Bright Data MCP
Web data extraction over the Bright Data network with two operating modes: Rapid Mode (free, basic search and scrape) and Pro Mode (60+ structured-dataset tools targeting Amazon, LinkedIn, Walmart, Instagram, and more).
“Web data extraction over the Bright Data network, exposed as MCP tools. Two operating modes: Rapid Mode (free, basic search and scrape) and Pro Mode (60+ structured-dataset tools targeting Amazon, LinkedIn, Walmart, Instagram, and more). 2,336 GitHub stars and 10 commits on main in the last 30 days.”
INSTALL THIS SERVER
{
"mcpServers": {
"brightdata": {
"command": "npx",
"args": [
"-y",
"@brightdata/brightdata-mcp"
],
"env": {
"BRIGHTDATA_API_TOKEN": "<your-brightdata-token>",
"GROUPS": "rapid"
}
}
}
}
{
"mcpServers": {
"brightdata": {
"command": "npx",
"args": [
"-y",
"@brightdata/brightdata-mcp"
],
"env": {
"BRIGHTDATA_API_TOKEN": "<your-brightdata-token>",
"GROUPS": "rapid"
}
}
}
}
{
"mcpServers": {
"brightdata": {
"command": "npx",
"args": [
"-y",
"@brightdata/brightdata-mcp"
],
"env": {
"BRIGHTDATA_API_TOKEN": "<your-brightdata-token>",
"GROUPS": "rapid"
}
}
}
}
{
"mcpServers": {
"brightdata": {
"command": "npx",
"args": [
"-y",
"@brightdata/brightdata-mcp"
],
"env": {
"BRIGHTDATA_API_TOKEN": "<your-brightdata-token>",
"GROUPS": "rapid"
}
}
}
}
{
"mcpServers": {
"brightdata": {
"command": "npx",
"args": [
"-y",
"@brightdata/brightdata-mcp"
],
"env": {
"BRIGHTDATA_API_TOKEN": "<your-brightdata-token>",
"GROUPS": "rapid"
}
}
}
}
7 TOOLS AVAILABLE
OUR ASSESSMENT
- 2,336 GitHub stars and MIT licence.
- 10 commits on main in the last 30 days.
- Two-tier model: Rapid Mode is free; Pro Mode unlocks 60+ structured-data extractors.
- Structured datasets sidestep the brittleness of HTML scraping for the 60+ supported sources.
- GROUPS and TOOLS environment variables let operators scope the tool surface to specific bundles.
- Bright Data network proxies handle IP-based blocking that plain fetch hits.
- Pro Mode tools require a Bright Data subscription; usage is metered.
- The web_data_* tools are tied to specific source schemas that change when the source changes layout.
- POLLING_TIMEOUT controls how long web_data tools wait; long-running extractions can stall an agent loop.
BRIGHTDATA_API_TOKEN grants access to the Bright Data account including paid extractor calls. Scope tokens to specific zones and rate-limit at the account level. Outputs include third-party content; treat the result stream as untrusted text in the host LLM context.
Agents that need structured data from major e-commerce, social, or marketplace sources where HTML scraping is brittle; workflows where the agent should bypass IP-based blocking via the Bright Data residential proxy network; operators who want a free Rapid Mode for prototyping then upgrade to Pro Mode for production volume.
TECHNICAL DETAILS
ADOPTION METRICS
// Reading this2,336 stars on the brightdata-com/brightdata-mcp repo. 10 commits on main in the last 30 days.
// Reading thisSecond-ranked in data on Pro Mode breadth; one rank below apify-mcp on commit cadence.
SOURCES & VERIFICATION
We don't take any single directory's word for it. Before scoring, we cross-reference 4 public MCP sources, install the server ourselves against the clients we cover, and record when we last re-verified.
The same server, 4 different lenses. We reconcile these signals into our editorial score, which is why our number sometimes diverges from a directory-aggregate star count.
| Source | Their rating | Their star count | Their downloads | Last synced |
|---|---|---|---|---|
| AutomationSwitch This page | 4.4editorial | 2,336 | — | MAY 3, 2026 |
| PulseMCP | — unrated | unavailable | unavailable | MAY 3, 2026 |
| MCP.so | — unrated | unavailable | unavailable | MAY 3, 2026 |
| Glama | — unrated | unavailable | unavailable | MAY 3, 2026 |
| Smithery | — unrated | unavailable | unavailable | MAY 3, 2026 |
// Counts are directory-reported; we don't adjust them. Discrepancies usually come from different snapshot times or star-caching.
OTHER DATA / ANALYTICS MCP SERVERS
Firecrawl
Web intelligence layer that turns any URL into LLM-optimised markdown. Handles JavaScript rendering, pagination, and structured extraction so your agent reads the live web instead of stale training data.
Apify Actors MCP
Apify Actors as MCP tools: 6,000+ web scrapers, automation actors, and AI agents callable from Claude, Cursor, or any MCP client. Hosted streamable transport at https://mcp.apify.com plus stdio via npx. Dynamic actor discovery at runtime.
DISCUSS YOUR
MCP REQUIREMENTS.
Evaluating a server, scoping an internal deployment, or working out whether MCP is the right fit at all. Start the conversation and we will point you at the right piece of the ecosystem.