How to Use the Nimbleway MCP in LangChain

Q: How do I integrate Nimbleway with LangChain?

Install the langchain-mcp-adapters package. Configure the MultiServerMCPClient with your Vinkius endpoint. Pass the tools to createagent and you are ready to scrape.

Q: Can LangChain agents parse raw HTML from Nimbleway?

Yes. You can use extracthtml if you need the full DOM. For most LLM tasks, extractmarkdown provides a much cleaner context window.

Q: How do I stop my LangChain agent from burning Nimbleway proxy credits?

Give your agent access to getaccountusage. You can write a system prompt that forces it to check bandwidth before executing large loops.

Connect LangChain to Nimbleway and let your agents harvest web data dynamically.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nimbleway MCP to LangChain

Create your Vinkius account to connect Nimbleway 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 Nimbleway with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build reactive scraping chains with this MCP Server

Your ReAct agent needs live data to make decisions. With `search_web`, the agent queries target domains directly. It evaluates the search results, picks the most relevant URLs, and decides what to scrape next. Once it finds the right page, it calls `extract_markdown`. The raw web content flows straight into your LangGraph pipeline as clean text. If a target blocks the request, the agent can check `list_proxies` and retry automatically.

Track usage across your agents

Web scraping gets expensive fast when autonomous agents run wild. You need strict limits. By exposing `get_account_usage` to your LangChain MCP setup, you give the system self-awareness over its budget. The agent checks its remaining bandwidth before kicking off massive parallel runs. You get full visibility in LangSmith, showing exactly which tool call consumed your proxy credits.

Manage async extraction jobs

Some pages take time to render. Instead of blocking your entire chain, the agent initiates a background scrape and polls `get_job` to check the status. This keeps your memory context clean. The agent moves on to other tasks and only retrieves the final payload when the job completes. You can also review active queues using `list_jobs` if things back up.

Setup guide

Set up Nimbleway 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 Nimbleway 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({
    "nimbleway-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 Nimbleway 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 Nimbleway. 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 Nimbleway 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 Nimbleway MCP in LangChain

Install the `langchain-mcp-adapters` package. Configure the `MultiServerMCPClient` with your Vinkius endpoint. Pass the tools to `create_agent` and you are ready to scrape.

Yes. You can use `extract_html` if you need the full DOM. For most LLM tasks, `extract_markdown` provides a much cleaner context window.

Give your agent access to `get_account_usage`. You can write a system prompt that forces it to check bandwidth before executing large loops.

Native scrapers break when layouts change. This setup gives your agent the tools to adapt. It reads the page structure dynamically and pivots if a site updates.

The server only touches the specific URLs and search queries your agent requests. Vinkius runs the connection in an ephemeral V8 Isolate sandbox, meaning your proxy configurations and scraped markdown are wiped from memory the second the session ends.

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