Build, attack and defend an MCP server.

About

Connect any LLM — local Ollama or cloud Claude / GPT / Gemini — to MCP servers, break them with 23 real, runnable exploits, then harden them with a reusable guardrails library. All from a polished desktop console or the CLI.

What it does

• Threat taxonomy — every module is mapped to OWASP Top 10 for LLM Apps (2025), CWE, and
• PurpleMCP-Bench — purplemcp bench measures guardrail effectiveness (deterministic: attack vs
• SARIF output — purplemcp scan <path> --format sarif emits SARIF 2.1.0 for GitHub code scanning /
• Posture report — purplemcp report stitches the taxonomy, a static scan of the lab's own code, and
• CI — .github/workflows/ci.yml runs the test suite + benchmark on
• Citable — see CITATION.cff and the full write-up in

Getting started

# 1. Install PurpleMCP (editable, so edits take effect immediately)
python3 -m venv .venv
source .venv/bin/activate
pip install -e ".[gui]"      # include the desktop GUI; use `pip install -e .` for CLI-only

# 2. Configure keys (only the providers you want; Ollama needs none)
cp .env.example .env         # then edit .env

# 3. Pull a TOOL-CAPABLE local model (skip if you only use cloud)
ollama pull qwen2.5          # the default; reliably does structured tool calls

# 4. Launch the desktop app — drive everything from here
purplemcp gui