How to Use the BrandMentions MCP in OpenAI Agents SDK

Q: How does the OpenAI Agents SDK manage long-running BrandMentions searches?

The agent initiates a search job with postsearch and can monitor progress using getprocessedmentions. This keeps your agent responsive instead of blocking while waiting for the full job to finish.

Q: What happens if my API credits run out during an active run?

Your agent can proactively call getremainingcredits before launching new search jobs. This lets you build fallback logic to pause operations before encountering hard API errors.

Feed clean social listening data directly to your OpenAI Agents SDK pipelines with built-in guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect BrandMentions MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run BrandMentions campaigns inside OpenAI Agents SDK

This MCP Server lets your autonomous agents set up and tear down brand tracking campaigns on the fly. By exposing `add_project` and `delete_project` directly to your agent constructors, you let your system spin up targeted tracking when a new competitor launches. The SDK handles the heavy lifting, making sure these tools are auto-discovered without writing custom boilerplate. Because production safety matters, you can wire up guardrails to inspect these actions before execution. If an agent tries to delete a critical project, your validation logic stops it. You get clean tracking setup with the peace of mind that your agent won't accidentally wipe out active campaigns.

Track live web mentions with built-in tracing

Pulling raw data into an LLM can get messy fast. This MCP server lets your OpenAI agents run live queries using `post_search` and grab partial results via `get_processed_mentions` while a job is running. You can watch the whole data-fetching pipeline unfold inside your OpenAI tracing dashboard, making it easy to debug where a query stalled. Once the search job finishes, the agent can call `get_mentions` to ingest the complete dataset. The SDK manages handoffs between specialized agents, meaning one agent can focus on fetching the raw mentions while another handles the sentiment analysis.

Monitor influencer outreach and budget limits

Keep your automated outreach systems from running blind. Your agents can query `get_influencers` to find key voices for specific campaigns and check `get_remaining_credits` to prevent costly API overages. It keeps your automation running within strict operational boundaries. You can list all active tracking campaigns using `list_projects` and get detailed reports with `get_project_mentions`. Everything stays contained within your secure MCP context, giving you a reliable way to run marketing automation at scale.

Setup guide

Set up BrandMentions 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 BrandMentions tools at runtime.
3

Create your Agent

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

Run the agent

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

You install the library, set up your MCP server streamable HTTP parameters, and pass the server directly to your Agent constructor. The SDK auto-discovers all tools like `list_projects` with zero manual configuration.

Yes. You can enforce guardrails in your agent pipeline to restrict access to destructive actions like `delete_project`. This keeps your brand tracking safe while letting agents read data freely.

The agent initiates a search job with `post_search` and can monitor progress using `get_processed_mentions`. This keeps your agent responsive instead of blocking while waiting for the full job to finish.

Your agent can proactively call `get_remaining_credits` before launching new search jobs. This lets you build fallback logic to pause operations before encountering hard API errors.

All brand tracking queries and social mentions process through a zero-trust, ephemeral V8 isolate sandbox. Your API keys and fetched mention data are never cached or logged on Vinkius servers, ensuring strict isolation between your OpenAI runs.

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