How to Use the Crawlbase MCP in LangChain

Q: How do I install the Crawlbase MCP Server for LangChain?

Run pip install langchain-mcp-adapters langgraph. Then initialize MultiServerMCPClient with your Vinkius endpoint URL. Pass the result of client.gettools() directly to your ReAct agent.

Q: Do the scraping tools support custom extraction rules?

You can trigger scrapejsonformat to extract specific properties from the DOM. The agent receives structured fields instead of a massive HTML string. This saves tokens when passing context to your LLM.

Connect LangChain to the Crawlbase MCP Server to build scraping agents that bypass CAPTCHAs and extract clean web data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Crawlbase MCP to LangChain

Create your Vinkius account to connect Crawlbase to LangChain and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Crawlbase with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Extracting clean data through the MCP Server

Your ReAct agents need raw web data without getting blocked. Connecting Crawlbase gives them direct access to millions of datacenter proxies. They just call `scrape_html` and get back clean DOM content ready for the next node in your chain. Handling client-side rendering is usually a massive headache. We built `scrape_js_rendered` so your agent can wait for React or Vue apps to load before pulling the payload. You get the exact structural matching required for your downstream vector databases.

Social media and search engine pipelines

LangChain thrives on structured inputs. Throwing `scrape_google_serp` into your pipeline lets your agent pull active search arrays directly from Google. Output from that tool feeds straight into your competitor analysis chain. Scraping social profiles usually breaks automated scripts fast. Using `scrape_twitter` or `scrape_linkedin` routes the request through explicit mapped limits. Your agent gets the blueprint constraints without triggering rate limits.

E-commerce tracking with LangSmith observability

Building price trackers requires constant validation. When you wire up `scrape_amazon`, your chain inspects deep internal arrays to pull accurate product data. Every single request logs latency and token usage straight to LangSmith. Sometimes you need visual proof of a layout change. Calling `get_screenshot_link` dispatches an automated validation check and returns a snapshot URL. You track exactly what the tool saw when the chain executed.

Setup guide

Set up Crawlbase MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Crawlbase tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "crawlbase-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Crawlbase transactions"
    })
    print(result["messages"][-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Crawlbase. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Crawlbase now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Crawlbase MCP in LangChain

Run `pip install langchain-mcp-adapters langgraph`. Then initialize `MultiServerMCPClient` with your Vinkius endpoint URL. Pass the result of `client.get_tools()` directly to your ReAct agent.

Yes. The underlying engine automatically routes requests through residential proxies to bypass blocks. Your agent just calls the scraping tools and waits for the clean HTML.

Standard requests fail on JavaScript-heavy sites and get blocked by Cloudflare. This integration handles the browser rendering and proxy rotation automatically. You keep your chains focused on logic instead of anti-bot workarounds.

You can trigger `scrape_json_format` to extract specific properties from the DOM. The agent receives structured fields instead of a massive HTML string. This saves tokens when passing context to your LLM.

Target URLs and scraped payloads pass strictly through the V8 Isolate Sandbox. Vinkius operates a zero-trust ephemeral environment. Your session dies the moment the chain finishes executing.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript