How to Use the Firecrawl MCP in LangChain

Q: Can a LangChain agent run recursive crawls asynchronously with Firecrawl?

Yes, the crawlsite tool returns a job ID instead of blocking your LangChain execution thread. Your agent can check the job status periodically while continuing other chain operations.

Feed clean Markdown directly into your LangChain chains and trace every web extraction step with LangSmith.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Firecrawl MCP to LangChain

Create your Vinkius account to connect Firecrawl 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 Firecrawl with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Recursive Site Crawls in LangChain Pipelines

LangChain agents can initiate deep, multi-page crawls by calling the `crawl_site` tool. The tool returns a job ID, allowing your chain to track progress asynchronously or pause until the site mapping finishes. This async execution fits into LangGraph state machines. You do not block the main agent execution loop while waiting for hundreds of pages to convert to Markdown.

Targeted Scraping for Multi-Step Chains

When your LangChain agent needs raw data from a specific URL, it calls `scrape_page` to bypass anti-bot shields and cookie walls. The output is clean, stripped Markdown that fits right into your LLM prompt window without wasting tokens. You can trace this exact data flow in LangSmith. Monitor the precise latency and token footprint of the raw Markdown payload before it feeds into subsequent chain links.

Dynamic Web Search in LangChain Agents

Equip your LangChain ReAct agent with these Firecrawl MCP tools like `search_web` and `map_site` to discover and extract information dynamically. The agent decides when to run a broad query and when to map a specific site architecture. This setup turns your static chains into live research loops. The agent inspects the sitemap returned by `map_site`, selects the high-signal URLs, and pulls the content.

Setup guide

Set up Firecrawl 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 Firecrawl 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({
    "firecrawl-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 Firecrawl 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 Firecrawl. 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 Firecrawl 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 Firecrawl MCP in LangChain

Install the adapter using pip install langchain-mcp-adapters langgraph. Instantiate the MCP client pointing to your Vinkius endpoint, fetch the tools, and pass them directly to your create_agent call.

Yes, the `crawl_site` tool returns a job ID instead of blocking your LangChain execution thread. Your agent can check the job status periodically while continuing other chain operations.

LangSmith automatically captures every input and output from `scrape_page` and `search_web`. You can inspect the exact Markdown payload size and latency for every single web call in your trace UI.

Definitely. Because this is exposed as an MCP Server, the retrieved tools plug into any agent alongside database connectors or vector store retrievers in the same runtime.

The raw HTML, URLs, and search queries are processed in an ephemeral V8 sandbox on our MCP host. No scraped page content is stored permanently on Vinkius, ensuring your target data remains isolated.

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