How to Use the Apify MCP in LangChain

Q: How do I pass Apify dataset results to a LangChain document loader?

Use getdatasetresults to fetch the raw JSON from your run. Your agent then maps those records into LangChain Document objects, ready for your splitting and embedding steps.

Q: Can my LangChain agent run an Apify actor and wait for the output?

Yes. The agent calls runactor to start the scraper, then checks getrundetails in a loop until the status shows as finished. Once done, it pulls the data to continue the chain.

Run Apify scrapers and pipe structured web data directly into your LangChain reasoning loops.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Apify MCP to LangChain

Create your Vinkius account to connect Apify 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 Apify with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trigger Scrapers from LangChain Chains

Your LangChain chain uses `run_actor` to kick off web scrapers when a user asks for live data. When your chain needs fresh data from a site without an API, this MCP integration boots up an actor and polls `get_run_details` to pause the chain until the scraper finishes. The model handles the logic of waiting for the run. By monitoring `list_actor_runs` within a LangGraph state loop, your chain knows if a scraper stalled or completed, keeping your multi-stage agentic workflow moving.

Feed Scraped Datasets into LangChain Documents

The `get_dataset_results` tool pulls raw web data directly into your LangChain document loaders. This means your chain can read thousands of scraped rows, convert them to LangChain documents, and feed them straight to an LLM or vector store. Your chain can find past runs easily by calling `list_datasets` to locate the exact storage bucket. This keeps your LangChain agents from wasting money re-running scrapers when the data is already sitting in your Apify storage.

Dynamic Task Selection via MCP Server

Your LangChain run uses `list_actor_tasks` to see what scrapers you already configured in your account. Instead of hardcoding actor IDs, the chain inspects this list and dynamically routes the run to the exact task designed for the target website. This makes your LangChain setup highly adaptive. If you add a new scraper in your dashboard, `list_actors` instantly exposes it to your chain without requiring a single code change in your Python app.

Setup guide

Set up Apify 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 Apify 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({
    "apify-extended-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 Apify 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 Apify. 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 Apify 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 Apify MCP in LangChain

Use `get_dataset_results` to fetch the raw JSON from your run. Your agent then maps those records into LangChain Document objects, ready for your splitting and embedding steps.

Yes. The agent calls `run_actor` to start the scraper, then checks `get_run_details` in a loop until the status shows as finished. Once done, it pulls the data to continue the chain.

The server passes API responses directly to your agent. If Apify throttles a request, your LangChain run handles it via your configured retry handlers or LangGraph error steps.

No. Vinkius handles the authentication behind the scenes. Your agent connects to the hosted MCP endpoint with a single Vinkius token, keeping your Apify credentials safe.

Your scraped web data and dataset payloads run inside secure, ephemeral V8 isolates. Vinkius never stores the contents of your `get_dataset_results` calls, keeping your scraped targets private.

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