scan_prompt_injection — prompt guard mcp MCP Tool
scan_prompt_injection
(scan prompt injection) is one of 2 tools on the
prompt guard mcp
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call scan_prompt_injection from your client
- Claude Code prompt guard mcp scan_prompt_injection run in your project directory
- Claude Desktop prompt guard mcp scan_prompt_injection ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor prompt guard mcp scan_prompt_injection ~/.cursor/mcp.json
- VS Code prompt guard mcp scan_prompt_injection .vscode/mcp.json
- Zed prompt guard mcp scan_prompt_injection ~/.config/zed/settings.json
- Windsurf prompt guard mcp scan_prompt_injection ~/.codeium/windsurf/mcp_config.json
- Cline prompt guard mcp scan_prompt_injection ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI prompt guard mcp scan_prompt_injection ~/.gemini/settings.json
- Grok prompt guard mcp scan_prompt_injection .mcp.json (in your project root)
- ChatGPT prompt guard mcp scan_prompt_injection Settings → Connectors → Advanced → Developer mode
- Claude.ai prompt guard mcp scan_prompt_injection Settings → Connectors → Add custom connector
- LangChain prompt guard mcp scan_prompt_injection pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http prompt-guard-mcp https://prompt-guard-72343955726.us-central1.run.app/mcp/prompt-guardOther tools on this server
This list was read from the server itself, by connecting to it and calling tools/list on 13 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.