MCP server for parallel browser automation across multiple providers.
Connect Parallel Browser MCP to Claude, Cursor or any other MCP client and it stops being a tab you switch to. MCP server for parallel browser automation across multiple providers. The parallel browser mcp mcp server is what makes that connection.
parallel-browser-mcp is an MCP server for parallel browser automation. It exposes a numeric session model over MCP so one client can create and control multiple browser sessions at the same time across multiple browser providers.
The server ships on npm as parallel-browser-mcp, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
start_session — close_sessionclose_all_sessions — get_sessionsbrowser_navigate — browser_go_backbrowser_click — browser_fillbrowser_fill_form — browser_screenshotbrowser_snapshot — browser_hoverbrowser_drag — browser_select_optionbrowser_generate_locator — browser_get_page_structurebrowser_evaluate — browser_keyboard_pressbrowser_keyboard_type — browser_mouse_movebrowser_mouse_click_xy — browser_mouse_dragbrowser_upload_file — browser_wait_for_selectorConfiguration is passed through the environment: BROWSER_MCP_CONFIG, BROWSERBASE_API_KEY, ANCHOR_API_KEY, BROWSER_MCP_CONFIG_PATH, BROWSERBASE_PROJECT_ID, CLOUDFLARE_API_TOKEN, CLOUDFLARE_ACCOUNT_ID, BROWSERBASE_CONTEXT_ID. 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.
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. Parallel Browser MCP's toolset — start_session, close_all_sessions, browser_navigate and 11 more — is a fair guide to whether it matches your workflow. It is maintained by etairl; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Parallel Browser MCP's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| start_session | close_session |
| close_all_sessions | get_sessions |
| browser_navigate | browser_go_back |
| browser_click | browser_fill |
| browser_fill_form | browser_screenshot |
| browser_snapshot | browser_hover |
| browser_drag | browser_select_option |
| browser_generate_locator | browser_get_page_structure |
| browser_evaluate | browser_keyboard_press |
| browser_keyboard_type | browser_mouse_move |
| browser_mouse_click_xy | browser_mouse_drag |
| browser_upload_file | browser_wait_for_selector |
| playwright | none |
| browserbase | BROWSERBASE_API_KEY, plus a projectId in config or BROWSERBASE_PROJECT_ID |
{
"mcpServers": {
"parallel-browser": {
"command": "npx",
"args": ["-y", "parallel-browser-mcp"],
"env": {
"BROWSER_MCP_CONFIG": "your-value",
"BROWSERBASE_API_KEY": "your-value",
"ANCHOR_API_KEY": "your-value",
"BROWSER_MCP_CONFIG_PATH": "your-value",
"BROWSERBASE_PROJECT_ID": "your-value",
"CLOUDFLARE_API_TOKEN": "your-value",
"CLOUDFLARE_ACCOUNT_ID": "your-value",
"BROWSERBASE_CONTEXT_ID": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| BROWSER_MCP_CONFIG | Configuration value read at startup. | Optional |
| BROWSERBASE_API_KEY | Credential the server authenticates with. | Yes |
| ANCHOR_API_KEY | Credential the server authenticates with. | Yes |
| BROWSER_MCP_CONFIG_PATH | Filesystem location the server is allowed to use. | Optional |
| BROWSERBASE_PROJECT_ID | Configuration value read at startup. | Optional |
| CLOUDFLARE_API_TOKEN | Credential the server authenticates with. | Yes |
| CLOUDFLARE_ACCOUNT_ID | Configuration value read at startup. | Optional |
| BROWSERBASE_CONTEXT_ID | Configuration value read at startup. | Optional |
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
Industrial-strength web extraction — render, scrape, crawl and search entire sites into clean markdown.
The original Chromium automation reference server — simple, screenshot-driven browser control.
Give your coding agent the full DevTools toolbox: traces, network, console, heap snapshots and Lighthouse.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Cloud browsers for AI agents — automation sessions that run in Browserbase's fleet, not on your machine.