# promptscan

Production-ready prompt injection detection for AI agents. Scan user input, retrieved docs, and tool outputs before passing them to an LLM. Returns injection_detected, score, attack_type, and sanitiz…

## Quick Start

```bash
# Connect this server (installs CLI if needed)
npx -y @smithery/cli@latest mcp add nicks-brn/promptscan

# Browse available tools
npx -y @smithery/cli@latest tool list nicks-brn/promptscan

# Get full schema for a tool
npx -y @smithery/cli@latest tool get nicks-brn/promptscan scan_text

# Call a tool
npx -y @smithery/cli@latest tool call nicks-brn/promptscan scan_text '{}'
```

## Direct MCP Connection

Endpoint: `https://promptscan--nicks-brn.run.tools`

## Tools (1)

- `scan_text` — Scan text for prompt injection attacks before passing it to an LLM. Returns injection_detected (bool), score (0.0–1.0),…

```bash
# Get full input/output schema for a tool
npx -y @smithery/cli@latest tool get nicks-brn/promptscan <tool-name>
```