How can Linkup help my agent provide more up-to-date answers?

Use the `linkup_search` tool to give your agent access to live web data. By performing semantic searches across the internet, your agent can retrieve the latest news, reports, and documentation, grounding its answers in current facts.

Can I extract clean text from a specific URL for RAG?

Yes. The `linkup_fetch` tool is specifically designed for content extraction. It renders the target page and returns a clean text version stripped of navigation and ads, making it ideal for feeding high-quality context to your agent.

What is the difference between standard and deep search modes?

Standard search focuses on rapid fact-finding and top results. Deep search performs a more comprehensive crawl across many more sources, which is better for complex research tasks that require diverse perspectives and detailed data.

Linkup (AI Search & RAG) MCP Server for OpenAI Agents SDK 2 tools — connect in under 2 minutes

Name: Linkup (AI Search & RAG)
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 2 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Linkup (AI Search & RAG) through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

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

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Linkup (AI Search & RAG) Assistant",
            instructions=(
                "You help users interact with Linkup (AI Search & RAG). "
                "You have access to 2 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Linkup (AI Search & RAG)"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Linkup (AI Search & RAG) MCP Server

Connect your Linkup account to any AI agent and take full control of real-time web intelligence and content retrieval for RAG pipelines through natural conversation.

The OpenAI Agents SDK auto-discovers all 2 tools from Linkup (AI Search & RAG) through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Linkup (AI Search & RAG), another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Semantic Web Search — Execute context-rich queries that return high-relevancy results specifically optimized for Large Language Models directly from your agent
Deep Content Retrieval — Extract clean, readable text from any web URL, stripping away noise and navigation to feed high-quality grounding data to your AI
RAG-Ready Payloads — Retrieve structured search results including titles, snippets, and source URLs designed for seamless integration into vector stores
Precision Extraction — Target specific URLs for content parsing, ensuring your agent has the exact technical context or documentation required for its task
Real-time Intelligence — Access the latest facts and data from across the internet to ground your agent's answers in up-to-date reality
Search Breadth — Switch between standard and deep search modes to balance between rapid fact-finding and comprehensive research across the web

The Linkup (AI Search & RAG) MCP Server exposes 2 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Linkup (AI Search & RAG) to OpenAI Agents SDK via MCP

Follow these steps to integrate the Linkup (AI Search & RAG) MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 2 tools from Linkup (AI Search & RAG)

Why Use OpenAI Agents SDK with the Linkup (AI Search & RAG) MCP Server

OpenAI Agents SDK provides unique advantages when paired with Linkup (AI Search & RAG) through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Linkup (AI Search & RAG) + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Linkup (AI Search & RAG) MCP Server delivers measurable value.

Automated workflows: build agents that query Linkup (AI Search & RAG), process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries Linkup (AI Search & RAG), another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Linkup (AI Search & RAG) tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Linkup (AI Search & RAG) to resolve tickets, look up records, and update statuses without human intervention

Linkup (AI Search & RAG) MCP Tools for OpenAI Agents SDK (2)

These 2 tools become available when you connect Linkup (AI Search & RAG) to OpenAI Agents SDK via MCP:

fetch_url

Bypasses advanced bot protections executing complex SPA JavaScript loops automatically. Fetch and extract clean content from any specific URL using Linkup Platform

search_web

Choose "fast" mapping for basic factual requests and "deep" for thorough research limits. Perform a real-time web search extracting deep answers utilizing Linkup Platform

Example Prompts for Linkup (AI Search & RAG) in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Linkup (AI Search & RAG) immediately.

"Search for the latest NVIDIA earnings report summary"

"Extract the technical specifications from this documentation URL: [url]"

"Deep search for 'AI agent security best practices 2024'"

Troubleshooting Linkup (AI Search & RAG) MCP Server with OpenAI Agents SDK

Common issues when connecting Linkup (AI Search & RAG) to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Linkup (AI Search & RAG) + OpenAI Agents SDK FAQ

Common questions about integrating Linkup (AI Search & RAG) MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.