MCP Servers · brightdata

brightdata-mcp

Brightdata-mcp is a Model Context Protocol server that connects LLMs to live web data via Bright Data's infrastructure, offering web scraping, search, and structured data extraction with anti-bot handling. It provides a free tier (5,000 credits/month) and paid pro modes with additional tools like browser automation and e-commerce datasets.

Talk to DEV.co Discuss Implementation

Source: GitHub — github.com/brightdata/brightdata-mcp

2.5k

GitHub stars

312

Forks

JavaScript

Primary language

MIT

License (OSI-approved)

Key facts

Objective fields from the source. Values we can't verify are shown as “Unknown” rather than guessed.

Field	Value
Repository	brightdata/brightdata-mcp
Owner	brightdata
Primary language	JavaScript
License	MIT — OSI-approved
Stars	2.5k
Forks	312
Open issues	18
Latest release	v2.11.0 (2026-06-16)
Last updated	2026-06-21
Source	https://github.com/brightdata/brightdata-mcp

What brightdata-mcp is

JavaScript-based MCP server exposing REST-style tools for web search, scraping, batch operations, and specialized data APIs (ecommerce, social, finance, etc.). Runs locally or via hosted endpoint; authentication via API token; tool access controlled by PRO_MODE flag, GROUPS config, or explicit TOOLS list.

Quickstart

Get the brightdata-mcp source

Clone the repository and explore it locally.

terminalbash

1git clone https://github.com/brightdata/brightdata-mcp.git2cd brightdata-mcp3# follow the project's README for install & configuration

Need it deployed, integrated, or customized instead? DEV.co ships production installs.

Best use cases

Real-time AI research and fact-checking

Agents need current web data (prices, news, live stats) without outdated training data. This MCP provides search and scraping tools that work within Claude, GPT, Gemini, and other LLMs via standard MCP protocol.

E-commerce and competitive intelligence

Monitor product availability, pricing, and reviews across Amazon, Walmart, Google Shopping. Specialized web_data_* tools return structured product metadata; free tier covers basic scraping; pro tier unlocks dedicated retailer APIs.

Autonomous coding agents

The new 'code' tool group queries npm and PyPI metadata directly, eliminating stale dependency caches. Useful for Cursor, Claude Code, Windsurf agents that need live package version, README, and dependency data.

Implementation considerations

API token management: Requires Bright Data account signup; free tier auto-renews monthly with no card. Store tokens securely (environment variables or secrets manager).
Tool filtering: Control tool exposure via PRO_MODE, GROUPS, or TOOLS config. Start with default rapid mode (base tools only) to manage costs; opt-in to pro/group features as needed.
Rate limits and credit consumption: Free tier is 5,000 credits/month, shared across all requests. Base tools cost 1 credit/request; web_data_* tools cost 1 credit per record. Monitor usage to avoid service interruption.
LLM integration: Deployed as npm package or hosted endpoint. Works with any MCP-compatible LLM (Claude, GPT, Gemini, Llama); configure via mcpServers JSON or custom connector URL.
Graceful degradation: When free credits exhaust, requests fail silently (no surprise charges unless funds deposited). Plan for fallback behavior in agent logic.

When to avoid it — and what to weigh

Strict data privacy or air-gapped deployments — Server sends requests through Bright Data's infrastructure; cannot guarantee zero external network exposure. Self-hosting the MCP does not eliminate backend dependency on Bright Data's scraping/unblocking service.
Target sites explicitly forbid automated access — Anti-bot detection bypass is a feature, but use violates many sites' terms of service. Operator bears legal/ethical risk. No warranty or indemnification stated in README.
High-volume, mission-critical scraping at scale — Free tier (5,000 credits/month) is capped; pro pricing is pay-as-you-go without published rate cards in README. Cost predictability and SLA guarantees unknown.
Requirement for on-premises or sovereign data handling — Data flows through Bright Data's hosted infrastructure. No explicit mention of data residency, GDPR/CCPA compliance, or on-prem deployment options in the README.

License & commercial use

MIT License. Permits use, modification, and distribution in commercial and private contexts, provided original MIT notice is retained. No warranty or liability. Low friction for commercial adoption; code reuse and forking allowed.

MIT license permits commercial use. However, the service depends on Bright Data's commercial terms (pricing, SLAs, terms of service). Using the MCP to automate scraping or data extraction may violate target sites' ToS; operator is liable for compliance. Bright Data's backend service likely has commercial licensing terms separate from the open-source MCP client code. Requires review with legal and Bright Data support.

DEV.co evaluation signals

Editorial assessment — not user reviews. Directional, with an explicit confidence level.

Signal	Assessment
Maintenance	Active
Documentation	Adequate
License clarity	Clear
Deployment complexity	Low
DEV.co fit	Good
Assessment confidence	High

Security considerations

Token exposure: API tokens in environment variables or config files must be protected; no mention of token rotation or expiry. Upstream security: reliance on Bright Data's infrastructure; no public security audit or vulnerability disclosure policy stated. Request data: web requests and responses flow through Bright Data servers; sensitive data in user queries or target responses could be logged. No encryption in transit or at rest details provided. Terms of service and privacy policy should be reviewed before handling PII.

Alternatives to consider

Firecrawl / Apify MCP servers

Alternative web scraping MCP servers with different backend providers. Evaluate based on cost, unblocking reliability, and data quality for your use case.

Native LLM web search (ChatGPT, Claude, Gemini)

Built-in real-time search for some LLMs. No setup, but limited control over scraping depth, data format, and tool availability. Free but subject to LLM provider rate limits.

Bright Data Web Scraping API (REST / SDK)

Direct integration with Bright Data without MCP; more granular control but requires custom agent/workflow code. Useful if MCP overhead is unacceptable.

Software development agency

Build on brightdata-mcp with DEV.co software developers

Brightdata-mcp provides a low-complexity, MIT-licensed MCP server with free credits and pay-as-you-go pro tools. Ideal for research, competitive intelligence, and autonomous coding agents. Contact Devco to integrate this into your AI stack.

Talk to DEV.co

Related open-source tools

Surfaced by semantic similarity across the DEV.co open-source index.

mcp-server-browserbase mobile-mcp firecrawl-mcp-server

Related on DEV.co

Explore the category and the services that help you build with it.

MCP Servers AI Application Development API Development Custom Software & Integration Talk to DEV.co

brightdata-mcp FAQ

Is the free tier really free, and will I be charged unexpectedly?

Yes, the free tier (5,000 credits/month) requires no credit card and auto-renews. When credits exhaust, requests fail—no surprise charges unless you explicitly deposit funds. Pro mode (if enabled) incurs additional pay-as-you-go charges based on tool usage; rates not published in README.

Can I run this on-premises or air-gapped?

The MCP client can run locally, but it sends requests to Bright Data's hosted infrastructure for scraping, unblocking, and data APIs. No on-premises backend option is mentioned. Data privacy and residency are unclear; contact Bright Data for sovereign/GDPR/CCPA guarantees.

Will my scraping requests get me banned?

Bright Data's anti-bot and unblocking features aim to prevent blocks and CAPTCHAs, but using automated scraping to circumvent site ToS may still violate legal terms. Operator is liable for compliance. The MCP provides the tool; use responsibility is yours.

What LLMs and agents are supported?

Any MCP-compatible LLM or agent: Claude, GPT, Gemini, Llama, and frameworks like Cursor, Windsurf, etc. Deploy as npm package or use the hosted URL endpoint. No proprietary integrations.

Software developers & web developers for hire

From first prototype to production, DEV.co delivers software development services around tools like brightdata-mcp. Our software development agency staffs experienced software developers and web developers for custom software development, web development, integrations, and ongoing support across mcp servers and beyond.

Need AI agents that can browse the live web?

Talk to DEV.co Schedule a Consultation