🤖 Add Comprehensive AI Agent Friendly CLI Support

.github/workflows/generate-llm-txt.yml

@@ -0,0 +1,90 @@
+name: Generate LLM.txt
+
+on:
+  # Trigger on releases
+  release:
+    types: [published]
+
+  # Trigger on pushes to main branch
+  push:
+    branches: [main]
+    paths:
+      - 'src/mcpm/commands/**'
+      - 'src/mcpm/cli.py'
+      - 'scripts/generate_llm_txt.py'
+
+  # Allow manual trigger
+  workflow_dispatch:
+
+jobs:
+  generate-llm-txt:
+    runs-on: ubuntu-latest
+
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v4
+      with:
+        token: ${{ secrets.GITHUB_TOKEN }}
+        fetch-depth: 0
+
+    - name: Set up Python
+      uses: actions/setup-python@v4
+      with:
+        python-version: '3.11'
+
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install -e .
+
+    - name: Generate llm.txt
+      run: |
+        python scripts/generate_llm_txt.py
+
+    - name: Check for changes
+      id: check_changes
+      run: |
+        if git diff --quiet llm.txt; then
+          echo "no_changes=true" >> $GITHUB_OUTPUT
+        else
+          echo "no_changes=false" >> $GITHUB_OUTPUT
+        fi
+
+    - name: Commit and push changes
+      if: steps.check_changes.outputs.no_changes == 'false'
+      run: |
+        git config --local user.email "[email protected]"
+        git config --local user.name "GitHub Action"
+        git add llm.txt
+        git commit -m "docs: update llm.txt for AI agents [skip ci]"
+        git push
+      env:
+        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+    - name: Create Pull Request (for releases)
+      if: github.event_name == 'release' && steps.check_changes.outputs.no_changes == 'false'
+      uses: peter-evans/create-pull-request@v5
+      with:
+        token: ${{ secrets.GITHUB_TOKEN }}
+        commit-message: "docs: update llm.txt for release ${{ github.event.release.tag_name }}"
+        title: "📚 Update llm.txt for AI agents (Release ${{ github.event.release.tag_name }})"
+        body: |
+          ## 🤖 Automated llm.txt Update
+
+          This PR automatically updates the llm.txt file for AI agents following the release of version ${{ github.event.release.tag_name }}.
+
+          ### Changes
+          - Updated command documentation
+          - Refreshed examples and usage patterns
+          - Updated version information
+
+          ### What is llm.txt?
+          llm.txt is a comprehensive guide for AI agents to understand how to interact with MCPM programmatically. It includes:
+          - All CLI commands with parameters and examples
+          - Environment variables for automation
+          - Best practices for AI agent integration
+          - Error handling and troubleshooting
+
+          This file is automatically generated from the CLI structure using `scripts/generate_llm_txt.py`.
+        branch: update-llm-txt-${{ github.event.release.tag_name }}
+        delete-branch: true

README.md

@@ -46,6 +46,7 @@ MCPM v2.0 provides a simplified approach to managing MCP servers with a global c
 - 🚀 **Direct Execution**: Run servers over stdio or HTTP for testing
 - 🌐 **Public Sharing**: Share servers through secure tunnels
 - 🎛️ **Client Integration**: Manage configurations for Claude Desktop, Cursor, Windsurf, and more
+- 🤖 **AI Agent Friendly**: Non-interactive CLI with comprehensive automation support and [llm.txt](llm.txt) guide
 - 💻 **Beautiful CLI**: Rich formatting and interactive interfaces
 - 📊 **Usage Analytics**: Monitor server usage and performance
 
@@ -145,6 +146,47 @@ mcpm migrate                  # Migrate from v1 to v2 configuration
 
 The MCP Registry is a central repository of available MCP servers that can be installed using MCPM. The registry is available at [mcpm.sh/registry](https://mcpm.sh/registry).
 
+## 🤖 AI Agent Integration
+
+MCPM is designed to be AI agent friendly with comprehensive automation support. Every interactive command has a non-interactive alternative using CLI parameters and environment variables.
+
+### 🔧 Non-Interactive Mode
+
+Set environment variables to enable full automation:
+
+```bash
+export MCPM_NON_INTERACTIVE=true  # Disable all interactive prompts
+export MCPM_FORCE=true            # Skip confirmations
+export MCPM_JSON_OUTPUT=true      # JSON output for parsing
+```
+
+### 📋 LLM.txt Guide
+
+The [llm.txt](llm.txt) file provides comprehensive documentation specifically designed for AI agents, including:
+
+- Complete command reference with parameters and examples
+- Environment variable usage patterns
+- Best practices for automation
+- Error handling and troubleshooting
+- Batch operation patterns
+
+The llm.txt file is automatically generated from the CLI structure and kept up-to-date with each release.
+
+### ⚡ Example Usage
+
+```bash
+# Server management
+mcpm new myserver --type stdio --command "python -m server" --force
+mcpm edit myserver --env "API_KEY=secret" --force
+
+# Profile management  
+mcpm profile edit web-dev --add-server myserver --force
+mcpm profile run web-dev --port 8080
+
+# Client integration
+mcpm client edit cursor --add-profile web-dev --force
+```
+
 ## 🗺️ Roadmap
 
 ### ✅ v2.0 Complete

docs/llm-txt-generation.md

@@ -0,0 +1,178 @@
+# llm.txt Generation for AI Agents
+
+## Overview
+
+MCPM automatically generates an `llm.txt` file that provides comprehensive documentation for AI agents on how to interact with the MCPM CLI programmatically. This ensures that AI agents always have up-to-date information about command-line interfaces and parameters.
+
+## What is llm.txt?
+
+llm.txt is a markdown-formatted documentation file specifically designed for Large Language Models (AI agents) to understand how to interact with CLI tools. It includes:
+
+- **Complete command reference** with all parameters and options
+- **Usage examples** for common scenarios
+- **Environment variables** for automation
+- **Best practices** for AI agent integration
+- **Error codes and troubleshooting** information
+
+## Automatic Generation
+
+The llm.txt file is automatically generated using the `scripts/generate_llm_txt.py` script, which:
+
+1. **Introspects the CLI structure** using Click's command hierarchy
+2. **Extracts parameter information** including types, defaults, and help text
+3. **Generates relevant examples** based on command patterns
+4. **Includes environment variables** and automation patterns
+5. **Formats everything** in a structured, AI-agent friendly format
+
+## Generation Triggers
+
+The llm.txt file is regenerated automatically in these scenarios:
+
+### 1. GitHub Actions (CI/CD)
+
+- **On releases**: When a new version is published
+- **On main branch commits**: When CLI-related files change
+- **Manual trigger**: Via GitHub Actions workflow dispatch
+
+### 2. Local Development
+
+Developers can manually regenerate the file:
+
+```bash
+# Using the generation script directly
+python scripts/generate_llm_txt.py
+
+# Using the convenience script
+./scripts/update-llm-txt.sh
+```
+
+## File Structure
+
+The generated llm.txt follows this structure:
+
+```
+# MCPM - AI Agent Guide
+
+## Overview
+- Tool description
+- Key concepts
+
+## Environment Variables for AI Agents
+- MCPM_NON_INTERACTIVE
+- MCPM_FORCE
+- MCPM_JSON_OUTPUT
+- Server-specific variables
+
+## Command Reference
+- Each command with parameters
+- Usage examples
+- Subcommands recursively
+
+## Best Practices for AI Agents
+- Automation patterns
+- Error handling
+- Common workflows
+
+## Troubleshooting
+- Common issues and solutions
+```
+
+## Customization
+
+### Adding New Examples
+
+To add examples for new commands, edit the `example_map` in `scripts/generate_llm_txt.py`:
+
+```python
+example_map = {
+    'mcpm new': [
+        '# Create a stdio server',
+        'mcpm new myserver --type stdio --command "python -m myserver"',
+    ],
+    'mcpm your-new-command': [
+        '# Your example here',
+        'mcpm your-new-command --param value',
+    ]
+}
+```
+
+### Modifying Sections
+
+The script generates several predefined sections. To modify content:
+
+1. Edit the `generate_llm_txt()` function
+2. Update the `lines` list with your changes
+3. Test locally: `python scripts/generate_llm_txt.py`
+
+## Integration with CI/CD
+
+The GitHub Actions workflow (`.github/workflows/generate-llm-txt.yml`) handles:
+
+1. **Automatic updates** when CLI changes are detected
+2. **Pull request creation** for releases
+3. **Version tracking** in the generated file
+4. **Error handling** if generation fails
+
+### Workflow Configuration
+
+Key configuration options in the GitHub Actions workflow:
+
+- **Trigger paths**: Only runs when CLI-related files change
+- **Commit behavior**: Auto-commits changes with `[skip ci]`
+- **Release behavior**: Creates PRs for manual review
+- **Dependencies**: Installs MCPM before generation
+
+## Benefits for AI Agents
+
+1. **Always Up-to-Date**: Automatically reflects CLI changes
+2. **Comprehensive**: Covers all commands, parameters, and options
+3. **Structured**: Consistent format for parsing
+4. **Practical**: Includes real-world usage examples
+5. **Complete**: Covers automation, error handling, and troubleshooting
+
+## Maintenance
+
+### Updating the Generator
+
+When adding new CLI commands or options:
+
+1. The generator automatically detects new commands via Click introspection
+2. Add specific examples to the `example_map` if needed
+3. Update environment variable documentation if new variables are added
+4. Test locally before committing
+
+### Version Compatibility
+
+The generator is designed to be compatible with:
+
+- **Click framework**: Uses standard Click command introspection
+- **Python 3.8+**: Compatible with the MCPM runtime requirements
+- **Cross-platform**: Works on Linux, macOS, and Windows
+
+### Troubleshooting Generation
+
+If the generation fails:
+
+1. **Check imports**: Ensure all MCPM modules can be imported
+2. **Verify CLI structure**: Ensure commands are properly decorated
+3. **Test locally**: Run `python scripts/generate_llm_txt.py`
+4. **Check dependencies**: Ensure Click and other deps are installed
+
+## Contributing
+
+When contributing new CLI features:
+
+1. **Add examples** to the example map for new commands
+2. **Document environment variables** if you add new ones
+3. **Test generation** locally before submitting PR
+4. **Update this documentation** if you modify the generation process
+
+## Future Enhancements
+
+Potential improvements to the generation system:
+
+- **JSON Schema generation** for structured API documentation
+- **Interactive examples** with expected outputs
+- **Multi-language examples** for different automation contexts
+- **Plugin system** for custom documentation sections
+- **Integration testing** to verify examples work correctly