quarryman-labs-streaming-inference-mcp

J-X0/quarryman-labs-streaming-inference-mcp
★ 0 stars Python Security Updated today
Streaming inference mcp-server for Quarryman Labs — every decision must carry a reviewable audit trail
View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "quarryman-labs-strea": {
      "command": "uvx",
      "args": [
        "quarryman-labs-streaming-inference-mcp"
      ]
    }
  }
}

Or install with pip: pip install quarryman-labs-streaming-inference-mcp

README Excerpt

Incremental model scoring over an append-only event log, with a hash-chained audit trail so every decision can be reviewed and independently re-verified. Built for Quarryman Labs (Project Kingfisher). The governing constraint is that **every decision must carry a reviewable audit trail**. That drives the architecture:

Tools (8)

KINGFISHER_AUDIT_PATHKINGFISHER_LOG_LEVELKINGFISHER_LOG_PATHKINGFISHER_MAX_EVENT_BYTESKINGFISHER_MAX_FEATURESKINGFISHER_MIN_SAMPLESKINGFISHER_PROVIDERKINGFISHER_THRESHOLD

Topics

commercialmcp-serverpythonstreaming-inference