CLI and coding-agent reference — AgentTwin Documentation MCP Resource
CLI and coding-agent reference
is one of 30 resources on the
AgentTwin Documentation
MCP server. Connect the server and your client can attach it as context.
by client
How to attach CLI and coding-agent reference from your client
- Claude Code AgentTwin Documentation Resource/CLI and coding-agent reference run in your project directory
- Claude Desktop AgentTwin Documentation Resource/CLI and coding-agent reference ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor AgentTwin Documentation Resource/CLI and coding-agent reference ~/.cursor/mcp.json
- VS Code AgentTwin Documentation Resource/CLI and coding-agent reference .vscode/mcp.json
- Zed AgentTwin Documentation Resource/CLI and coding-agent reference ~/.config/zed/settings.json
- Windsurf AgentTwin Documentation Resource/CLI and coding-agent reference ~/.codeium/windsurf/mcp_config.json
- Cline AgentTwin Documentation Resource/CLI and coding-agent reference ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI AgentTwin Documentation Resource/CLI and coding-agent reference ~/.gemini/settings.json
- Grok AgentTwin Documentation Resource/CLI and coding-agent reference .mcp.json (in your project root)
- ChatGPT AgentTwin Documentation Resource/CLI and coding-agent reference Settings → Connectors → Advanced → Developer mode
- Claude.ai AgentTwin Documentation Resource/CLI and coding-agent reference Settings → Connectors → Add custom connector
- LangChain AgentTwin Documentation Resource/CLI and coding-agent reference pip install langchain-mcp-adapters
Other resources on this server
- AgentTwin agent testing — test workflows before production
- AgentTwin pricing and access
- About AgentTwin
- Contact AgentTwin
- Privacy and data handling
- AgentTwin developer resources
- AgentTwin API authentication
- AgentTwin API versioning and deprecation policy
- AgentTwin sandbox: test a synthetic workflow
- Worlds, twins, and replicas
- Dashboard guide
- Read evidence and approve a fix
- FAQ
- Fidelity contract
- Welcome to AgentTwin
- Infrastructure and evidence
- Prepare your actual application
- Explore the browser demo
- Your first verified fix
- Product roadmap
- Safety and isolation
- Design reproducible scenarios
- From discovery to a verified fix
- What works today
- Troubleshoot setup and tests
- Example: timeout after a write
- Discover, test and retest
- Reproduce, fix, and retest
- Supported provider operations
Read from the server itself, by connecting to it and calling resources/list on 24 October 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.