Robot Framework MCP Server

A local Python MCP server for analysing Robot Framework output.xml results and exposing structured failure data to Claude Desktop and Claude Code.

Why?

Large Robot Framework suites often produce hundreds of failures across dozens of areas. Instead of manually reading output.xml files, this MCP server:

• groups failures by shared root cause

• prioritises by business impact and severity tags

• escalates API/server errors automatically (5xx → 92, 4xx → 87, 403 → 80)

• generates interactive HTML reports with score-distribution charts

• provides Claude with full keyword traces for rapid debugging

The result: a triage session that takes minutes instead of hours.

Related MCP server: RobotMCP

Quick Start

# 1. Install
pip install -r requirements.txt
pip install mcp

# 2. Start the server
python -m uvicorn robot_mcp_server.http_server:app --host 127.0.0.1 --port 8000

# 3. In Claude — ingest your results, then triage
ingest_results(results_dir="/path/to/results")
generate_failure_matrix(output_path="/path/to/report.html")
get_triage_queue()

API docs available at http://127.0.0.1:8000/docs once the server is running.

Demo

Interactive HTML Report

Why not just inspect output.xml manually?

Features

Installation

python -m pip install -r requirements.txt
pip install mcp

Connecting to Claude Desktop

Add to %APPDATA%\Claude\claude_desktop_config.json:

{
  "mcpServers": {
    "robot-framework-failure-review": {
      "command": "python",
      "args": ["C:\\path\\to\\robot-framework-mcp-server\\examples\\mcp_stdio_wrapper.py"],
      "env": {
        "BASE_URL": "http://127.0.0.1:8000"
      }
    }
  }
}

Then restart Claude Desktop. The server appears under the + → Connectors menu.

Connecting to Claude Code

The .claude/settings.json in this repo configures the MCP server automatically for Claude Code when working in this directory.

Documentation

• Architecture and design decisions

• Configuration — results layout, database initialisation, area categories

• MCP tools reference and typical workflow

• Failure scoring rubric

• SQL query examples

Tests

pytest