How to Use the Linkup (AI Search & RAG) MCP in LangChain

Feed real-time web search results directly into your LangChain reasoning loops without writing scraping boilerplate.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Linkup (AI Search & RAG) MCP to LangChain

Create your Vinkius account to connect Linkup (AI Search & RAG) 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 Linkup (AI Search & RAG) with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain search outputs directly into agent steps

This MCP server exposes `search_web` to let your ReAct chains pull live facts instantly. Your LangChain agents need fresh data to make decisions, not stale training weights. It makes multi-step reasoning actually work because the agent decides what to search for based on previous chain steps. LangSmith tracks every single step of this process. You see the exact latency of the web searches and how many tokens the scraped text consumes in your prompts. It keeps your chains fast and your token bills predictable.

Bypass bot blocks with LangChain and Linkup

The `fetch_url` tool bypasses modern bot protections to deliver clean page content to your LangChain chains. Most web scrapers choke on modern single-page apps or get blocked by Cloudflare immediately. Your agent gets the raw meat of the page without the layout junk. This MCP connector handles the bypass logic on Vinkius infrastructure, keeping your local LangChain code simple. You do not have to build custom document loaders for every weird site your agent encounters.

Fast facts or deep research on demand

By providing both fast and deep options, `search_web` lets you control the latency of your LangChain runs. Not every prompt requires an exhaustive deep dive into the web. Choose the fast mode for instant factual answers. This flexibility keeps your chain runtimes low. Your agents use only the horsepower they need for the specific question at hand, saving API credits and execution time.

Setup guide

Set up Linkup (AI Search & RAG) 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 Linkup (AI Search & RAG) 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({
    "linkup-ai-search-rag-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 Linkup (AI Search & RAG) 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 Linkup. 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 Linkup (AI Search & RAG) 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 Linkup (AI Search & RAG) MCP in LangChain

Install the langchain-mcp-adapters package to connect the server. You initialize the client with the Vinkius HTTP endpoint, get the tools, and pass them directly to your agent constructor. It takes about five lines of Python code.

Yes. Your agent can first call the search tool to find relevant links, then use the fetch tool to extract the full content of the best results. The output of one tool feeds directly into the next step of the chain.

Absolutely. Because it uses standard LangChain tool interfaces, every call to the search or fetch tools is automatically logged in LangSmith. You can monitor latency, raw tool payloads, and exact token usage for every query.

You can mix these search tools with databases, vector stores, or local APIs in the same agent config. This MCP Server behaves like any other native tool in the ecosystem.

Your search queries and target URLs go directly to the Linkup API to fetch results, but Vinkius runs the actual connector in an isolated, zero-trust sandbox. No data is stored or used to train models. Your scraped text and search parameters remain completely private and ephemeral.

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