How to Use the Jina AI MCP in LangChain

Q: How does Jina AI perform a web search in LangChain?

The server exposes searchweb as a standard LangChain tool. Your agent calls this function whenever it needs external context, passing the query directly to the Jina API.

Q: Can I use Jina AI to rerank LangChain retrieval results?

Yes. You pass your documents to rerankdocuments within your chain. It returns the items sorted by relevance to your specific query.

Build complex reasoning chains in LangChain with Jina AI tools. Turn live web data into actionable inputs for your agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Jina AI MCP to LangChain

Create your Vinkius account to connect Jina AI 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 Jina AI with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain web search into your agent pipeline

Feed live results from `search_web` directly into your LangChain agent. Your model gets the latest data without hallucinating facts. Connect this MCP Server to your chain to automate data collection. The agent decides when to trigger a search based on the current prompt context.

Clean and rerank content for LLMs

Pass messy web text through `read_url` to get clean markdown. Your agent sees only the relevant content, reducing token noise. Use `rerank_documents` to sort those results by relevance. LangChain handles the ordering, ensuring your final output stays focused on the user request.

Validate facts during execution

Verify your agent's conclusions using `check_fact`. This tool adds a layer of logic to your chain, confirming accuracy before the agent responds. Include this in your LangGraph workflow to catch errors early. It keeps your multi-step pipelines reliable and grounded in reality.

Setup guide

Set up Jina AI 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 Jina AI 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({
    "jina-ai-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 Jina AI 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 Jina AI. 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 Jina AI 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 Jina AI MCP in LangChain

The server exposes `search_web` as a standard LangChain tool. Your agent calls this function whenever it needs external context, passing the query directly to the Jina API.

Yes. You pass your documents to `rerank_documents` within your chain. It returns the items sorted by relevance to your specific query.

The MCP Server is stateless, but you can manage state within your LangChain session. You store the outputs of these tools in your agent's memory for subsequent turns.

Use LangSmith to track every call. You will see the exact inputs and outputs for every tool invocation, including latency data.

The server handles text content and URLs only for the duration of the request. It does not store your search queries or the documents retrieved.

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