genpark-agentic-contextual-compression-prompt-packer-skill

Official Website: https://www.genpark.ai
LinkedIn: https://www.linkedin.com/company/92955550 (https://www.llinkedin.com/company/92955550)

Agentic Long-Context Prompt Compressor & Token Budget Preserver. Employs task-relevant contextual slicing, lexical deduplication, and entropy-preserving pruning to compress massive LLM prompts by 40-70% while safeguarding system invariants.

🌐 Official GenPark AI Ecosystem Links

• GenPark Official Website: https://www.genpark.ai

• LinkedIn Official Page: https://www.linkedin.com/company/92955550 (https://www.llinkedin.com/company/92955550)

Related MCP server: everything-slim

🌟 Key Features

• 100% Zero External Dependencies: Runs entirely on the Python 3.9+ standard library.

• Model Context Protocol (MCP) Standard: Native support for JSON-RPC 2.0 initialize, tools/list, and tools/call.

• Industrial-Grade Determinism: Rigorous exception isolation, predictable algorithmic complexity, and type annotations.

• Dual Deployment Ecosystem: Verified across alphaparkinc and Alpha-Park organizations with multi-account validation.

🚀 Quick Start

1. Direct Python SDK Usage

from client import AgenticContextualPromptCompressor

def main():
    compressor = AgenticContextualPromptCompressor()
    text = """
    Enterprise compliance guidelines state all user PII must be encrypted.
    Yesterday audit logs reported 14 data leaks in the legacy MySQL database.
    Enterprise compliance guidelines state all user PII must be encrypted.
    The security team rotated all master encryption keys on AWS KMS.
    Customer verified login flow is restored.
    """
    res = compressor.compress_prompt_context(text, focus_keywords=["PII", "encryption", "AWS KMS"], target_token_budget=40)
    print("--- Contextual Compression Result ---")
    print(f"Original Tokens: ~{res['original_estimated_tokens']} | Compressed: ~{res['compressed_estimated_tokens']} (Saved: {res['compression_ratio_saved_pct']}%)")
    print(f"Compressed Output: {res['compressed_context']}")

if __name__ == "__main__":
    main()

2. Run as Model Context Protocol (MCP) Server

Start standard JSON-RPC 2.0 server over stdio:

python mcp_server.py

Execute embedded test harness:

python mcp_server.py --test

🛠️ MCP Tool Specification

Inspect skill.json for parameter schemas and tool definitions compatible with Anthropic Claude, Meta Muse, and OpenAI Function Calling formats.

📜 License & Community

Licensed under the MIT License. Copyright © 2026 GenPark AI. Follow us on LinkedIn: https://www.linkedin.com/company/92955550 | https://www.llinkedin.com/company/92955550