Agent Webbridge vs Playwright MCP Server

A side-by-side look at the Agent Webbridge and Playwright MCP Server MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.

Agent Webbridge logoAgent WebbridgeBrowser Automation · Local subprocess (stdio)Drive your real, logged-in Chrome (many profiles, parallel tabs) from any MCP client. Local only.59GoodAuth: not declaredPlaywright MCP Server logoPlaywright MCP ServerBrowser Automation · Local subprocess (stdio)An MCP server using Playwright for browser automation and webscrapping68GreatAuth: no auth required

Verdict: choose Agent Webbridge for browser automation work as a local process; choose Playwright MCP Server for browser automation as a local process. You can also run both side by side in one mcpServers block.

Which MCP server should you choose?

Agent Webbridge logoChoose Agent Webbridge when

  • You need dedicated capabilities in the Browser Automation domain.
  • You prefer a local stdio subprocess transport.
  • You want tools like navigate, find_tab, evaluate.
Explore Agent Webbridge

Playwright MCP Server logoChoose Playwright MCP Server when

  • You need dedicated capabilities in the Browser Automation domain.
  • You prefer a local stdio subprocess transport.
  • Its auth model fits you: No auth required.
  • You want tools like start_codegen_session, end_codegen_session, get_codegen_session.
Explore Playwright MCP Server

Feature & specification comparison

Rows where the two servers differ are marked.

SpecAgent Webbridge logoAgent WebbridgePlaywright MCP Server logoPlaywright MCP Server
CategoryBrowser AutomationBrowser Automation
Quality signal59/100 · Good68/100 · Great
Install commandConfirmedConfirmed
TransportLocal subprocess (stdio)Local subprocess (stdio)
AuthNot declaredNo auth required
PricingNot declaredFree
Required env varsNone listedNone listed
Verified ownerCommunity listingCommunity listing
GitHub stars125,669
Directory activity 1 views 0 installs 0 upvotes 5 views 0 installs 0 upvotes
Tools1533

Tools & capabilities

Agent Webbridge tools 15

  • navigateOpen a URL in a new or existing tab
  • find_tabLocate a tab by URL / title
  • evaluateRun JavaScript in the page, return the result
  • snapshotAccessibility tree with stable `@e` element refs
  • clickClick an element by `@e` ref (synthetic DOM click)
  • trusted_clickReal mouse click (CDP, `isTrusted`) for pages that ignore `click
  • fillSet native inputs **and** `contenteditable` rich text fields
  • uploadProgrammatically assign files to `<input type="file">
  • file_chooser_interceptSuppress native OS file picker dialogs (Finder/Explorer) during programmatic upload
  • screenshotCapture full-page or element screenshot directly to disk
  • save_as_pdfSave the page as a PDF
  • networkCapture network requests (`start`, `stop`, `list`, `detail`)
  • +3 more on the listing page

Playwright MCP Server tools 33

  • start_codegen_sessionStart a new code generation session to record Playwright actions
  • end_codegen_sessionEnd a code generation session and generate the test file
  • get_codegen_sessionGet information about a code generation session
  • clear_codegen_sessionClear a code generation session without generating a test
  • playwright_navigateNavigate to a URL
  • playwright_screenshotTake a screenshot of the current page or a specific element
  • playwright_clickClick an element on the page
  • playwright_iframe_clickClick an element in an iframe on the page
  • playwright_iframe_fillFill an element in an iframe on the page
  • playwright_fillfill out an input field
  • playwright_selectSelect an element on the page with Select tag
  • playwright_hoverHover an element on the page
  • +21 more on the listing page

Ready-to-paste client configs

Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.

Agent Webbridge

mcpServers (Claude Desktop / Cursor)
{
  "mcpServers": {
    "agent-webbridge": {
      "command": "npx",
      "args": [
        "-y",
        "agent-webbridge"
      ]
    }
  }
}

Playwright MCP Server

mcpServers (Claude Desktop / Cursor)
{
  "mcpServers": {
    "executeautomation-playwright-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@executeautomation/playwright-mcp-server"
      ]
    }
  }
}

Frequently asked questions

Agent Webbridge is categorized under Browser Automation and uses a local stdio subprocess. Playwright MCP Server belongs to Browser Automation and uses a local stdio subprocess. Pick Agent Webbridge for browser automation work and Playwright MCP Server for browser automation.

Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.

Agent Webbridge has no declared pricing — check the project's own site. Playwright MCP Server is listed as free. Auth: no auth required. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.

Yes. MCP clients support multiple servers: add agent-webbridge and executeautomation-playwright-mcp-server as separate keys in the same mcpServers object, and your assistant will call tools from either one.

On AllMCPs, Agent Webbridge has a quality signal of 59/100 (Good) with 1 views, 0 installs and 12 GitHub stars. Playwright MCP Server has 68/100 (Great) with 5 views, 0 installs and 5,669 GitHub stars.