Agent Webbridge vs Chrome MCP
A side-by-side look at the Agent Webbridge and Chrome MCP MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Agent Webbridge for browser automation work as a local process; choose Chrome MCP 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?
Choose 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.
Choose Chrome MCP when
- You need dedicated capabilities in the Browser Automation domain.
- You prefer a local stdio subprocess transport.
- You have the keys it needs:
CHROME_MCP_TOKEN, CHROME_MCP_EXTENSION_DIR. - You want tools like
tabs_list, screenshot, get_text.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Browser Automation | Browser Automation |
| Quality signal | 59/100 · Good | 64/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | Not declared | Not declared |
| Pricing | Not declared | Not declared |
| Required env vars | None listed | CHROME_MCP_TOKENCHROME_MCP_EXTENSION_DIR |
| Verified owner | Community listing | Community listing |
| GitHub stars | 12 | 6 |
| Directory activity | 1 views 0 installs 0 upvotes | 2 views 0 installs 0 upvotes |
| Tools | 15 | 22 |
| Full listing | View Agent Webbridge | View Chrome MCP |
Tools & capabilities
Agent Webbridge tools 15
navigateOpen a URL in a new or existing tabfind_tabLocate a tab by URL / titleevaluateRun JavaScript in the page, return the resultsnapshotAccessibility tree with stable `@e` element refsclickClick an element by `@e` ref (synthetic DOM click)trusted_clickReal mouse click (CDP, `isTrusted`) for pages that ignore `clickfillSet native inputs **and** `contenteditable` rich text fieldsuploadProgrammatically assign files to `<input type="file">file_chooser_interceptSuppress native OS file picker dialogs (Finder/Explorer) during programmatic uploadscreenshotCapture full-page or element screenshot directly to disksave_as_pdfSave the page as a PDFnetworkCapture network requests (`start`, `stop`, `list`, `detail`)- +3 more on the listing page
Chrome MCP tools 22
tabs_listList open browser tabs.screenshotCapture a screenshot (page or element). Default is JPEG (quality 70) at CSS-pixel size, which is several times smaller than PNG and reads fine. Pass format:"png" for lossless, quality 1-100 for JPEG, scale 2 for device pixels on a Retina display or 0.5 to shrink.get_textGet visible text of the page or an element.get_htmlGet HTML of the page or an element. Output is capped (see maxBytes) and cut at a tag boundary; narrow it with `selector` rather than raising the cap when you can. Password field values are always blanked.snapshotAccessibility snapshot: interactive elements with refs to target by `ref` (more reliable than guessing CSS selectors). Pass diff:true to get only what changed since the last snapshot of this tab - far cheaper in a click/read loop. Password fields appear as secret:true with no value.page_watchSave a local page checkpoint and compare it later. Actions: create (name), compare (watchId), list, delete. Stores accessibility labels and state, never form values. Site allowlist still applies.get_cookiesCookies for the tab's URL (or url); values need --enable-cookie-values.storageRead/write localStorage (or sessionStorage). op: get|set|remove|clear.wait_forWait for a selector or text to appear/disappear.extract_linksExtract anchors from the page or a subtree. dedupe=true collapses links sharing an href (nav/footer noise); limit caps the count.read_as_markdownRead the page (or subtree) as readable markdown.frames_listList the tab's frames (the top document plus every iframe the extension can reach), with each frame's id and URL. Use it when a selector that should match does not: the element is probably in one of these frames, and you can then pass frameId (or allFrames:true) to act inside it.- +10 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": {
"agent-webbridge": {
"command": "npx",
"args": [
"-y",
"agent-webbridge"
]
}
}
}
Chrome MCP
{
"mcpServers": {
"chrome-mcp": {
"command": "npx",
"args": [
"-y",
"mcp-browser-extension@latest"
],
"env": {
"CHROME_MCP_TOKEN": "YOUR_CHROME_MCP_TOKEN_HERE",
"CHROME_MCP_EXTENSION_DIR": "YOUR_CHROME_MCP_EXTENSION_DIR_HERE"
}
}
}
}
Frequently asked questions
Agent Webbridge is categorized under Browser Automation and uses a local stdio subprocess. Chrome MCP belongs to Browser Automation and uses a local stdio subprocess. Pick Agent Webbridge for browser automation work and Chrome MCP 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. Chrome MCP has no declared pricing — check the project's own site. 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 chrome-mcp 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. Chrome MCP has 64/100 (Good) with 2 views, 0 installs and 6 GitHub stars.