genpark-agent-execution-tree-rollback-checkpointer-skill
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
genpark-agent-execution-tree-rollback-checkpointer-skill
🌐 GenPark MCP Hub • 📦 GenPark Official • 📖 Documentation
🌟 Overview
genpark-agent-execution-tree-rollback-checkpointer-skill delivers robust, industrial-grade capabilities for autonomous agents, copilot frameworks, and personal assistant architectures. Built exclusively on the Python standard library with zero external runtime dependencies, it integrates seamlessly as a native Model Context Protocol (MCP) server or an importable Python module.
Autonomous Agent Tree-of-Thoughts (ToT) State Rollback Checkpointer. Allows long-running personal agents (Manus, Devin) to snapshot environment/context states, evaluate branch viability, and backtrack when an exploration path fails without restarting from scratch.
💡 Key Capabilities
Zero-Dependency Architecture: Runs anywhere Python 3.9+ is installed without
pip installoverhead or supply-chain vulnerabilities.Model Context Protocol (MCP) First: Compatible with Claude Desktop, Cursor, GenPark Engine, and custom agentic frameworks.
Deterministic & Safe: Designed with strict validation, graceful error handling, and structured telemetry.
High Concurrency & Low Latency: In-memory caching and optimized data structures for real-time agent execution loops.
Related MCP server: genpark-agentic-workflow-state-checkpoint-skill
🚀 Quickstart
1. Direct Python Usage
from client import ExecutionTreeRollbackCheckpointer
client = ExecutionTreeRollbackCheckpointer()
result = client.snapshot_checkpoint()
print(result)2. Standalone MCP Server Execution
Run the MCP server via standard JSON-RPC 2.0 stdio:
python mcp_server.pyVerify standard compliance and self-tests:
python mcp_server.py --test3. Claude Desktop / Cursor MCP Configuration
Add this tool to your claude_desktop_config.json or Cursor MCP settings:
{
"mcpServers": {
"genpark-agent-execution-tree-rollback-checkpointer-skill": {
"command": "python",
"args": ["/absolute/path/to/genpark-agent-execution-tree-rollback-checkpointer-skill/mcp_server.py"]
}
}
}🛠️ Verification & Testing
Run the included verification suite:
python example_usage.py📄 License
This project is licensed under the MIT License - see the LICENSE file for details.
Developed with ❤️ by the GenPark Autonomous Agent Ecosystem Team.
Related MCP Connectors
Hosted agent memory with provenance, contradiction surfacing, and snapshot rollback.
Shared, versioned context that humans and AI agents can publish, review, annotate, and continue.
Private memory, scratchpads, context export/restore and task handoff for AI agents.
Persistent memory and knowledge graphs for AI agents. Hybrid search, context checkpoints, and more.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables Claude agents to checkpoint their context state and reset back to saved points with handoff messages, maintaining clean context windows during complex tasks by avoiding fragmented summaries from compactions.52MIT
- FlicenseNot gradedqualityBmaintenanceEnables AI agents to commit stateful workflow checkpoints by calculating state hashes and rollback points through the Model Context Protocol. It provides deterministic, dependency-free checkpoint management for autonomous agent execution.8-
- AlicenseNot gradedqualityNot gradedmaintenanceEnables autonomous agents to snapshot execution-tree and context states, evaluate branch viability, and roll back to previous checkpoints when an exploration path fails without restarting from scratch.MIT
- AlicenseNot gradedqualityAmaintenanceEnables Claude AI coding assistants to persist and restore context across sessions, organize saved work by channels and categories, create checkpoints, search past context, and share state between parallel sessions.228 npmMIT