Brightdata MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 22 137 installs a week from npm. Last commit 5 Nov 2026.
Bright Data's Web MCP server enabling AI agents to search, extract & navigate the web
Nothing serious here today
Today is the operative word: we check Brightdata MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Connect this server
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add brightdata-mcp -e 'API_TOKEN=<API_TOKEN>' -- npx -y @brightdata/mcp{
"mcpServers": {
"brightdata-mcp": {
"command": "npx",
"args": [
"-y",
"@brightdata/mcp"
],
"env": {
"API_TOKEN": "<API_TOKEN>"
}
}
}
}[mcp_servers.brightdata-mcp]
command = "npx"
args = ["-y", "@brightdata/mcp"]
env = { API_TOKEN = "<API_TOKEN>" }{
"mcpServers": {
"brightdata-mcp": {
"command": "npx",
"args": [
"-y",
"@brightdata/mcp"
],
"env": {
"API_TOKEN": "<API_TOKEN>"
}
}
}
}{
"servers": {
"brightdata-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@brightdata/mcp"
],
"env": {
"API_TOKEN": "<API_TOKEN>"
}
}
}
}Put your own value in place of
<API_TOKEN> (Your API key for Bright Data).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
BROWSER_ZONE (Your browser zone name), GROUPS (Comma-separated tool group IDs (e.g., 'ecommerce,browser')), TOOLS (Comma-separated tool names to enable), BASE_TIMEOUT (Request timeout in seconds for base tools (search & scrape). No limit if unset), BASE_MAX_RETRIES (Max retries for base tools on transient errors (0-3, default: 0)).
Alternatives to Brightdata MCP
same job, measured the same wayWeb data for agents. Extract web pages, crawl websites, discover URLs, and search the web.
AI-powered web research MCP server for agents. Supports web search, browse page, extract...
Open-source MCP server for AI agents: web search, content extraction, and library docs.
Open-source MCP server for AI agents: web search, content extraction, and library docs.
MCP server for LocalStack AWS services, enabling AI agents to interact with local AWS infra.
The live web data engine for teams and agents: Search API, Extract API and Deep Search.
MCP server for Mudrex futures trading enabling AI agents to securely access data and risk tools.
MCP server for AI agents: discover a web page's data sources and drive the page to reach them.
Brightdata MCP — questions
Answers built from our own checks of this server.