Krauncher analyzer

Overview

Krauncher analyzer is a Model Context Protocol (MCP) server: How long a GPU job will run and cost, before running it — static code analysis, never executed. As an MCP server it plugs straight into AI assistants, exposing its functionality as tools the model can invoke on your behalf.

It runs locally: the Python package krauncher-mcp (via uvx) speaks MCP over stdio on your machine. The current release is v0.5.0, published under the MIT license, with source at Ilya-a-sergeyev-ger/krauncher on GitHub.

You'll find Krauncher analyzer in the Development category here on mcp.site; it connects to Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed, and any other MCP client — see the install snippets below. If you maintain Krauncher analyzer for Ilya-a-sergeyev-ger, claim this listing to verify ownership, earn the Verified badge, and keep the details current.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "krauncher_analyzer": {
      "command": "uvx",
      "args": [
        "krauncher-mcp"
      ]
    }
  }
}