GUIDES, read 12 Nov 2026
12 guides to securing coding agents and the endpoints they run on
- Securing Claude Code on developer laptopsClaude Code ships a permission system, an optional OS sandbox (Seatbelt on macOS, bubblewrap on Linux), hooks, MCP allowlists and OpenTelemetry export.
- Securing Cursor on developer machinesCursor's agent reads files and edits workspace files without approval, asks before shell commands and MCP calls, and offers three Run Modes plus a sandbox.
- Securing GitHub Copilot agent mode and the cloud agentCopilot agent mode in VS Code approves terminal commands, MCP tools and URLs, but network access defaults to on (chat.agent.sandbox.network.allowNetwork is true).
- Securing OpenAI Codex CLI on developer laptopsOpenAI's Codex CLI runs commands in an OS-enforced sandbox with network off and writes limited to the workspace by default, plus an approval policy for leaving it.
- Securing Google Gemini CLI on developer laptopsGoogle's Gemini CLI documents sandboxing through Seatbelt, Docker, Podman, gVisor and a Windows native option, but tools.sandbox defaults to undefined and Trusted Folders is disabled by default.
- What coding agents can touch on a developer laptop, and which controls ship with eachClaude Code, Cursor, GitHub Copilot agent mode, Codex CLI and Gemini CLI all run shell commands as the signed-in developer.
- What agentless means on an endpointAgentless AI endpoint security can mean an MDM-pushed profile, a browser extension, an OS API sensor, existing EDR telemetry or a SaaS API connector.
- Local MCP servers on the endpointA local MCP server is a process an AI client starts on a laptop, usually over stdio, with the user's own file and network rights.
- Browser agents and AI extensionsAI browser extensions and agentic browsers such as Comet, ChatGPT Atlas and Gemini in Chrome read pages and act inside the user's signed-in sessions.
- AI DLP on the endpointAI DLP on the endpoint applies data loss prevention to pastes, uploads and agent reads involving AI tools.
- Shadow AI detection signalsShadow AI detection on endpoints draws on five signals: process and binary inventory, browser extension inventory, network and DNS records, agent and MCP config files, and OAuth grants.
- Agent surfaces explainedSix agent surfaces make up AI on a laptop: desktop AI apps, IDE assistants, command-line agents, MCP servers, browser extensions and SaaS copilots.
Short answers to 30 common questions are on the FAQ page.
Sources
- Method, read 12 Nov 2026
Last reviewed 12 Nov 2026.