How to Use the Exa MCP in LangChain

Run multi-step web research chains in LangChain with neural search results that actually match user intent.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Exa MCP to LangChain

Create your Vinkius account to connect Exa 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 Exa with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed clean web text directly into LangChain runs

The `exa_get_contents` tool extracts raw, stripped text from specific web pages without any of the HTML clutter that bloats your model's context window. Your ReAct agent can inspect a list of URLs, grab only the clean body text, and pass it directly to the next step in your chain. Since this MCP Server handles the scraping and cleaning on Vinkius, your LangSmith traces stay clean. You can monitor exactly how many tokens you save by avoiding raw HTML junk.

Build deep research chains with semantic search

The `exa_search` tool queries the web using neural embeddings to find conceptually relevant pages rather than matching literal keywords. When your LangChain agent needs to answer a complex question, it runs this search to gather high-quality sources. You can configure the search depth to use deep mode for thorough sweeps or instant mode when latency matters. This MCP utility returns page text, highlights, and relevance scores so your chain can filter out low-quality hits before synthesizing.

Find alternative sources using this MCP Server

The `exa_find_similar` tool takes a seed URL and returns semantically related pages to help your agent discover competitors or alternative viewpoints. This is perfect for competitive analysis chains where you need to map out an entire industry from a single link. The agent takes the output from this tool and feeds it right into a summarization step. No manual scraping scripts required.

Setup guide

Set up Exa 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 Exa 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({
    "exa-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 Exa 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 Exa. 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 Exa 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 Exa MCP in LangChain

Install the adapters package and connect to the Vinkius endpoint using the multi-server client. Call the tool getter and pass the list directly to your agent executor.

Yes. You can aggregate this search tool with databases or vector stores. The agent decides which MCP tool to call and in what order based on intermediate results.

Keyword search often fails on highly specific technical queries or conceptual lookups. This MCP tool uses neural embeddings to find matches based on meaning, not just exact words.

Yes, every tool call is traced. You can see the exact input query, the returned text, and the latency of your search operations.

Your search queries and target URLs are sent over an encrypted channel to the Vinkius sandbox. We run your queries in an isolated V8 environment and never store the retrieved page contents or search history on our persistent disks.

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