Agent MCP Server

MCP server for browser automation via Vercel's agent-browser CLI

Local serverstdioGo

What is the Agent MCP server?

If you already use Agent, the agent mcp server is the piece that lets your assistant work with it directly. MCP server for browser automation via Vercel's agent-browser CLI.

What the server does

Let LLMs drive a real browser. This MCP server wraps agent-browser (by Vercel Labs) so any MCP-compatible client — Claude Desktop, Claude Code, or others — can navigate pages, fill forms, click buttons, take screenshots, and more.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • Navigation — open URLs, go back/forward, reload
  • Interaction — click, type, fill, press keys, hover, scroll, drag, select, check/uncheck, upload, download
  • Reading — get page text, HTML, attributes, URL, title
  • Accessibility — browser_snapshot returns an accessibility tree with @ref identifiers that can be used as selectors in subsequent calls
  • State — check if elements are visible, enabled, or checked
  • Capture — screenshots (with optional annotation for vision models) and PDF export
  • Sessions — create isolated browser sessions with independent cookies/storage/viewport
  • Cookies — get, set, clear
  • JavaScript — evaluate arbitrary JS in the page context
  • DevTools — read console logs, inspect network requests, connect via CDP
  • AGENT_BROWSER_PATH — Path to the agent-browser binary

Credentials and setup notes

Configuration is passed through the environment: AGENT_BROWSER_PATH. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Install the agent-browser CLI:

Installation

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.

Where it fits

This sits in the browser automation group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Agent's toolset — Navigation, Interaction, Reading and 8 more — is a fair guide to whether it matches your workflow. It is maintained by codeChap; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Agent's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Worth knowing first

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 11 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Agent.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
Navigationopen URLs, go back/forward, reload
Interactionclick, type, fill, press keys, hover, scroll, drag, select, check/uncheck, upload, download
Readingget page text, HTML, attributes, URL, title
Accessibilitybrowser_snapshot returns an accessibility tree with @ref identifiers that can be used as selectors in subsequent calls
Statecheck if elements are visible, enabled, or checked
Capturescreenshots (with optional annotation for vision models) and PDF export
Sessionscreate isolated browser sessions with independent cookies/storage/viewport
Cookiesget, set, clear
JavaScriptevaluate arbitrary JS in the page context
DevToolsread console logs, inspect network requests, connect via CDP
AGENT_BROWSER_PATHPath to the agent-browser binary

How to install the Agent MCP server

{
  "mcpServers": {
    "agent-browser": {
      "command": "/path/to/mcp-server-agent-browser"
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

Install the agent-browser CLI:

VariableDescriptionRequired
AGENT_BROWSER_PATHFilesystem location the server is allowed to use.Optional

Example prompts to try

  • Use Agent to Navigation.
  • Use Agent to Interaction.
  • Use Agent to Reading.

Frequently asked questions

It connects Agent to MCP-compatible AI assistants such as Claude and Cursor, exposing 11 tools (Navigation, Interaction, Reading, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Agent directly.