How to Use the Exa AI MCP in OpenAI Agents SDK

Q: How do I configure Exa AI within the OpenAI Agents SDK?

Point your client to the Vinkius MCP endpoint. Use the MCPServerStreamableHttp class to establish the connection, then pass the server instance directly to your agent constructor.

Build production-ready search agents using OpenAI Agents SDK backed by Exa AI's semantic web index.

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

Semantic search via OpenAI Agents SDK

`search_web` acts as your agent's primary gateway to Exa AI's semantic search database. Instead of dumping raw keyword matches, this tool returns links graded by conceptual relevance to feed your agent's reasoning loops. You get clean, pre-filtered results that fit directly into your context window. This prevents your production runs from wasting tokens on irrelevant web noise.

Deep content retrieval with built-in guardrails

`get_contents` pulls down cleaned HTML and plain text from specific Exa IDs without the typical scraping overhead. Your agent grabs the exact text it needs to execute tasks, avoiding the raw markup that confuses LLMs. This MCP Server allows your OpenAI agents to inspect the actual page data before passing it to downstream tasks. If you need both search and content in a single round-trip, `search_with_contents` executes both operations to cut network latency.

Locate related web assets automatically

`find_similar` takes a target URL and returns a list of matching domains that share the same semantic profile. This tool handles the heavy lifting when your agent needs to map out a competitive market or find alternative sources. You can monitor your operational overhead using `get_api_usage` to track crawl statistics and API calls. Keep an eye on these metrics directly through your OpenAI tracing dashboard to maintain budget control.

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

Point your client to the Vinkius MCP endpoint. Use the `MCPServerStreamableHttp` class to establish the connection, then pass the server instance directly to your agent constructor.

Yes, the SDK natively routes semantic queries to the Exa engine. Your agent can then evaluate the context of the returned links to make smarter execution decisions.

The server handles API limits on the backend and exposes usage metrics through `get_api_usage`. You can write custom guardrails in the OpenAI Agents SDK to pause execution when your monthly crawl statistics approach their limit.

The SDK allows you to spin up multiple specialized agents that query the Exa AI backend concurrently. You can hand off tasks between agents while maintaining a single, shared connection pool to the MCP server.

All web search queries and scraped HTML text pass through an ephemeral, zero-trust V8 sandbox. Vinkius does not store the returned page text or your search parameters, ensuring your proprietary research data remains private.

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