How to Use the Exa AI MCP in OpenAI Agents SDK

Q: Does Exa AI support filtering by domain within my OpenAI Agents SDK workflow?

You can pass domain constraints to the searchspecificdomains tool. The agent handles these parameters just like any other function argument.

Q: What happens if the API connection drops during an OpenAI Agents SDK session?

You can check the link with getapistatus. If the connection is down, your agent can catch the error and retry or notify you.

Get neural search results directly inside your OpenAI Agents SDK production pipeline.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Exa AI MCP to OpenAI Agents SDK

Create your Vinkius account to connect Exa 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 Exa AI with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Native integration for OpenAI Agents SDK

Your agent discovers all twelve search tools automatically. You initialize the connection using the standard context manager and pass the server instance to your agent constructor. Caching the tool list prevents unnecessary overhead during runtime. This setup ensures your production agent system handles data retrieval without manual configuration.

Advanced content extraction for your agents

When your agent needs raw data, use `extract_page_content` or `search_with_contents`. These tools pull clean text directly from the web into your agent's context window. Combined with `get_query_highlights`, your system pulls only the relevant snippets. This keeps your agent's token usage predictable while maintaining high retrieval quality.

Real-time web access for your MCP Server

Need the latest info? Use `perform_live_crawl` to fetch data that hasn't been indexed by standard search engines yet. This MCP Server gives your agent a direct window into the live web. Your agent can also filter by date using `search_by_crawl_date`. You get granular control over the freshness of the data your agent processes.

Setup guide

Set up Exa 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 Exa AI tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Exa 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 Exa 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="Exa AI Agent",
            instructions="You have access to Exa 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 Exa 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 Exa 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 Exa AI MCP in OpenAI Agents SDK

You simply call the agent's tool execution method with your query string. The agent automatically maps the request to the `semantic_search` tool provided by the server.

Yes, because the server tools are registered as native functions. The SDK treats the output of Exa AI as standard input for the next step in your agent's logic.

You can pass domain constraints to the `search_specific_domains` tool. The agent handles these parameters just like any other function argument.

You can check the link with `get_api_status`. If the connection is down, your agent can catch the error and retry or notify you.

Exa AI only retrieves public web data based on your specific queries. The server does not store your search history, and all traffic is handled over encrypted connections.

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