How to Use the Jina AI MCP in OpenAI Agents SDK

Q: How does Jina AI handle web search inside OpenAI Agents SDK?

The agent automatically discovers the searchweb tool from the MCP server. When a user asks a question requiring live data, the agent invokes the tool, pulls the search results, and processes them directly.

Q: Do I need to write custom code to parse HTML?

No. The readurl tool handles the scraping and cleaning automatically. Your agent receives clean markdown, so you do not have to write custom regex or BeautifulSoup parsers.

Get raw web data, clean it, and verify facts inside your production OpenAI Agents SDK workflows without leaving your python runtime.

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 OpenAI Agents SDK

Create your Vinkius account to connect Jina AI to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Fact-check agent decisions with an MCP Server

Your agent calls `check_fact` to audit statements against live web data directly inside your OpenAI Agents SDK workflow. This keeps your production systems clean and prevents hallucinated claims from corrupting your databases. If the agent tries to assert an unverified claim, the guardrails flag it immediately. By integrating `search_web` and `check_fact`, you stop bad data at the source without manual intervention.

Parse clean markdown from raw URLs

Your agent uses `read_url` to strip raw HTML down to clean markdown before processing. This cuts out navigation menus, tracking scripts, and ads, keeping your context clean. You can then feed this clean output directly to `tokenize_text` to check the exact token count before passing it to your model. This saves money and keeps your OpenAI Agents SDK running fast.

Search and rerank the web in real-time

Your agent runs `search_web` to retrieve raw links and instantly filters them with `rerank_documents` to get the best context. Noisy search results are ignored, leaving only high-signal data. This means your OpenAI Agents SDK only processes the absolute best context. You can also generate embeddings on the fly with `get_embeddings` to store these vetted results in your vector database.

Setup guide

Set up Jina AI MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Jina AI tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Jina AI tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Jina AI tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Jina AI Agent",
            instructions="You have access to Jina AI tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the package using pip install openai-agents. Then, instantiate MCPServerStreamableHttp pointing to your Vinkius endpoint. Pass this server in the mcp_servers list when building your agent.

Set cacheToolsList=True in your server configuration. This prevents the SDK from querying the server endpoint on every single turn, keeping your agent latency low.

The agent automatically discovers the search_web tool from the MCP server. When a user asks a question requiring live data, the agent invokes the tool, pulls the search results, and processes them directly.

No. The read_url tool handles the scraping and cleaning automatically. Your agent receives clean markdown, so you do not have to write custom regex or BeautifulSoup parsers.

Vinkius runs this MCP server in a zero-trust, ephemeral V8 isolate sandbox. Your search queries, scraped URLs, text content, embeddings, and tokens are processed strictly in memory and never written to persistent disk.

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