# prompt-injection-detector

Prompt Injection Detector is a stateless security microservice built for the agent economy. Before your agent acts on any input — whether from a user, an email, a document, or another agent — run it …

## Quick Start

```bash
# Connect this server (installs CLI if needed)
npx -y @smithery/cli@latest mcp add found402/prompt-injection-detector

# Browse available tools
npx -y @smithery/cli@latest tool list found402/prompt-injection-detector

# Get full schema for a tool
npx -y @smithery/cli@latest tool get found402/prompt-injection-detector scan_for_injection

# Call a tool
npx -y @smithery/cli@latest tool call found402/prompt-injection-detector scan_for_injection '{}'
```

## Direct MCP Connection

Endpoint: `https://prompt-injection-detector--found402.run.tools`

## Tools (1)

- `scan_for_injection` — Scans text for prompt injection patterns including instruction overrides, jailbreak attempts, role-play manipulations, …

```bash
# Get full input/output schema for a tool
npx -y @smithery/cli@latest tool get found402/prompt-injection-detector <tool-name>
```