Agent pattern: verify before you trust — Trooth MCP Resource
Agent pattern: verify before you trust
is one of 3 resources on the
Trooth
MCP server. Connect the server and your client can attach it as context.
by client
How to attach Agent pattern: verify before you trust from your client
- Claude Code Trooth Resource/Agent pattern: verify before you trust run in your project directory
- Claude Desktop Trooth Resource/Agent pattern: verify before you trust ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor Trooth Resource/Agent pattern: verify before you trust ~/.cursor/mcp.json
- VS Code Trooth Resource/Agent pattern: verify before you trust .vscode/mcp.json
- Zed Trooth Resource/Agent pattern: verify before you trust ~/.config/zed/settings.json
- Windsurf Trooth Resource/Agent pattern: verify before you trust ~/.codeium/windsurf/mcp_config.json
- Cline Trooth Resource/Agent pattern: verify before you trust ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI Trooth Resource/Agent pattern: verify before you trust ~/.gemini/settings.json
- Grok Trooth Resource/Agent pattern: verify before you trust .mcp.json (in your project root)
- ChatGPT Trooth Resource/Agent pattern: verify before you trust Settings → Connectors → Advanced → Developer mode
- Claude.ai Trooth Resource/Agent pattern: verify before you trust Settings → Connectors → Add custom connector
- LangChain Trooth Resource/Agent pattern: verify before you trust pip install langchain-mcp-adapters
Other resources on this server
Trooth also offers 3 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.