AI browser tools with Chrome CDP. Navigate, screenshot, interact. Multi-provider failover.
Browser MCP server is a hosted integration for AI assistants that speak the Model Context Protocol. AI browser tools with Chrome CDP. Navigate, screenshot, interact. Multi-provider failover.
One endpoint that routes across every browser provider you use: automatic failover, persistent profiles, session replay, REST API, MCP server, dashboard.
One endpoint. Multiple providers. Automatic failover when one is saturated or goes down.
Once Browser is connected, these are the calls the assistant has available:
Screenshot — POST /v1/screenshot returns any URL as PNG or JPEG, full-page or scoped to a selectorScrape — POST /v1/scrape extracts structured data via CSS selectors or full-page formatsEndpoint — MethodManagement — The Management tool exposed by this serverPersistence — Everything the gateway writes to disk lives under a single directory, BG_DATA_DIR (defaults to /data inside the image). Mount that as a named volumeUpgrades — State lives in the volume, code lives in the image. Pull the new image, recreate the container — no data lost:Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.
You will need one environment variable: PROVIDER_TOKEN. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
Plenty of browser automation servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Browser's toolset — Screenshot, Scrape, Endpoint and 3 more — is a fair guide to whether it matches your workflow. It is maintained by browser-gateway; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| Screenshot | POST /v1/screenshot returns any URL as PNG or JPEG, full-page or scoped to a selector |
| Scrape | POST /v1/scrape extracts structured data via CSS selectors or full-page formats |
| Endpoint | Method |
| Management | The Management tool exposed by this server. |
| Persistence | Everything the gateway writes to disk lives under a single directory, BG_DATA_DIR (defaults to /data inside the image). Mount that as a named volume or a bind mount and all state survives container restarts and image upg |
| Upgrades | State lives in the volume, code lives in the image. Pull the new image, recreate the container — no data lost: |
{
"mcpServers": {
"playwright": {
"command": "npx",
"args": ["@playwright/mcp@latest", "--cdp-endpoint", "http://localhost:9500"]
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| PROVIDER_TOKEN | Credential the server authenticates with. | Yes |
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.