Anticells Red MCP

Introduction

A practical starting point for AI security research with Anticells Red MCP.

Meet Anticells Red MCP

Anticells Red MCP is an open-source MCP server for authorized LLM security research. It connects structured assessment tools to an MCP-compatible agent workflow.

Discover research templates, assess configured model endpoints, inspect responses, and save evidence for review.

How it works

An MCP client starts the Python server locally and communicates through standard input and output. The server makes HTTP or HTTPS requests when an assessment uses a configured model endpoint.

The research tools run locally. The target model can be self-hosted or a hosted service within your authorized scope.

Your first steps

  1. Install the server and complete the installer checks.
  2. Connect it to your MCP client using the generated configuration.
  3. Discover a small set of templates, check compatibility, and run a bounded assessment.
  4. Export the evidence and review what the observations establish.