How to Use the Linkup (AI Search & RAG) MCP in OpenAI Agents SDK

Q: How do I configure Linkup (AI Search & RAG) with the OpenAI Agents SDK?

Install the SDK and register the MCP Server using MCPServerStreamableHttp. Pass this server instance inside the mcpservers list when initializing your Agent. The agent automatically discovers the search and fetch tools.

Q: Can I use Linkup (AI Search & RAG) to pass search results between different agents in OpenAI Agents SDK?

Yes, you can. The router agent runs searchweb to gather raw data and passes the clean output to downstream agents. This keeps your specialized agents focused on processing rather than searching.

Q: Does caching tools in OpenAI Agents SDK improve Linkup (AI Search & RAG) latency?

It definitely does. Setting cacheToolsList=True stops the SDK from querying the MCP Server on every single request. Your agent immediately knows how to call fetchurl without extra network overhead.

Feed real-time web data directly to your OpenAI Agents SDK pipelines without breaking your strict validation guardrails.

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 OpenAI Agents SDK

Create your Vinkius account to connect Linkup (AI Search & RAG) 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 Linkup (AI Search & RAG) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Verify live data before OpenAI Agents SDK execution

Stop guessing if your agents have the right context. This MCP Server lets your OpenAI Agents SDK system run `search_web` to pull fresh facts, while your built-in guardrails validate the retrieved data before any action runs. If the search finds conflicting info, your supervisor agent intercepts the payload. By combining live search with OpenAI's native validation, you prevent hallucinated parameters from hitting your production APIs.

Clean web extraction for multi-agent handoffs

Complex research tasks usually require passing clean data between specialized agents. When your router agent triggers `fetch_url`, Linkup strips away the tracking scripts and returns clean markdown that's easy to parse. This clean output prevents context bloat during handoffs. Your secondary agents receive only the essential text, which keeps token counts low and prevents your OpenAI dashboard traces from becoming unreadable.

Cached tool discovery for fast production runtime

Running agents in production means latency is your enemy. By setting `cacheToolsList=True` during setup, your agents discover the `search_web` and `fetch_url` MCP tools instantly on startup. The SDK registers the MCP Server tools via `MCPServerStreamableHttp` without making redundant discovery calls. This keeps your agent initialization times sub-second, ensuring your users aren't waiting on slow network roundtrips.

Setup guide

Set up Linkup (AI Search & RAG) 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 Linkup (AI Search & RAG) tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Linkup (AI Search & RAG) 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="Linkup (AI Search & RAG) Agent",
            instructions="You have access to Linkup (AI Search & RAG) 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 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 OpenAI Agents SDK

Install the SDK and register the MCP Server using `MCPServerStreamableHttp`. Pass this server instance inside the `mcp_servers` list when initializing your Agent. The agent automatically discovers the search and fetch tools.

Yes, you can. The router agent runs `search_web` to gather raw data and passes the clean output to downstream agents. This keeps your specialized agents focused on processing rather than searching.

It definitely does. Setting `cacheToolsList=True` stops the SDK from querying the MCP Server on every single request. Your agent immediately knows how to call `fetch_url` without extra network overhead.

Fast mode returns quick factual answers for simple lookups. Deep mode performs a thorough research loop, which is perfect when your agent needs to analyze complex topics before making a decision.

All raw search queries and fetched web content are processed in ephemeral V8 sandboxes. Your data is never saved to persistent storage or used to train public models. Vinkius isolates each request session and discards the memory immediately after the tool returns its payload.

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