How to Use the Brandwatch MCP in AutoGen

Q: How do AutoGen agents coordinate when pulling Brandwatch mentions?

Agents use a conversational loop where one calls getmentions and shares the payload with the rest of the group. They then deliberate on the contents to extract key themes.

Q: Can I use this Brandwatch MCP Server to trigger actions between different AutoGen agents?

Yes, an agent can use createtag based on the consensus reached during a debate. Once the group agrees on a classification, the executing agent applies the tag.

Q: How do AutoGen agents handle rate limits when querying Brandwatch?

The agents discuss their query budget before calling getvolumeaggregates. A coordinator agent regulates the frequency of calls to prevent hitting API limits.

Q: Can AutoGen agents automatically configure new tracking parameters in Brandwatch?

They can inspect existing configurations using listqueries to see what is already tracked. If a gap is found, they can recommend new setups to the user.

Run multi-agent debates in AutoGen to analyze Brandwatch consumer data and reach consensus on market trends.

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 AutoGen

Create your Vinkius account to connect Brandwatch to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Sentiment Analysis in AutoGen

This system uses `get_mentions` to feed raw social text into a multi-agent debate loop. One agent identifies negative feedback, another highlights positive sentiment, and a coordinator compiles the final summary. Because AutoGen agents discuss the findings before presenting them, you get a balanced view of the data. The MCP connection ensures that every agent in the conversation has immediate access to the same raw mentions.

Collaborative Volume Spike Investigation

The agents trigger `get_volume_aggregates` when they detect unusual patterns in your social feeds. An analyst agent flags the spike, while a research agent searches for the root cause using active query parameters. This collaborative loop operates through the MCP Server, allowing the agents to request data dynamically based on the direction of their discussion. They debate the cause of the spike until they reach a consensus.

Workspace Auditing and Query Cleanup

By calling `list_queries` and `list_tags`, your agents can audit your entire workspace to find unused tracking filters. A performance agent suggests removing redundant tags, while a compliance agent reviews the impact on active projects. They verify their findings using `list_dashboards` through the MCP Server to ensure no active reporting breaks. This process keeps your workspace clean without requiring manual inspection of each campaign.

Setup guide

Set up Brandwatch MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Brandwatch tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Brandwatch_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Brandwatch data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Brandwatch_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Brandwatch data")
    print(result.messages[-1].content)

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 AutoGen

Agents use a conversational loop where one calls `get_mentions` and shares the payload with the rest of the group. They then deliberate on the contents to extract key themes.

Yes, an agent can use `create_tag` based on the consensus reached during a debate. Once the group agrees on a classification, the executing agent applies the tag.

The agents discuss their query budget before calling `get_volume_aggregates`. A coordinator agent regulates the frequency of calls to prevent hitting API limits.

They can inspect existing configurations using `list_queries` to see what is already tracked. If a gap is found, they can recommend new setups to the user.

Your project structures and query parameters are kept strictly local within the Vinkius execution environment. No conversation history or API keys are transmitted to external servers during the agent negotiation process.

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