SuperClaude/docs/User-Guide/mcp-servers.md
kazuki nakai 050d5ea2ab
refactor: PEP8 compliance - directory rename and code formatting (#425)
* fix(orchestration): add WebFetch auto-trigger for infrastructure configuration

Problem: Infrastructure configuration changes (e.g., Traefik port settings)
were being made based on assumptions without consulting official documentation,
violating the 'Evidence > assumptions' principle in PRINCIPLES.md.

Solution:
- Added Infrastructure Configuration Validation section to MODE_Orchestration.md
- Auto-triggers WebFetch for infrastructure tools (Traefik, nginx, Docker, etc.)
- Enforces MODE_DeepResearch activation for investigation
- BLOCKS assumption-based configuration changes

Testing: Verified WebFetch successfully retrieves Traefik official docs (port 80 default)

This prevents production outages from infrastructure misconfiguration by ensuring
all technical recommendations are backed by official documentation.

* feat: Add PM Agent (Project Manager Agent) for seamless orchestration

Introduces PM Agent as the default orchestration layer that coordinates
all sub-agents and manages workflows automatically.

Key Features:
- Default orchestration: All user interactions handled by PM Agent
- Auto-delegation: Intelligent sub-agent selection based on task analysis
- Docker Gateway integration: Zero-token baseline with dynamic MCP loading
- Self-improvement loop: Automatic documentation of patterns and mistakes
- Optional override: Users can specify sub-agents explicitly if desired

Architecture:
- Agent spec: SuperClaude/Agents/pm-agent.md
- Command: SuperClaude/Commands/pm.md
- Updated docs: README.md (15→16 agents), agents.md (new Orchestration category)

User Experience:
- Default: PM Agent handles everything (seamless, no manual routing)
- Optional: Explicit --agent flag for direct sub-agent access
- Both modes available simultaneously (no user downside)

Implementation Status:
-  Specification complete
-  Documentation complete
-  Prototype implementation needed
-  Docker Gateway integration needed
-  Testing and validation needed

Refs: kazukinakai/docker-mcp-gateway (IRIS MCP Gateway integration)

* feat: Add Agent Orchestration rules for PM Agent default activation

Implements PM Agent as the default orchestration layer in RULES.md.

Key Changes:
- New 'Agent Orchestration' section (CRITICAL priority)
- PM Agent receives ALL user requests by default
- Manual override with @agent-[name] bypasses PM Agent
- Agent Selection Priority clearly defined:
  1. Manual override → Direct routing
  2. Default → PM Agent → Auto-delegation
  3. Delegation based on keywords, file types, complexity, context

User Experience:
- Default: PM Agent handles everything (seamless)
- Override: @agent-[name] for direct specialist access
- Transparent: PM Agent reports delegation decisions

This establishes PM Agent as the orchestration layer while
respecting existing auto-activation patterns and manual overrides.

Next Steps:
- Local testing in agiletec project
- Iteration based on actual behavior
- Documentation updates as needed

* refactor(pm-agent): redesign as self-improvement meta-layer

Problem Resolution:
PM Agent's initial design competed with existing auto-activation for task routing,
creating confusion about orchestration responsibilities and adding unnecessary complexity.

Design Change:
Redefined PM Agent as a meta-layer agent that operates AFTER specialist agents
complete tasks, focusing on:
- Post-implementation documentation and pattern recording
- Immediate mistake analysis with prevention checklists
- Monthly documentation maintenance and noise reduction
- Pattern extraction and knowledge synthesis

Two-Layer Orchestration System:
1. Task Execution Layer: Existing auto-activation handles task routing (unchanged)
2. Self-Improvement Layer: PM Agent meta-layer handles documentation (new)

Files Modified:
- SuperClaude/Agents/pm-agent.md: Complete rewrite with meta-layer design
  - Category: orchestration → meta
  - Triggers: All user interactions → Post-implementation, mistakes, monthly
  - Behavioral Mindset: Continuous learning system
  - Self-Improvement Workflow: BEFORE/DURING/AFTER/MISTAKE RECOVERY/MAINTENANCE

- SuperClaude/Core/RULES.md: Agent Orchestration section updated
  - Split into Task Execution Layer + Self-Improvement Layer
  - Added orchestration flow diagram
  - Clarified PM Agent activates AFTER task completion

- README.md: Updated PM Agent description
  - "orchestrates all interactions" → "ensures continuous learning"

- Docs/User-Guide/agents.md: PM Agent section rewritten
  - Section: Orchestration Agent → Meta-Layer Agent
  - Expertise: Project orchestration → Self-improvement workflow executor
  - Examples: Task coordination → Post-implementation documentation

- PR_DOCUMENTATION.md: Comprehensive PR documentation added
  - Summary, motivation, changes, testing, breaking changes
  - Two-layer orchestration system diagram
  - Verification checklist

Integration Validated:
Tested with agiletec project's self-improvement-workflow.md:
 PM Agent aligns with existing BEFORE/DURING/AFTER/MISTAKE RECOVERY phases
 Complements (not competes with) existing workflow
 agiletec workflow defines WHAT, PM Agent defines WHO executes it

Breaking Changes: None
- Existing auto-activation continues unchanged
- Specialist agents unaffected
- User workflows remain the same
- New capability: Automatic documentation and knowledge maintenance

Value Proposition:
Transforms SuperClaude into a continuously learning system that accumulates
knowledge, prevents recurring mistakes, and maintains fresh documentation
without manual intervention.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* docs: add Claude Code conversation history management research

Research covering .jsonl file structure, performance impact, and retention policies.

Content:
- Claude Code .jsonl file format and message types
- Performance issues from GitHub (memory leaks, conversation compaction)
- Retention policies (consumer vs enterprise)
- Rotation recommendations based on actual data
- File history snapshot tracking mechanics

Source: Moved from agiletec project (research applicable to all Claude Code projects)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* feat: add Development documentation structure

Phase 1: Documentation Structure complete

- Add Docs/Development/ directory for development documentation
- Add ARCHITECTURE.md - System architecture with PM Agent meta-layer
- Add ROADMAP.md - 5-phase development plan with checkboxes
- Add TASKS.md - Daily task tracking with progress indicators
- Add PROJECT_STATUS.md - Current status dashboard and metrics
- Add pm-agent-integration.md - Implementation guide for PM Agent mode

This establishes comprehensive documentation foundation for:
- System architecture understanding
- Development planning and tracking
- Implementation guidance
- Progress visibility

Related: #pm-agent-mode #documentation #phase-1

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* feat: PM Agent session lifecycle and PDCA implementation

Phase 2: PM Agent Mode Integration (Design Phase)

Commands/pm.md updates:
- Add "Always-Active Foundation Layer" concept
- Add Session Lifecycle (Session Start/During Work/Session End)
- Add PDCA Cycle (Plan/Do/Check/Act) automation
- Add Serena MCP Memory Integration (list/read/write_memory)
- Document auto-activation triggers

Agents/pm-agent.md updates:
- Add Session Start Protocol (MANDATORY auto-activation)
- Add During Work PDCA Cycle with example workflows
- Add Session End Protocol with state preservation
- Add PDCA Self-Evaluation Pattern
- Add Documentation Strategy (temp → patterns/mistakes)
- Add Memory Operations Reference

Key Features:
- Session start auto-activation for context restoration
- 30-minute checkpoint saves during work
- Self-evaluation with think_about_* operations
- Systematic documentation lifecycle
- Knowledge evolution to CLAUDE.md

Implementation Status:
-  Design complete (Commands/pm.md, Agents/pm-agent.md)
-  Implementation pending (Core components)
-  Serena MCP integration pending

Salvaged from mistaken development in ~/.claude directory

Related: #pm-agent-mode #session-lifecycle #pdca-cycle #phase-2

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* fix: disable Serena MCP auto-browser launch

Disable web dashboard and GUI log window auto-launch in Serena MCP server
to prevent intrusive browser popups on startup. Users can still manually
access the dashboard at http://localhost:24282/dashboard/ if needed.

Changes:
- Add CLI flags to Serena run command:
  - --enable-web-dashboard false
  - --enable-gui-log-window false
- Ensures Git-tracked configuration (no reliance on ~/.serena/serena_config.yml)
- Aligns with AIRIS MCP Gateway integration approach

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* refactor: rename directories to lowercase for PEP8 compliance

- Rename superclaude/Agents -> superclaude/agents
- Rename superclaude/Commands -> superclaude/commands
- Rename superclaude/Core -> superclaude/core
- Rename superclaude/Examples -> superclaude/examples
- Rename superclaude/MCP -> superclaude/mcp
- Rename superclaude/Modes -> superclaude/modes

This change follows Python PEP8 naming conventions for package directories.

* style: fix PEP8 violations and update package name to lowercase

Changes:
- Format all Python files with black (43 files reformatted)
- Update package name from 'SuperClaude' to 'superclaude' in pyproject.toml
- Fix import statements to use lowercase package name
- Add missing imports (timedelta, __version__)
- Remove old SuperClaude.egg-info directory

PEP8 violations reduced from 2672 to 701 (mostly E501 line length due to black's 88 char vs flake8's 79 char limit).

* docs: add PM Agent development documentation

Add comprehensive PM Agent development documentation:
- PM Agent ideal workflow (7-phase autonomous cycle)
- Project structure understanding (Git vs installed environment)
- Installation flow understanding (CommandsComponent behavior)
- Task management system (current-tasks.md)

Purpose: Eliminate repeated explanations and enable autonomous PDCA cycles

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* feat(pm-agent): add self-correcting execution and warning investigation culture

## Changes

### superclaude/commands/pm.md
- Add "Self-Correcting Execution" section with root cause analysis protocol
- Add "Warning/Error Investigation Culture" section enforcing zero-tolerance for dismissal
- Define error detection protocol: STOP → Investigate → Hypothesis → Different Solution → Execute
- Document anti-patterns (retry without understanding) and correct patterns (research-first)

### docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md
- Add PDCA workflow hypothesis document for PM Agent autonomous enhancement

## Rationale

PM Agent must never retry failed operations without understanding root causes.
All warnings and errors require investigation via context7/WebFetch/documentation
to ensure production-quality code and prevent technical debt accumulation.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* feat(installer): add airis-mcp-gateway MCP server option

## Changes

- Add airis-mcp-gateway to MCP server options in installer
- Configuration: GitHub-based installation via uvx
- Repository: https://github.com/oraios/airis-mcp-gateway
- Purpose: Dynamic MCP Gateway for zero-token baseline and on-demand tool loading

## Implementation

Added to setup/components/mcp.py self.mcp_servers dictionary with:
- install_method: github
- install_command: uvx test installation
- run_command: uvx runtime execution
- required: False (optional server)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

---------

Co-authored-by: kazuki <kazuki@kazukinoMacBook-Air.local>
Co-authored-by: Claude <noreply@anthropic.com>
2025-10-14 08:47:09 +05:30

11 KiB

SuperClaude MCP Servers Guide 🔌

Overview

MCP (Model Context Protocol) servers extend Claude Code's capabilities through specialized tools. SuperClaude integrates 8 MCP servers and provides Claude with instructions on when to activate them based on your tasks.

🔍 Reality Check

  • What MCP servers are: External Node.js processes that provide additional tools
  • What they aren't: Built-in SuperClaude functionality
  • How activation works: Claude reads instructions to use appropriate servers based on context
  • What they provide: Real tools that extend Claude Code's native capabilities

Core Servers:

  • context7: Official library documentation and patterns
  • sequential-thinking: Multi-step reasoning and analysis
  • magic: Modern UI component generation
  • playwright: Browser automation and E2E testing
  • morphllm-fast-apply: Pattern-based code transformations
  • serena: Semantic code understanding and project memory
  • tavily: Web search and real-time information retrieval
  • chrome-devtools: Performance analysis and debugging

Quick Start

Setup Verification: MCP servers activate automatically. For installation and troubleshooting, see Installation Guide and Troubleshooting.

Auto-Activation Logic:

Request Contains Servers Activated
Library imports, API names context7
--think, debugging sequential-thinking
component, UI, frontend magic
test, e2e, browser playwright
Multi-file edits, refactoring morphllm-fast-apply
Large projects, sessions serena
/sc:research, latest, current tavily
performance, debug, LCP chrome-devtools

Server Details

context7 📚

Purpose: Official library documentation access Triggers: Import statements, framework keywords, documentation requests Requirements: Node.js 16+, no API key

# Automatic activation
/sc:implement "React authentication system"
# → Provides official React patterns

# Manual activation  
/sc:analyze auth-system/ --c7

sequential-thinking 🧠

Purpose: Structured multi-step reasoning and systematic analysis Triggers: Complex debugging, --think flags, architectural analysis Requirements: Node.js 16+, no API key

# Automatic activation
/sc:troubleshoot "API performance issues"
# → Enables systematic root cause analysis

# Manual activation
/sc:analyze --think-hard architecture/

magic

Purpose: Modern UI component generation from 21st.dev patterns Triggers: UI requests, /ui commands, component development Requirements: Node.js 16+, TWENTYFIRST_API_KEY ()

# Automatic activation
/sc:implement "responsive dashboard component"
# → Generates accessible UI with modern patterns

# API key setup
export TWENTYFIRST_API_KEY="your_key_here"

playwright 🎭

Purpose: Real browser automation and E2E testing Triggers: Browser testing, E2E scenarios, visual validation Requirements: Node.js 16+, no API key

# Automatic activation
/sc:test --type e2e "user login flow"
# → Enables browser automation testing

# Manual activation
/sc:validate "accessibility compliance" --play

morphllm-fast-apply 🔄

Purpose: Efficient pattern-based code transformations Triggers: Multi-file edits, refactoring, framework migrations Requirements: Node.js 16+, MORPH_API_KEY

# Automatic activation
/sc:improve legacy-codebase/ --focus maintainability
# → Applies consistent patterns across files

# API key setup
export MORPH_API_KEY="your_key_here"

serena 🧭

Purpose: Semantic code understanding with project memory Triggers: Symbol operations, large codebases, session management Requirements: Python 3.9+, uv package manager, no API key

# Automatic activation  
/sc:load existing-project/
# → Builds project understanding and memory

# Manual activation
/sc:refactor "extract UserService" --serena

tavily 🔍

Purpose: Web search and real-time information retrieval for research Triggers: /sc:research commands, "latest" information requests, current events, fact-checking Requirements: Node.js 16+, TAVILY_API_KEY (free tier available at https://app.tavily.com)

# Automatic activation
/sc:research "latest AI developments 2024"
# → Performs intelligent web research

# Manual activation  
/sc:analyze "market trends" --tavily

# API key setup (get free key at https://app.tavily.com)
export TAVILY_API_KEY="tvly-your_api_key_here"

chrome-devtools 📊

Purpose: Performance analysis, debugging, and real-time browser inspection Triggers: Performance auditing, debugging layout issues (e.g., CLS), slow loading times (LCP), console errors, network requests Requirements: Node.js 16+, no API key

# Automatic activation
/sc:debug "page is loading slowly"
# → Enables performance analysis with Chrome DevTools

# Manual activation
/sc:analyze --performance "homepage"

Capabilities:

  • Web Search: Comprehensive searches with ranking and filtering
  • News Search: Time-filtered current events and updates
  • Content Extraction: Full-text extraction from search results
  • Domain Filtering: Include/exclude specific domains
  • Multi-Hop Research: Iterative searches based on findings (up to 5 hops)

Research Depth Control:

  • --depth quick: 5-10 sources, basic synthesis
  • --depth standard: 10-20 sources, structured report (default)
  • --depth deep: 20-40 sources, comprehensive analysis
  • --depth exhaustive: 40+ sources, academic-level research

Configuration

MCP Configuration File (~/.claude.json):

{
  "mcpServers": {
    "context7": {
      "command": "npx",
      "args": ["-y", "@upstash/context7-mcp@latest"]
    },
    "sequential-thinking": {
      "command": "npx", 
      "args": ["-y", "@modelcontextprotocol/server-sequential-thinking"]
    },
    "magic": {
      "command": "npx",
      "args": ["@21st-dev/magic"],
      "env": {"TWENTYFIRST_API_KEY": "${TWENTYFIRST_API_KEY}"}
    },
    "playwright": {
      "command": "npx",
      "args": ["@playwright/mcp@latest"]
    },
    "morphllm-fast-apply": {
      "command": "npx",
      "args": ["@morph-llm/morph-fast-apply"],
      "env": {"MORPH_API_KEY": "${MORPH_API_KEY}"}
    },
    "serena": {
      "command": "uvx",
      "args": ["--from", "git+https://github.com/oraios/serena", "serena", "start-mcp-server", "--context", "ide-assistant"]
    },
    "tavily": {
      "command": "npx",
      "args": ["-y", "tavily-mcp@latest"],
      "env": {"TAVILY_API_KEY": "${TAVILY_API_KEY}"}
    },
    "chrome-devtools": {
      "command": "npx",
      "args": ["-y", "chrome-devtools-mcp@latest"]
    }
  }
}

Usage Patterns

Server Control:

# Enable specific servers
/sc:analyze codebase/ --c7 --seq

# Disable all MCP servers
/sc:implement "simple function" --no-mcp

# Enable all servers
/sc:design "complex architecture" --all-mcp

Multi-Server Coordination:

# Full-stack development
/sc:implement "e-commerce checkout"
# → Sequential: workflow analysis
# → Context7: payment patterns  
# → Magic: UI components
# → Serena: code organization
# → Playwright: E2E testing

Troubleshooting

Common Issues:

  • No servers connected: Check Node.js: node --version (need v16+)
  • Context7 fails: Clear cache: npm cache clean --force
  • Magic/Morphllm errors: Expected without API keys (paid services)
  • Server timeouts: Restart Claude Code session

Quick Fixes:

# Reset connections
# Restart Claude Code session

# Check dependencies  
node --version  # Should show v16+

# Test without MCP
/sc:command --no-mcp

# Check configuration
ls ~/.claude.json

API Key Configuration:

# For Magic server (required for UI generation)
export TWENTYFIRST_API_KEY="your_key_here"

# For Morphllm server (required for bulk transformations)
export MORPH_API_KEY="your_key_here"

# For Tavily server (required for web search - free tier available)
export TAVILY_API_KEY="tvly-your_key_here"

# Add to shell profile for persistence
echo 'export TWENTYFIRST_API_KEY="your_key"' >> ~/.bashrc
echo 'export MORPH_API_KEY="your_key"' >> ~/.bashrc
echo 'export TAVILY_API_KEY="your_key"' >> ~/.bashrc

Environment Variable Usage:

  • TWENTYFIRST_API_KEY - Required for Magic MCP server functionality
  • MORPH_API_KEY - Required for Morphllm MCP server functionality
  • TAVILY_API_KEY - Required for Tavily MCP server functionality (free tier available)
  • Other env vars in docs - Examples only, not used by framework
  • 📝 Magic and Morphllm are paid services, Tavily has free tier, framework works without them

Server Combinations

No API Keys (Free):

  • context7 + sequential-thinking + playwright + serena

1 API Key:

  • Add magic for professional UI development

2 API Keys:

  • Add morphllm-fast-apply for large-scale refactoring

Common Workflows:

  • Learning: context7 + sequential-thinking
  • Web Development: magic + context7 + playwright
  • Enterprise Refactoring: serena + morphllm + sequential-thinking
  • Complex Analysis: sequential-thinking + context7 + serena
  • Deep Research: tavily + sequential-thinking + serena + playwright
  • Current Events: tavily + context7 + sequential-thinking
  • Performance Tuning: chrome-devtools + sequential-thinking + playwright

Integration

With SuperClaude Commands:

  • Analysis commands automatically use Sequential + Serena
  • Implementation commands use Magic + Context7
  • Testing commands use Playwright + Sequential
  • Research commands use Tavily + Sequential + Playwright

With Behavioral Modes:

  • Brainstorming Mode: Sequential for discovery
  • Task Management: Serena for persistence
  • Orchestration Mode: Optimal server selection
  • Deep Research Mode: Tavily + Sequential + Playwright coordination

Performance Control:

  • Automatic resource management based on system load
  • Concurrency control: --concurrency N (1-15)
  • Priority-based server selection under constraints

Essential Reading:

Advanced Usage:

Technical References: