Prompt Injection Shield MCP Server

Prompt injection is the 1 security risk for LLM applications. aco-prompt-shield catches known jailbreak patterns, understands semantic intent via ML, and detects obfuscation — all locally, all…

Local serverstdio

What is the Prompt Injection Shield MCP Server?

Prompt Injection Shield is an MCP project maintained in the aniketkarne/promptinjectionshield repository. The maintainer describes its purpose as “Prompt injection is the 1 security risk for LLM applications. aco-prompt-shield catches known jailbreak patterns, understands semantic intent via ML, and detects obfuscation — all…”. Read the project documentation for the complete scope.

Local setup

The project provides a local client configuration using aco-prompt-shield. Follow the repository’s build and installation steps before copying it, and replace example paths with the paths on your own computer.

Configuration values

The example declares SHIELD_RISK_THRESHOLD. Secret-looking values have been replaced with placeholders. Required and optional labels are shown only when the documentation states them.

Source

Project documentation · Repository · Discovery listing. This profile records the public documentation checked on 2026-10-08.

How to install the Prompt Injection Shield MCP Server

{
  "mcpServers": {
    "aco-prompt-shield": {
      "command": "aco-prompt-shield",
      "args": [],
      "env": {
        "SHIELD_RISK_THRESHOLD": "0.6"
      }
    }
  }
}

From the project documentation. Replace placeholders and example paths before connecting.