Agent Browser MCP vs MCP Server Playwright
A side-by-side look at the Agent Browser MCP and MCP Server Playwright MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
A
Agent Browser MCPBrowser Automation · Local subprocess (stdio)MCP server integrating with Vercel's agent-browser for AI-driven browser automation57GoodAuth: no auth requiredVerdict: choose Agent Browser MCP for browser automation work as a local process; choose MCP Server Playwright 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?
AChoose Agent Browser MCP 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
browser_navigate, browser_go_back, browser_go_forward.
Choose MCP Server Playwright 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
browser_navigate, browser_screenshot, browser_click.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | A Agent Browser MCP | |
|---|---|---|
| Category | Browser Automation | Browser Automation |
| Quality signal | 57/100 · Good | 61/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | No auth required | No auth required |
| Pricing | Free | Free |
| Required env vars | None listed | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 14 | 297 |
| Directory activity | 0 views 0 installs 0 upvotes | 3 views 0 installs 0 upvotes |
| Tools | 34 | 10 |
| Full listing | View Agent Browser MCP | View MCP Server Playwright |
Tools & capabilities
Agent Browser MCP tools 34
browser_navigateNavigate to a URLbrowser_go_backNavigate back in browser historybrowser_go_forwardNavigate forward in browser historybrowser_reloadReload the current pagebrowser_clickClick on an element using selector or accessibility locatorbrowser_fillFill a text input field with a valuebrowser_typeType text character by character (triggers key events)browser_hoverHover over an elementbrowser_scrollScroll the page or a specific elementbrowser_selectSelect an option from a dropdownbrowser_checkCheck a checkbox or radio buttonbrowser_uncheckUncheck a checkbox- +22 more on the listing page
MCP Server Playwright tools 10
browser_navigateNavigate to a URLbrowser_screenshotTake a screenshot of the current page or a specific elementbrowser_clickClick an element on the page using CSS selectorbrowser_click_textClick an element on the page by its text contentbrowser_fillFill out an input fieldbrowser_selectSelect an element on the page with Select tag using CSS selectorbrowser_select_textSelect an element on the page with Select tag by its text contentbrowser_hoverHover an element on the page using CSS selectorbrowser_hover_textHover an element on the page by its text contentbrowser_evaluateExecute JavaScript in the browser console
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 Browser MCP
{
"mcpServers": {
"agent-browser-mcp": {
"command": "npx",
"args": [
"agent-browser-mcp"
]
}
}
}
MCP Server Playwright
{
"mcpServers": {
"automatalabs-mcp-server-playwright": {
"command": "npx",
"args": [
"-y",
"@automatalabs/mcp-server-playwright"
]
}
}
}
Frequently asked questions
Agent Browser MCP is categorized under Browser Automation and uses a local stdio subprocess. MCP Server Playwright belongs to Browser Automation and uses a local stdio subprocess. Pick Agent Browser MCP for browser automation work and MCP Server Playwright 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 Browser MCP is listed as free. Auth: no auth required. MCP Server Playwright 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-browser-mcp and automatalabs-mcp-server-playwright as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Agent Browser MCP has a quality signal of 57/100 (Good) with 0 views, 0 installs and 14 GitHub stars. MCP Server Playwright has 61/100 (Good) with 3 views, 0 installs and 297 GitHub stars.
