Read evidence and approve a fix — AgentTwin Documentation MCP Resource
Read evidence and approve a fix
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 Read evidence and approve a fix from your client
- Claude Code AgentTwin Documentation Resource/Read evidence and approve a fix run in your project directory
- Claude Desktop AgentTwin Documentation Resource/Read evidence and approve a fix ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor AgentTwin Documentation Resource/Read evidence and approve a fix ~/.cursor/mcp.json
- VS Code AgentTwin Documentation Resource/Read evidence and approve a fix .vscode/mcp.json
- Zed AgentTwin Documentation Resource/Read evidence and approve a fix ~/.config/zed/settings.json
- Windsurf AgentTwin Documentation Resource/Read evidence and approve a fix ~/.codeium/windsurf/mcp_config.json
- Cline AgentTwin Documentation Resource/Read evidence and approve a fix ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI AgentTwin Documentation Resource/Read evidence and approve a fix ~/.gemini/settings.json
- Grok AgentTwin Documentation Resource/Read evidence and approve a fix .mcp.json (in your project root)
- ChatGPT AgentTwin Documentation Resource/Read evidence and approve a fix Settings → Connectors → Advanced → Developer mode
- Claude.ai AgentTwin Documentation Resource/Read evidence and approve a fix Settings → Connectors → Add custom connector
- LangChain AgentTwin Documentation Resource/Read evidence and approve a fix 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
- CLI and coding-agent reference
- Worlds, twins, and replicas
- Dashboard guide
- 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.