Featured

Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger
Crawl and scrape any site into clean data, 10% off logoCrawl and scrape any site into clean data, 10% off

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits, and new users get 10% off their first purchase.

Try Firecrawl free
6,000+ web scrapers for your AI agent, start free logo6,000+ web scrapers for your AI agent, start free

Apify gives your agent live web data: 6,000+ prebuilt scrapers and actors, MCP-ready. Sign up free with $5 in usage credits.

Try Apify free
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it — secured from day one.

Get it set up for you
SEO data APIs for your agent, $1 free credit logoSEO data APIs for your agent, $1 free credit

DataForSEO gives your agent live access to SERP results, keyword data, backlinks, and on-page SEO data through one API. New accounts get a $1 credit, good for up to 20,000 keyword or backlink lookups.

Try DataForSEO free
Reach 48,000+ AI builders

A flat monthly placement in front of developers actively installing AI tools. No lock-in, cancel anytime.

Advertise here

Works with

Claude CodeClaude DesktopCursorVS CodeClineCodex CLIOpenClaw+ any MCP client

Install to Claude Code

This server doesn't publish a one-line install command. Follow the setup in the source repository.

Summary

Enables comprehensive collection and analysis of ClaudeCode development sessions, including agent tracking, tool usage analytics, and performance metrics.

README.md

ClaudeCode Session Notes MCP Server

![Tests](https://github.com/Claire-s-Monster/claudecode-session-notes) ![Quality](https://github.com/Claire-s-Monster/claudecode-session-notes) ![FastMCP](https://github.com/jlowin/fastmcp) ![Python](https://python.org)

A production-ready Model Context Protocol (MCP) server for comprehensive ClaudeCode session workbook collection and analysis. Built with FastMCP 2.0 for maximum performance and reliability.

🚀 Features

📊 Session Management

  • Start/End Sessions - Track development sessions with comprehensive metadata
  • Environment Collection - Automatic system environment capture (Python, OS, process info)
  • Session Status - Real-time session monitoring and metrics
  • Metadata Updates - Dynamic session attribute management

🤖 Agent Tracking

  • Agent Registration - Register AI agents with type, purpose, and capabilities
  • Execution Logging - Track agent actions with parameters, results, and timing
  • Interaction Analysis - Advanced behavioral tracking for decision-making patterns
  • Agent Statistics - Comprehensive activity metrics and performance data

🛠️ Tool Usage Analytics

  • Tool Request Logging - Track tool availability and usage patterns
  • Missing Tools Detection - Identify gaps in available toolsets
  • Success Rate Analysis - Monitor tool execution effectiveness
  • Usage Pattern Analysis - Understand tool utilization trends

📈 Analytics & Reporting

  • Comprehensive Reports - Session summaries with detailed analytics
  • Missing Tools Reports - Identify frequently requested but unavailable tools
  • Performance Metrics - Execution times, success rates, and efficiency measures
  • Data Export - JSON-based data persistence for external analysis

🏗️ Architecture

Built on FastMCP 2.0 with modern Python practices:

  • FastMCP 2.0 Framework - State-of-the-art MCP server implementation
  • Pydantic Models - Type-safe data validation and serialization
  • File-Based Storage - Reliable .claude/session-notes/ hierarchy
  • PIXI Dependency Management - Reproducible development environment
  • 100% Test Coverage - Production-ready with comprehensive test suite

📦 Installation

Prerequisites

  • Python 3.12+
  • PIXI (recommended) or pip
  • Git for development

Quick Start with PIXI (Recommended)

# Clone the repository
git clone https://github.com/Claire-s-Monster/claudecode-session-notes.git
cd claudecode-session-notes

# Install with PIXI
pixi install

# Start the MCP server
pixi run server

Alternative: pip Installation

# Clone and install
git clone https://github.com/Claire-s-Monster/claudecode-session-notes.git
cd claudecode-session-notes

# Install in editable mode
pip install -e .

# Start the MCP server
python -m session_notes.server

🔧 MCP Integration

Claude Desktop Configuration

Recommended (PIXI - Production Ready)

Add to your ~/.claude_desktop_config.json:

{
  "mcpServers": {
    "session-notes": {
      "command": "pixi",
      "args": ["run", "-e", "quality", "server"],
      "cwd": "/path/to/claudecode-session-notes"
    }
  }
}

Alternative Configurations

Development Mode (with debug logging): ``json { "mcpServers": { "session-notes": { "command": "pixi", "args": ["run", "-e", "quality", "server"], "cwd": "/path/to/claudecode-session-notes", "env": { "PYTHONPATH": "src", "CLAUDE_DEBUG": "1" } } } } ``

Minimal Runtime (fastest startup): ``json { "mcpServers": { "session-notes": { "command": "pixi", "args": ["run", "server"], "cwd": "/path/to/claudecode-session-notes" } } } ``

Legacy Python (fallback option): ``json { "mcpServers": { "session-notes": { "command": "python", "args": ["-m", "session_notes.server"], "cwd": "/path/to/claudecode-session-notes" } } } ``

💡 Why PIXI? Using PIXI commands ensures reproducible environments, exact dependency versions from pixi.lock, and optimal FastMCP 2.0 integration with conda-forge packages.

Available MCP Tools

| Tool | Description | |------|-------------| | start_session | Begin tracking a new development session | | end_session | End session with metrics calculation | | update_session_metadata | Update session attributes dynamically | | get_session_status | Retrieve real-time session information | | register_agent | Register an AI agent in the session | | get_agent_metadata | Get comprehensive agent statistics | | log_agent_execution | Record agent actions and results | | log_tool_request | Track tool usage and availability | | log_agent_interaction | Record complex agent behaviors | | analyze_missing_tools | Identify missing tool patterns | | save_missing_tools_report | Generate missing tools analysis |

Example Usage

# Start a session
start_session("my-dev-session")

# Register an agent
register_agent(
    session_id="my-dev-session",
    agent_type="code-reviewer",
    purpose="Review and analyze code quality"
)

# Log agent activity
log_agent_execution(
    session_id="my-dev-session",
    agent_id="agent-uuid",
    agent_type="code-reviewer",
    action="analyze_code",
    parameters={"file": "main.py"},
    result={"issues": 2, "score": 8.5}
)

# End session with metrics
end_session("my-dev-session", outcome="completed")

🧑‍💻 Development

Quality Standards

This project maintains production-grade quality standards:

  • 100% Test Pass Rate (285/290 tests passing)
  • Zero Critical Lint Violations
  • Type Safety with Pydantic models
  • Error Handling for all edge cases
  • Performance Optimized with FastMCP 2.0

Development Commands

# Install development environment
pixi install -e quality

# Run tests (100% pass rate)
pixi run test

# Run with coverage
pixi run test-cov

# Quality checks
pixi run lint          # Critical violations check
pixi run typecheck     # Type safety validation
pixi run quality       # Full quality pipeline

# Run the server in development
pixi run dev

Project Structure

claudecode-session-notes/
├── src/session_notes/
│   ├── __init__.py
│   └── server.py              # Main MCP server implementation
├── tests/                     # Comprehensive test suite (285 tests)
├── docs/                      # Documentation
├── pyproject.toml            # PIXI configuration & dependencies
├── .claude/                  # Claude integration
└── README.md                 # This file

📊 Data Storage

Session data is stored in a structured hierarchy under .claude/session-notes/:

.claude/session-notes/
├── {session-id}/
│   ├── session.json          # Session metadata & metrics
│   ├── missing_tools.json    # Missing tools analysis
│   └── agents/
│       └── {agent-id}/
│           ├── metadata.json      # Agent registration info
│           ├── execution.json     # Action logs
│           ├── tools.json         # Tool usage logs  
│           └── interactions.json  # Behavioral data

🤝 Contributing

We welcome contributions! This project has achieved 100% test pass rate and maintains high quality standards.

  1. Fork the repository
  2. Create a feature branch: git checkout -b feature/amazing-feature
  3. Maintain quality: Run pixi run quality before committing
  4. Write tests: Ensure 100% test coverage continues
  5. Submit a Pull Request

Quality Requirements

  • ✅ All tests must pass (pixi run test)
  • ✅ No critical lint violations (pixi run lint)
  • ✅ Type safety maintained (pixi run typecheck)
  • ✅ Code coverage maintained (pixi run test-cov)

📝 License

This project is licensed under the MIT License - see the LICENSE file for details.

🏆 Acknowledgments

  • FastMCP Framework - Built on the excellent FastMCP 2.0 by jlowin
  • PIXI Package Manager - Modern Python package management
  • Pydantic - Runtime type checking and data validation
  • ClaudeCode Integration - Seamless AI development workflow integration

📈 Project Status

  • Production Ready
  • 100% Test Pass Rate
  • Zero Critical Issues
  • Actively Maintained

---

Ready to supercharge your ClaudeCode development sessions with comprehensive analytics and insights! 🚀

For questions or support, please open an issue on GitHub.

See related servers & alternatives →

Related MCP servers

Browse all →

Related guides

Hand-picked reading to help you choose and use Developer Tools servers.