How to Use the Mention MCP in OpenAI Agents SDK

Q: How do I trace Mention tool calls in the OpenAI Agents SDK dashboard?

Every time your agent calls getmentioncontent or searchmentionsbykeyword, the SDK logs the exact tool input and output payloads. You can inspect these executions in real time on your OpenAI developer dashboard to debug agent behavior.

Track brand reputation safely using the OpenAI Agents SDK to query Mention alerts and analyze reach metrics with strict guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mention MCP to OpenAI Agents SDK

Create your Vinkius account to connect Mention 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 Mention with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Deploy Guarded Mention Alerts via OpenAI Agents SDK

Your agent uses `create_monitoring_alert` to establish real-time tracking parameters for brand keywords. The OpenAI Agents SDK applies runtime guardrails to ensure the agent does not create duplicate tracking parameters or exceed API quota limits during execution. If the OpenAI Agents SDK attempts to modify your tracking setup, it validates the payload before sending it to the MCP Server. This setup stops runaway loops from modifying your active Mention alerts without explicit developer approval.

Track Reputation Signals with Multi-Agent Handoffs

The main agent executes `list_recent_mentions` to pull the latest brand discussions from social media and news sources. Once the data arrives, the OpenAI Agents SDK triggers a handoff to a specialized sentiment analysis agent to evaluate the text. This specialized agent then uses `favorite_mention` to flag critical customer issues for your support team. The entire process gets recorded in your OpenAI developer dashboard for step-by-step auditing.

Analyze Brand Reach Metrics Safely

Your agent runs `get_alert_statistics` to fetch performance data and reach metrics across your active alerts. The OpenAI Agents SDK manages these calls using an ephemeral connection, ensuring your brand metrics are processed without local storage overhead on the MCP transport layer. By calling `get_alert_details` alongside these statistics, the agent builds a complete picture of your brand's share of voice. The SDK's built-in tracing lets you inspect exactly how the agent parses the raw JSON statistics.

Setup guide

Set up Mention 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 Mention tools at runtime.
3

Create your Agent

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

Run the agent

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

The SDK connects using the Vinkius managed endpoint, which injects your API credentials securely at the transport layer. Your Python code only needs to pass the single Vinkius token to MCPServerStreamableHttpParams, keeping your credentials out of raw agent logs.

Yes, you control tool access directly in your Python code when passing the toolset to the Agent constructor. You can expose only list_recent_mentions and mark_mention_as_read to triage agents, while keeping configuration tools like remove_monitoring_alert restricted on the MCP Server.

Every time your agent calls get_mention_content or search_mentions_by_keyword, the SDK logs the exact tool input and output payloads. You can inspect these executions in real time on your OpenAI developer dashboard to debug agent behavior.

Absolutely. The SDK uses async with context managers to handle HTTP connections, allowing your agent to run list_monitoring_alerts concurrently without blocking your main application loop.

The SDK never writes your account data, profile details, or webhook configurations to disk. All data fetched via get_my_profile and list_active_webhooks remains in transient memory within an isolated V8 sandbox and is discarded immediately after the agent finishes execution.

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