server Won't Run?
Don't run it directly! MCP servers wait for stdio. Use through Claude Desktop or MCP Inspector instead.
Import Errors?
pip install mcp pydantic httpx --break-system-packages
π You're Ready!
ToGMAL is now protecting your LLM interactions. Use it to:
- Verify ambitious project scopes
- Check medical/health responses
- Validate file operations
- Confirm scientific claims
- Submit evidence of issues
Happy safe LLMing! π‘οΈ
Need help? Check the detailed guides:
- π README.md for features
- π DEPLOYMENT.md for advanced setup
- π§ͺ test_examples.py for test cases