How to Use the Brandwatch MCP in OpenAI Agents SDK

Q: How do I initialize the Brandwatch MCP Server using the OpenAI Agents SDK?

Install the SDK using pip, then configure MCPServerStreamableHttp with your Vinkius endpoint. Pass this instance into your agent constructor using the mcpservers argument and set tool caching to true.

Q: Can my OpenAI Agents SDK handle multi-agent handoffs for Brandwatch tasks?

Yes. You can route social data from getmentions to an analysis agent, then hand off to a tagging agent that executes createtag to organize the findings.

Q: How does the OpenAI Agents SDK manage tool caching with Brandwatch?

Set cacheToolsList=True in your SDK configuration. This prevents your agent from repeatedly querying listqueries and listtags, reducing latency on every run.

Q: What happens if a Brandwatch query returns thousands of mentions?

The getmentions tool returns a structured payload that your agent processes in chunks. You should set system instructions to limit the initial count to avoid hitting model context windows.

Connect your OpenAI Agents SDK directly to Brandwatch MCP Server to track sentiment and pull social mentions 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 Brandwatch MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Auto-discover Brandwatch tools for your OpenAI agents

The `list_projects` tool lets your OpenAI Agents SDK query active Brandwatch projects the second you spin it up. No manual schema mapping or custom API wrappers needed here. Your agent reads the available endpoints, checks your setup, and starts pulling data immediately. By passing the server configuration to your agent constructor, you let the agent map out `list_queries` and `list_tags` dynamically. This setup ensures that when you run multi-agent MCP workflows, each specialized agent knows exactly which consumer research tools it has permission to call.

Guardrail-validated social sentiment tracking

The `get_volume_aggregates` tool runs within your OpenAI Agents SDK safety constraints to verify query volumes before executing downstream actions. This setup stops runaway loops before they start costing you money on API calls. When your agent pulls raw text using `get_mentions`, the SDK validates the payload structure against your pre-defined security rules. You get clean, verified data without worrying about raw, unescaped social media text injecting malicious instructions into your LLM context.

Trace Brandwatch MCP Server calls in your dashboard

The `list_dashboards` tool exposes your Brandwatch workspace structure to your OpenAI Agents SDK while logging every single transaction to your telemetry dashboard. You see exactly when your agent checks a dashboard and how much context it consumes. If an agent attempts to organize chaotic social data by running `create_tag`, the entire execution path shows up in your tracing logs. This visibility makes it easy to debug agent handoffs when passing Brandwatch project data between your research agent and your reporting agent.

Setup guide

Set up Brandwatch 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 Brandwatch tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the SDK using pip, then configure `MCPServerStreamableHttp` with your Vinkius endpoint. Pass this instance into your agent constructor using the `mcp_servers` argument and set tool caching to true.

Yes. You can route social data from `get_mentions` to an analysis agent, then hand off to a tagging agent that executes `create_tag` to organize the findings.

Set `cacheToolsList=True` in your SDK configuration. This prevents your agent from repeatedly querying `list_queries` and `list_tags`, reducing latency on every run.

The `get_mentions` tool returns a structured payload that your agent processes in chunks. You should set system instructions to limit the initial count to avoid hitting model context windows.

Your Brandwatch API tokens and social mention text never persist on Vinkius. The MCP server operates in an ephemeral, zero-trust V8 sandbox that destroys the runtime memory the moment your SDK finishes pulling data.

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