scan_text — Prompt Injection Scanner MCP Tool
scan_text
(scan text) is one of 4 tools on the
Prompt Injection Scanner
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call scan_text from your client
- Claude Code Prompt Injection Scanner scan_text run in your project directory
- Claude Desktop Prompt Injection Scanner scan_text ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor Prompt Injection Scanner scan_text ~/.cursor/mcp.json
- VS Code Prompt Injection Scanner scan_text .vscode/mcp.json
- Zed Prompt Injection Scanner scan_text ~/.config/zed/settings.json
- Windsurf Prompt Injection Scanner scan_text ~/.codeium/windsurf/mcp_config.json
- Cline Prompt Injection Scanner scan_text ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI Prompt Injection Scanner scan_text ~/.gemini/settings.json
- Grok Prompt Injection Scanner scan_text .mcp.json (in your project root)
- ChatGPT Prompt Injection Scanner scan_text Settings → Connectors → Advanced → Developer mode
- Claude.ai Prompt Injection Scanner scan_text Settings → Connectors → Add custom connector
- LangChain Prompt Injection Scanner scan_text pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http injection-scan https://injectionscan.openkrill.app/mcpOther tools on this server
This list was read from the server itself, by connecting to it and calling tools/list on 16 October 2026. It is what
the server actually exposes, not what its listing claims.
Mutating and Read-only are read off each tool's name, not its schema — a hint, not a guarantee. The registry stores tool names only; connect the server for its live schemas.