mcp-context-dedup

Zero-dependency semantic context stream compression & token deduplication engine for MCP tools (achieving 60%–80% LLM token savings).

🚀 Key Features

• 💰 60%–80% Token Savings: Saves LLM prompt token costs on verbose stdout streams and repetitive log outputs.

• ⚡ Zero External Dependencies: Built 100% on Python Standard Library.

• 🧹 Traceback & Log Deduplication: Collapses repeated traceback frames and identical log lines into [Repeated Nx] count blocks.

• 🗜️ JSON Array Summarization: Truncates large homogeneous JSON arrays while preserving top/bottom schema context.

• 🛠️ Stdio MCP Server: Ready for instant integration into Claude Desktop, Cursor, and Windsurf via uvx.

Related MCP server: MCP Squeeze

🏗️ Architecture

+-------------------+     +--------------------------+     +------------------------+
| Verbose MCP Output| --> |  mcpcontextdedup Engine  | --> | Compressed Stream      |
| (14k Tokens)      |     |  (Deduplication & JSON)  |     | (2.8k Tokens / 80% Off)|
+-------------------+     +--------------------------+     +------------------------+

📦 Quickstart

uvx mcp-context-dedup

Python Library Usage

from mcpcontextdedup import compress_context

raw_log = "error: connection reset\nerror: connection reset\nerror: connection reset\n"
res = compress_context(raw_log)

print(f"Reduction: {res.reduction_percentage}%")
print(res.text)
# Output:
# Reduction: 66.7%
# error: connection reset [Repeated 3x]

⚙️ Claude Desktop & Cursor Setup

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "context-dedup": {
      "command": "uvx",
      "args": ["mcp-context-dedup"]
    }
  }
}

⚡ Performance Benchmarks

🔒 Privacy & Security

• 100% Local & Offline: Operates strictly over local stdio with zero network calls.

• Zero Telemetry: No analytics, no tracking, and no phone-home mechanisms.

📄 License

MIT © Abhishek Prasad