Agent discover index — SQLGuard — Execution Certificate Firewall MCP Resource

Agent discover index is one of 7 resources on the SQLGuard — Execution Certificate Firewall 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 — Execution Certificate Firewall Resource/Agent discover index run in your project directory
• Claude Desktop SQLGuard — Execution Certificate Firewall Resource/Agent discover index ~/Library/Application Support/Claude/claude_desktop_config.json
• Cursor SQLGuard — Execution Certificate Firewall Resource/Agent discover index ~/.cursor/mcp.json
• VS Code SQLGuard — Execution Certificate Firewall Resource/Agent discover index .vscode/mcp.json
• Zed SQLGuard — Execution Certificate Firewall Resource/Agent discover index ~/.config/zed/settings.json
• Windsurf SQLGuard — Execution Certificate Firewall Resource/Agent discover index ~/.codeium/windsurf/mcp_config.json
• Cline SQLGuard — Execution Certificate Firewall Resource/Agent discover index ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
• Gemini CLI SQLGuard — Execution Certificate Firewall Resource/Agent discover index ~/.gemini/settings.json
• Grok SQLGuard — Execution Certificate Firewall Resource/Agent discover index .mcp.json (in your project root)
• ChatGPT SQLGuard — Execution Certificate Firewall Resource/Agent discover index Settings → Connectors → Advanced → Developer mode
• Claude.ai SQLGuard — Execution Certificate Firewall Resource/Agent discover index Settings → Connectors → Add custom connector
• LangChain SQLGuard — Execution Certificate Firewall 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 — Execution Certificate Firewall 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.