Amp

Amp MCP Setup: amp mcp add, amp.mcpServers and Workspace Approval

How do I add an MCP server to Amp?

Run amp mcp add with a name and either a command or a URL, or add the server to amp.mcpServers in ~/.config/amp/settings.json or .amp/settings.json. Amp recommends bundling MCP servers in skills so tools load only when needed. Servers in workspace settings must be approved with amp mcp approve.

Add a server from the CLI

Terminal

amp mcp add context7 -- npx -y @upstash/context7-mcp
amp mcp add linear https://mcp.linear.app/sse

Add servers in settings

Use command, args and env for local servers, and url and headers for remote ones. Reference environment variables with ${VAR_NAME}.

~/.config/amp/settings.json

"amp.mcpServers": {
    "playwright": {
        "command": "npx",
        "args": ["-y", "@playwright/mcp@latest", "--headless"]
    },
    "linear": {
        "url": "https://mcp.linear.app/sse"
    },
    "sourcegraph": {
        "url": "${SRC_ENDPOINT}/.api/mcp/v1",
        "headers": { "Authorization": "token ${SRC_ACCESS_TOKEN}" }
    }
}

Which config wins

1. CLI flag --mcp-config
2. Workspace config: amp.mcpServers in .amp/settings.json
3. User config: amp.mcpServers in ~/.config/amp/settings.json
4. Skills

Servers in .amp/settings.json need explicit approval before they run. Servers in your global settings or passed with --mcp-config do not.

Terminal

amp mcp doctor
amp mcp approve my-server

Bundle a server in a skill

Put an mcp.json next to a skill's SKILL.md. The tools stay hidden until the skill loads. includeTools limits which tools are exposed.

.agents/skills/browser/mcp.json

{
	"chrome-devtools": {
		"command": "npx",
		"args": ["-y", "chrome-devtools-mcp@latest"],
		"includeTools": ["navigate_*", "take_screenshot", "click", "fill*"]
	}
}

OAuth and remote definitions

For servers with automatic OAuth, Amp opens the browser flow when the TUI starts. For servers that need a manual client, register it with amp mcp oauth login. Remote definitions stored on ampcode.com work across clients and need a scope flag.

Terminal

amp mcp oauth login my-server \
  --server-url https://example.com/.api/mcp/v1 \
  --client-id your-client-id \
  --client-secret your-client-secret \
  --scopes "openid,profile,email,user:all"

amp mcp remote --personal add Linear https://mcp.linear.app/mcp
amp mcp remote --personal list

Get Amp settings changes by email

When a setting, flag or permission rule in this guide changes, it goes in the weekly AgentAtlas update, checked against the vendor docs. One email a week.

Sources

Amp: MCP Amp: Skills

More on Amp

Amp standards support

More Amp guides

Other guides

Cursor: allow all terminal commands Claude Code: allow commands without prompts Claude Code permissions: allow, ask and deny rules, rule syntax and allowed tools Codex CLI: approval and sandbox modes Gemini CLI: YOLO mode, auto_edit and allowing specific shell commands Cursor Privacy Mode: telemetry, training and data retention Claude Code telemetry and data retention: what is sent and how to turn it off Gemini CLI: turn off usage statistics and telemetry CLAUDE.md: where it goes, how it loads, and how it works with AGENTS.md Claude Code hooks: format on save, block risky edits, get notified Claude Code subagents: create one, limit its tools, and call it Add MCP servers to Cursor with mcp.json: Keep files out of Cursor with .cursorignore: Configure Codex with config.toml: Configure Gemini CLI with settings.json: Add MCP servers to Claude Code (claude mcp add, .mcp.json, scopes): Claude Code custom slash commands and skills (SKILL.md): GitHub Copilot custom instructions: Adding MCP servers to GitHub Copilot: Claude Code settings.json: file locations, precedence, and key settings Claude Code plugins and marketplaces: install, create, and share Gemini CLI extensions and custom commands: Configuring OpenCode with opencode.json: Cline Rules: workspace, global, and conditional rules Kiro steering files: .kiro/steering, inclusion modes, and AGENTS.md Zed agent: instruction files, MCP servers, tool permissions, and ACP agents Cursor CLI: install, headless mode, permissions and CI Aider: CONVENTIONS.md, .aider.conf.yml and API keys Junie guidelines, MCP and the Action Allowlist: Configure Goose extensions, hints, recipes and permissions: Customize OpenHands with skills, AGENTS.md, setup.sh and MCP: Configure Factory Droid CLI: AGENTS.md, settings.json, autonomy, custom droids and MCP Configure Qwen Code: settings.json, providers, QWEN.md, MCP and approval modes Cursor hooks: hooks.json, beforeShellExecution, afterFileEdit and exit codes Cursor sandbox: sandbox.json, network allowlist and run modes Cursor settings: settings.json, Cursor Settings and the ~/.cursor config files Cursor browser agent: @browser, browser automation and approval modes Cursor subagents: .cursor/agents, frontmatter, built-in Explore, Bash and Browser Cursor telemetry and OpenTelemetry export (Privacy Mode, OTLP, Analytics API): Cursor rules setup: project, user and Team Rules, .mdc frontmatter, globs and AGENTS.md Claude Code headless mode: claude -p, --output-format json, --bare and CI flags Claude Code statusline: custom status bar in settings.json with context %, cost and git branch Claude Code /model: switch models, aliases Claude Code /cost and /usage: check token spend, usage limits and reduce costs Claude Code VS Code extension: install, shortcuts, settings and /ide Codex AGENTS.md: global, project and override instruction files explained Codex MCP servers: codex mcp add and [mcp_servers] in config.toml Codex sandbox modes: read-only, workspace-write, danger-full-access and network access codex exec: run Codex non-interactively in scripts and CI with JSON output Codex skills: create SKILL.md, skill folder locations and $skill invocation GEMINI.md in Gemini CLI: context file locations, imports and /memory Gemini CLI MCP servers: gemini mcp add and mcpServers in settings.json Gemini CLI custom slash commands: TOML files, {{args}}, !{shell} and @{file}Gemini CLI headless mode: gemini -p, JSON output and exit codes for scripts and CI Gemini CLI sandbox: enable Docker, Podman, macOS Seatbelt or gVisor copilot-setup-steps.yml: set up the GitHub Copilot cloud GitHub Copilot CLI permissions: --allow-tool, --deny-tool, --allow-all-tools and trusted directories GitHub Copilot custom agents: .github/agents/*.agent.md profiles, tools and frontmatter GitHub Copilot code review settings: automatic PR reviews, rulesets, effort level and approvals OpenCode MCP Server Setup: Local and Remote Servers in opencode.json OpenCode Permissions: Allow, Ask or Deny Bash, Edit and Webfetch OpenCode Custom Agents and Subagents: Markdown Files, Modes and @ Mentions Cline MCP Setup: cline_mcp_settings.json for Local and Remote Servers Cline Auto Approve and YOLO Mode: Run Commands and Edits Without Prompts Cline Skills: SKILL.md Location, Format and Slash Command Use Kiro MCP Setup: .kiro/settings/mcp.json, autoApprove and OAuth Kiro Hooks: .kiro/hooks JSON, PreToolUse, PostFileSave and Stop Kiro Permissions: permissions.yaml Allow, Ask and Deny Rules Factory Droid MCP Setup: droid mcp add, mcp.json Locations and /mcp Factory Droid Hooks: hooks.json, PreToolUse Matchers and Exit Codes Factory Droid Custom Droids (Subagents): .factory/droids Markdown Files Junie MCP Setup: .junie/mcp/mcp.json for CLI and /mcp Command Junie Brave Mode and Action Allowlist: Auto-Approve Commands in Junie CLI Junie Custom Slash Commands: .junie/commands Markdown Files and Arguments goose .goosehints and AGENTS.md: Global and Project Instructions goose Permission Modes: GOOSE_MODE auto, approve, smart_approve and chat goose Recipes: recipe.yaml Format, Parameters and goose run --recipe Zed Agent Tool Permissions: Auto-Approve Terminal Commands with tool_permissions Use Claude, Codex and Gemini CLI in Zed: External Agents and agent_servers Zed with Ollama, LM Studio and llama.cpp: Local Model Setup and Context Length

Reviewed Oct 13, 2026. Settings change often; the linked vendor docs are the source of truth.