scan_prompt_injection — agentdiet MCP Tool
scan_prompt_injection
(scan prompt injection) is one of 18 tools on the
agentdiet
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 agentdiet scan_prompt_injection run in your project directory
- Claude Desktop agentdiet scan_prompt_injection ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor agentdiet scan_prompt_injection ~/.cursor/mcp.json
- VS Code agentdiet scan_prompt_injection .vscode/mcp.json
- Zed agentdiet scan_prompt_injection ~/.config/zed/settings.json
- Windsurf agentdiet scan_prompt_injection ~/.codeium/windsurf/mcp_config.json
- Cline agentdiet scan_prompt_injection ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI agentdiet scan_prompt_injection ~/.gemini/settings.json
- Grok agentdiet scan_prompt_injection .mcp.json (in your project root)
- ChatGPT agentdiet scan_prompt_injection Settings → Connectors → Advanced → Developer mode
- Claude.ai agentdiet scan_prompt_injection Settings → Connectors → Add custom connector
- LangChain agentdiet scan_prompt_injection pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http agentdiet https://agentdiet-72343955726.us-central1.run.app/mcpOther tools on this server
- distill_webpage
- recon_webpage_skeleton
- extract_structured_data
- scan_onchain_address_risk
- get_dex_token_intelligence
- enrich_company_domain
- verify_email_deliverability
- recon_domain_osint
- audit_x402_and_a2a_endpoint
- generate_site_llms_txt
- get_public_company_sec_intel
- audit_github_repository
- search_clean_agent_web
- extract_ecommerce_catalog
- repair_malformed_json
- fetch_arxiv_research_digest
- get_agent_wallet_status
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.