PromptScan

latest · 0.1.0

Prompt injection detection API for AI agents. Scan untrusted text before passing it to an LLM.

Install

claude mcp add --transport http io-github-corporatelad-promptscan https://promptscan.dev/mcp/

/mcp confirms it's connected.

Install

Or add it manually in ~/.cursor/mcp.json:

{
  "mcpServers": {
    "io-github-corporatelad-promptscan": {
      "url": "https://promptscan.dev/mcp/"
    }
  }
}

In claude_desktop_config.json (Settings → Developer → Edit Config), then restart:

{
  "mcpServers": {
    "io-github-corporatelad-promptscan": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://promptscan.dev/mcp/"
      ]
    }
  }
}

Endpoint, any MCP client:

https://promptscan.dev/mcp/

Community score

Community — from web signals no reviews yet

Public discussion about this server (community v1) — not enough signal to score yet. First-party reviews join the formula in v2.

What the web says

Ecosystem baseline 60 / 100

Objective public usage & activity (formula v3) — a secondary sort, never blended into the community score.

Ecosystem signals 4 collected

Endpoint status · 3 hours ago: Live
Response time · 3 hours ago: 184 ms
Namespace · 3 hours ago: Registry-verified
Listing completeness · 3 hours ago: 100%

Version history 1

0.1.0 release date unknown

Details

Transport: streamable-http
Status: listed
Source: Imported from the MCP registry
Repository: source ↗