How to Use the Exa MCP in OpenAI Agents SDK

Q: How do I initialize the Exa toolset in my OpenAI Agents SDK project?

Use MCPServerStreamableHttp to connect to the hosted Vinkius endpoint. Pass the server instance inside the mcpservers list when instantiating your Agent object. Set cacheToolsList=True to avoid redundant network calls during agent startup.

Q: Can an agent built with OpenAI Agents SDK run a search on a specific domain using Exa?

Yes, your agent can call searchdomain to restrict its queries to specific sites like GitHub or StackOverflow. This is highly effective when you want to prevent the agent from pulling untrusted forum posts during technical research.

Q: How does Exa handle time-sensitive research within the OpenAI Agents SDK?

Your agent can run the searchrecent tool to fetch newly published articles and trending topics. This lets your production system analyze breaking news without relying on outdated model knowledge.

Give your OpenAI Agents SDK production deployment real-time web search with Exa, protected by built-in schema guardrails.

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

Semantic Web Discovery for OpenAI Agents SDK

The `search_neural` tool provides your autonomous agents with semantic web search capabilities to bypass static training data limitations. By connecting this Exa MCP Server to your runtime, your system can trigger queries based on conceptual meaning rather than exact keywords. This prevents your agents from hitting dead ends when users ask questions with non-obvious phrasing. The OpenAI Agents SDK automatically maps the JSON schemas from this MCP Server directly into the agent's function-calling registry. You don't have to write custom wrappers or handle manual argument extraction. Once triggered, the agent simply calls the tool, receives the clean web text, and continues its task.

Deep Competitor Auditing via Similarity Matching

The `find_similar` tool allows your production agent to instantly discover related websites on the fly. This avoids the overhead of orchestrating complex scraper pipelines or scraping broad search engines that return irrelevant ad links. You can chain this with `find_similar_with_contents` to grab the actual text of those similar pages in a single trip. Since the OpenAI Agents SDK handles agent-to-agent handoffs, a research agent can pull this structural data and pass it directly to a writing agent without losing context.

Targeted Content Extraction with Built-in Guardrails

The `get_contents` tool extracts clean, parsed markdown of specific URLs directly into your agent's context window. Before execution, the SDK's built-in schema validation checks the input arguments, ensuring your agent never passes malformed parameters to the API. If a user asks a highly specific question, your agent can call `answer` to get a direct, structured response backed by web sources. This keeps your token usage predictable because you aren't feeding entire web pages into the primary model when a simple, verified answer is all that is required.

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

Use `MCPServerStreamableHttp` to connect to the hosted Vinkius endpoint. Pass the server instance inside the `mcp_servers` list when instantiating your `Agent` object. Set `cacheToolsList=True` to avoid redundant network calls during agent startup.

Yes, your agent can call `search_domain` to restrict its queries to specific sites like GitHub or StackOverflow. This is highly effective when you want to prevent the agent from pulling untrusted forum posts during technical research.

Yes, the SDK automatically discovers all ten tools exposed by the Exa MCP Server at runtime. You do not need to manually define Python function schemas or write boilerplate integration code.

Your agent can run the `search_recent` tool to fetch newly published articles and trending topics. This lets your production system analyze breaking news without relying on outdated model knowledge.

All target URLs and search terms sent through the server are processed inside an ephemeral, zero-trust V8 Isolate sandbox on Vinkius. No search payloads or retrieved page contents are persisted to disk or used for model training.

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