How to Use the Exa MCP in OpenAI Agents SDK

Feed your OpenAI Agents SDK production pipelines real-time web context using Exa neural search.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Exa MCP to OpenAI Agents SDK

Create your Vinkius account to connect Exa 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 with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Neural search with OpenAI Agents SDK

OpenAI Agents SDK uses its built-in guardrails to run `exa_search` safely, preventing your system from pulling in junk data. Your OpenAI Agents SDK agent gets clean, conceptually relevant search results from Exa instead of keyword-stuffed spam, keeping your token costs down. You can configure the Exa search depth to deep or fast directly inside your OpenAI Agents SDK agent configuration. The OpenAI Agents SDK handles the Exa tool execution automatically while the OpenAI dashboard traces the entire retrieval process in real time.

Find similar sources via MCP Server

When your OpenAI Agents SDK agent identifies a high-quality source, it passes the URL to `exa_find_similar` to discover alternative references. This helps your OpenAI Agents SDK pipeline perform deep market research without hardcoded search loops by using Exa's neural index. The OpenAI Agents SDK agent makes decisions based on Exa's semantic similarity scores. If the returned Exa search data triggers an OpenAI Agents SDK guardrail violation, the framework halts execution immediately.

Extract clean page content for agent handoffs

Your specialized OpenAI Agents SDK retrieval agent runs `exa_get_contents` to grab clean text before handing the context off to a synthesis agent. This keeps your OpenAI Agents SDK context windows small and prevents the synthesis model from choking on raw HTML scraped by Exa. By using this Exa MCP Server, the OpenAI Agents SDK handoff process becomes incredibly efficient. You avoid passing bloated payloads between your specialized OpenAI Agents SDK workers during Exa content retrieval.

Setup guide

Set up Exa 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 tools at runtime.
3

Create your Agent

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

Pass the server URL to MCPServerStreamableHttpParams and add it to your Agent constructor. The SDK auto-discovers the search tools instantly without manual schema definitions.

Yes, the SDK validates the target URL before the agent executes the tool. This prevents your agent from querying malicious or broken links.

It extracts only the clean text and highlights, stripping out raw HTML and script tags. Your OpenAI Agents SDK models process fewer tokens, lowering your API bills.

Every call to the search tools is fully logged and traced. You can monitor latency and token usage for each web query directly in your OpenAI console.

Your web search queries and scraped URLs are sent securely to the API for indexing and retrieval. Vinkius runs the connector in an isolated sandbox, ensuring your API keys and query parameters never leak to other tenants.

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