How to Use the X (Twitter) MCP in OpenAI Agents SDK

Q: Can I search historical data using X (Twitter) with OpenAI Agents SDK?

No. The searchrecenttweets tool only looks at public tweets posted within the last seven days. If you need older data, you'll have to find another way, because this MCP Server is limited to recent activity. It’s designed for current intelligence, not deep archival dives.

Q: What type of user data does OpenAI Agents SDK touch when using X (Twitter)?

When you use the lookupuserbyusername tool, the agent accesses public profile information. This includes the user’s bio text, follower count, and whether or not they have a verification badge. It only pulls what's publicly visible on the X platform.

Q: Is finding tweet metrics reliable with X (Twitter) using OpenAI Agents SDK?

Yes. The gettweetdetails tool provides direct, numerical data points for engagement—likes, retweets, and replies. This is the raw metric you need to make a decision. It avoids any guesswork about how successful a tweet was.

Get social intelligence working with your OpenAI Agents SDK. Full X (Twitter) data flows directly into production agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect X (Twitter) MCP to OpenAI Agents SDK

Create your Vinkius account to connect X (Twitter) 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 X (Twitter) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze User Profiles via MCP Server

The `lookup_user_by_username` tool pulls full details about any X user, using only their @handle. You get the follower count, bio text, and verification status immediately. This lets your agent build a profile of key players before initiating contact or analysis. Don't waste time scraping; just call `lookup_user_by_username` to get reliable data points.

Search for Trending Topics (MCP Server)

Need to track what people are saying right now? The `search_recent_tweets` tool searches for public tweets within the last seven days. You just pass in keywords, hashtags, or specific handles. This is perfect for monitoring campaigns or finding out if a niche topic suddenly picked up steam. It keeps your agent focused on relevant, timely conversation.

Check Specific Tweet Metrics

If you have a numeric ID for a tweet, `get_tweet_details` pulls the full text and all engagement stats associated with it. You don't need to read through comments; this gives you the raw numbers. It’s fast and precise. This tool lets your agent quantify impact—how many likes or retweets that specific message actually generated.

Setup guide

Set up X (Twitter) 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 X (Twitter) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives X (Twitter) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate X (Twitter) 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="X (Twitter) Agent",
            instructions="You have access to X (Twitter) 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 X (Twitter). 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 X (Twitter) 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 X (Twitter) MCP in OpenAI Agents SDK

The OpenAI Agents SDK auto-discovers all MCP tools, including the X (Twitter) functionality. You don't need to write boilerplate code for tool calls; the agent just knows how to use them. It handles the execution flow while your guardrails keep everything safe and contained.

No. The `search_recent_tweets` tool only looks at public tweets posted within the last seven days. If you need older data, you'll have to find another way, because this MCP Server is limited to recent activity. It’s designed for current intelligence, not deep archival dives.

When you use the `lookup_user_by_username` tool, the agent accesses public profile information. This includes the user’s bio text, follower count, and whether or not they have a verification badge. It only pulls what's publicly visible on the X platform.

Yes. The `get_tweet_details` tool provides direct, numerical data points for engagement—likes, retweets, and replies. This is the raw metric you need to make a decision. It avoids any guesswork about how successful a tweet was.

The server only retrieves publicly available profile information. When you use `lookup_user_by_username`, the agent collects non-private metrics like follower count and bio text. It doesn't require any credentials or access to private messages.

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