Injectcheck MCP Server: Install & Setup

Install Injectcheck in Claude Code

npm

Claude Code

claude mcp add injectcheck -- npx -y @reneturcios/injectcheck

mcp.json (Claude Desktop, Cursor, VS Code, Windsurf)

{
  "mcpServers": {
    "injectcheck": {
      "command": "npx",
      "args": [
        "-y",
        "@reneturcios/injectcheck"
      ]
    }
  }
}

Docker

Claude Code

claude mcp add injectcheck -- docker run -i --rm ghcr.io/cloudcorprecords/injectcheck:0.1.19

mcp.json (Claude Desktop, Cursor, VS Code, Windsurf)

{
  "mcpServers": {
    "injectcheck": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/cloudcorprecords/injectcheck:0.1.19"
      ]
    }
  }
}

Frequently asked questions

What does the Injectcheck MCP server do?

Scan what AI agents read for prompt injection: hidden unicode, comment instructions, exfil, lures.

Is the Injectcheck MCP server free?

Yes, most likely. Open source and no paid account or API key is mentioned in the listing. Check the provider for current pricing.

Does Injectcheck run locally or remotely?

Local. Runs on your machine (stdio). You install it with npx, uvx, Docker or from source.

How do I add Injectcheck to Claude Code?

Run: claude mcp add injectcheck -- npx -y @reneturcios/injectcheck

More ai agents & coding agents MCP servers

View all

Intent Analysis

las7/intent-analysis

Debug a bad AI-agent run from your editor: which intent fails, at which step, and why.

LocalAccount needed

INITE Atlas

inite-ai/inite-visibility

AI tools catalogue for agents: match a need to tools, compare prices, see price and API changes.

Local + RemoteAccount needed

io Consentease

io.consentease/mcp-server

Manage ConsentEase consent banners and cookie inventories from your coding agent.

Local + RemoteAccount needed

Ingressward

ingressward/ingressward-mcp-server

Block prompt injection, evasive spacing, and obscene content before it reaches your LLM.

LocalAccount needed

IOS

dockndevai/mcp-ios

Drive iPhone/iPad via Appium/WebDriverAgent from AI agents — safe-by-default, read-only by default.

LocalFree

Infraveil Control Plane

infraveilhq/infraveil-mcp

Govern your backend control plane from your AI agent - signed, human-approval-gated.

LocalAccount needed