Agent discover index — SQLGuard — permission before production writes MCP Resource

Agent discover index is one of 7 resources on the SQLGuard — permission before production writes MCP server. Connect the server and your client can attach it as context.

by client

How to attach Agent discover index from your client

• Claude Code SQLGuard — permission before production writes Resource/Agent discover index run in your project directory
• Claude Desktop SQLGuard — permission before production writes Resource/Agent discover index ~/Library/Application Support/Claude/claude_desktop_config.json
• Cursor SQLGuard — permission before production writes Resource/Agent discover index ~/.cursor/mcp.json
• VS Code SQLGuard — permission before production writes Resource/Agent discover index .vscode/mcp.json
• Zed SQLGuard — permission before production writes Resource/Agent discover index ~/.config/zed/settings.json
• Windsurf SQLGuard — permission before production writes Resource/Agent discover index ~/.codeium/windsurf/mcp_config.json
• Cline SQLGuard — permission before production writes Resource/Agent discover index ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
• Gemini CLI SQLGuard — permission before production writes Resource/Agent discover index ~/.gemini/settings.json
• Grok SQLGuard — permission before production writes Resource/Agent discover index .mcp.json (in your project root)
• ChatGPT SQLGuard — permission before production writes Resource/Agent discover index Settings → Connectors → Advanced → Developer mode
• Claude.ai SQLGuard — permission before production writes Resource/Agent discover index Settings → Connectors → Add custom connector
• LangChain SQLGuard — permission before production writes Resource/Agent discover index pip install langchain-mcp-adapters

Other resources on this server

• Handshake - what do you need?
• SQLGuard catalog
• Authorize-Before-Mutate Protocol
• Fail-closed write gate
• Why agents NEED SQLGuard
• llms.txt

SQLGuard — permission before production writes also offers 2 prompts — things you invoke, where a resource is context you attach.

Read from the server itself, by connecting to it and calling resources/list on 24 September 2026. A listing does not declare its resources, so asking is the only way to know them, and this is what the server actually offers rather than what its listing claims. Names only are stored; connect the server for each resource's type and contents.