How to Use the Jina AI (Search Foundation & LLM Grounding) MCP in OpenAI Agents SDK

Q: How do I integrate Jina AI (Search Foundation & LLM Grounding) into my OpenAI Agents SDK pipeline?

You instantiate the server via the MCPServerStreamableHttp class using your endpoint URL. Since the SDK auto-discovers tools, you just pass the server instance to your agent constructor and it handles the rest.

Q: Can Jina AI (Search Foundation & LLM Grounding) help my OpenAI Agents SDK project handle large documents?

Yes, use segmentcontent to split long files into smaller pieces. You then run those chunks through generateembeddings to build a searchable index that fits within your agent's context limits.

Q: Does Jina AI (Search Foundation & LLM Grounding) work with OpenAI Agents SDK to improve search accuracy?

It does. You search with searchwebjina and immediately pass the output through rerankdocuments. This ensures the most relevant information is at the top of the stack for your agent.

Build production-grade RAG agents with Jina AI and the OpenAI Agents SDK. Get precise search and grounding for every task.

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 (Search Foundation & LLM Grounding) MCP to OpenAI Agents SDK

Create your Vinkius account to connect Jina AI (Search Foundation & LLM Grounding) 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 (Search Foundation & LLM Grounding) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time web grounding for OpenAI Agents SDK

Stop relying on stale training data. Use `read_url_content` to pull clean markdown directly from live web pages, giving your agents instant access to current information. This MCP Server provides the context your agent needs to answer questions based on the latest facts. It strips away the clutter so your LLM stays focused on the data that matters.

Optimized semantic search for OpenAI Agents SDK

Your agent needs to find the right information fast. Use `search_web_jina` to execute semantic queries that return structured results instead of raw search links. Once you have the results, use `rerank_documents` to order them by relevance. This keeps your agent's context window clean and prevents it from hallucinating on low-quality matches.

Vector-ready embeddings for OpenAI Agents SDK

Prepare your data for long-term memory with `generate_embeddings`. It turns your text into high-dimensional vectors that you can store in your own database. If you have long documents, `segment_content` breaks them down into manageable chunks before embedding. This ensures your retriever catches specific details rather than just general themes.

Setup guide

Set up Jina AI (Search Foundation & LLM Grounding) 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 (Search Foundation & LLM Grounding) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Jina AI (Search Foundation & LLM Grounding) 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 (Search Foundation & LLM Grounding) 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 (Search Foundation & LLM Grounding) Agent",
            instructions="You have access to Jina AI (Search Foundation & LLM Grounding) 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 (Search Foundation & LLM Grounding) 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 (Search Foundation & LLM Grounding) MCP in OpenAI Agents SDK

You instantiate the server via the `MCPServerStreamableHttp` class using your endpoint URL. Since the SDK auto-discovers tools, you just pass the server instance to your agent constructor and it handles the rest.

Yes, use `segment_content` to split long files into smaller pieces. You then run those chunks through `generate_embeddings` to build a searchable index that fits within your agent's context limits.

It does. You search with `search_web_jina` and immediately pass the output through `rerank_documents`. This ensures the most relevant information is at the top of the stack for your agent.

The server returns structured responses. If a tool call fails, check the error message in your agent's trace. It will tell you exactly which parameter or network issue caused the problem.

This server acts as a pass-through for your text, URLs, and queries. It does not store your input data, and your agent only receives the cleaned markdown or embedding vectors returned during the execution.

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