Brightdata MCP
Web search, page scraping, structured data extraction, and browser automation for AI agents and LLMs over the Model Context Protocol. It runs locally over stdio via the published package.
People who work with scraping, ai integrations and anti bot detection and want it reachable from Claude, Cursor, VS Code, or another MCP client. The project is written in JavaScript.
VERIFIED ACTIVE
LAST COMMIT 2026-09-17 · ★ 2,649 · #8 OF 255 MAINTAINED BROWSER AUTOMATION · VERIFIED 2026-09-18
MIT · JavaScript servers · how we verify → /methodology
01 · Install Brightdata MCP
before you install - you'll need
Set API_TOKEN, RATE_LIMIT, WEB_UNLOCKER_ZONE, BROWSER_ZONE, POLLING_TIMEOUT before connecting.
Claude Code
claude mcp add brightdata-brightdata-mcp -- npx -y @brightdata/mcp Claude Desktop / Cursor / VS Code - add to config
{
"mcpServers": {
"brightdata-brightdata-mcp": {
"command": "npx",
"args": [
"-y",
"@brightdata/mcp"
]
}
}
} Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.
Using another client? Same JSON, different key
Claude Desktop · mcpServers
Cursor · mcpServers
VS Code · servers
Windsurf · mcpServers
Zed · context_servers
Cline · mcpServers
Roo Code · mcpServers
Continue · mcpServers
LibreChat · mcpServers
Gemini CLI · mcpServers
Codex CLI · mcp_servers
Full setup guides: every client.
02 · Evidence
Security posture
What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.
runs as local process (stdio) - runs on your machine with your user's permissions
license MIT - declared in the repository
npm package @brightdata/mcp - published under the repo owner's npm scope (@brightdata)
registry namespace io.github.brightdata is GitHub-verified and matches the repo owner
03 · What Brightdata MCP can do
Prose above is summarized from the project's README and registry record - no invented capabilities.
Latest releases
v2.11.3 · 2026-09-17
Security · Credentials embedded in URLs (scheme://user:pass@host) are now redacted from error output.
v2.11.2 · 2026-09-11
Improved error handling across all tools - failures are now · reported as clean, sanitized message strings. · scrape_batch: failed entries return a plain error message · instead of a serialized error object. Order…
v2.11.1 · 2026-07-27
Fixed compatibility with the updated Playwright API: replaced deprecated page._snapshotForAI() with page.ariaSnapshot({ mode: 'ai' }) in browser session snapshot capture. This restores correct functionality of the…
04 · Who maintains Brightdata MCP
brightdata-mcp is maintained by brightdata. We track 2 MCP servers from brightdata - 1 actively maintained, 2,649 combined GitHub stars, oldest repo from Apr 2025.
05 · Facts
- repository
- github.com/brightdata/brightdata-mcp
- category
- browser automation - ranked #8 of 255 actively-maintained browser automation servers as of 2026-09-18.
- release cadence
- 3 releases in the last 90 days (latest 2026-09-17)
- registry
- io.github.brightdata/brightdata-mcp (active, first published 2025-10-28 · 19 versions)
- packages
- npm:@brightdata/mcp
06 · Brightdata MCP FAQ
What is Brightdata MCP?
Web search, page scraping, structured data extraction, and browser automation for AI agents and LLMs over the Model Context Protocol. It runs locally over stdio via the published package.
Is Brightdata MCP still maintained?
Yes - as of 2026-09-18, its last commit was 2026-09-17 and it shipped 3 releases in the last 90 days. We re-verify nightly.
How do I install Brightdata MCP?
Run `npx -y @brightdata/mcp`. The README documents 5 environment variables (API_TOKEN, RATE_LIMIT, WEB_UNLOCKER_ZONE…) to set first. Set API_TOKEN, RATE_LIMIT, WEB_UNLOCKER_ZONE, BROWSER_ZONE, POLLING_TIMEOUT before connecting. You can also paste the ready-made client config above.
Does Brightdata MCP run locally?
Yes - it's a stdio server: it runs on your machine (via npx) with your user's permissions. Your data stays local unless the server itself calls external APIs.
07 · Alternatives to Brightdata MCP
Alternatives to Brightdata MCP
Maintained browser automation servers if Brightdata MCP isn't the fit.
- Chrome DevTools MCP MCP server for Chrome DevTools ★ 52,170 · 2026-09-17
- Server Browser MCP server for browser use access ★ 39,038 · 2026-09-11
- Playwright MCP Playwright Tools for MCP ★ 37,231 · 2026-09-17
- Aihawk AI browser agent: browses, clicks, types, and reads real web pages from plain-English instructions. ★ 31,628 · 2026-09-18
- SeleniumBase MCP Stealthy browser automation, testing, and web-scraping via CDP Mode. ★ 13,024 · 2026-09-18
- Mobile MCP MCP server for iOS and Android Mobile Development, Automation and Testing ★ 6,744 · 2026-09-16
Pairs well with
Servers that cover what Brightdata MCP doesn't - only shown when the pairing reason fits the companion.
- Firecrawl MCP Server → web scraping companion web scraping · ★ 7,478
- Tavily MCP → web scraping companion web scraping · ★ 2,390
- Codebase Memory → memory companion memory · ★ 43,715
- Memorix → memory companion memory · ★ 785
- Server Filesystem → filesystem companion filesystem · ★ 39,038
- Pdf MCP → filesystem companion filesystem · ★ 135
More browser automation MCP servers · Browser Gateway · Browserstack MCP Server · Screaming Frog SEO Spider MCP Server (headless) · Antigravity Link
More JavaScript MCP servers · Brilliant Directories MCP · Bug Bug · Vk · SSH Manager · Hubd · see all