How to Use the Brandwatch MCP in LangChain

Q: How do I pass Brandwatch query outputs to other tools in my LangChain graph?

You configure your LangChain agent to output the result of getmentions directly into your vector database or next chain node. The schema mapping is handled automatically by the adapter, turning raw JSON into document objects.

Q: Can a LangChain agent manage multiple Brandwatch projects simultaneously?

Yes, by chaining listprojects with specific queries. The agent inspects the project list, selects the correct ID, and runs its search parameters across those distinct workspaces.

Q: What happens if a query requested by the LangChain agent does not exist in Brandwatch?

The agent calls listqueries first to check availability. If the query isn't there, the chain catches the error, allowing your agent to write a new query or alert you.

Feed live Brandwatch consumer research directly into your LangChain pipelines to track social sentiment in real-time.

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 LangChain

Create your Vinkius account to connect Brandwatch to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Track Social Volume with LangChain Chains

This MCP Server setup runs `get_volume_aggregates` to pull historical and live social volume spikes directly into your active chains. Your agent reads the volume data, compares it against previous runs, and passes the raw numbers to the next node in your graph without manual data entry. You get clean, numeric volume inputs that feed directly into decision-making logic. LangSmith traces every step of this process, tracking how your agent decided to pull that specific query volume and how much latency the API call added to the run.

Dynamic Tagging on Incoming Mentions

The agent executes `get_mentions` to grab raw social posts and immediately follows up with `create_tag` to categorize them based on sentiment. The workflow loops through new posts, evaluates the text, and applies the appropriate label inside your project automatically. This automation runs entirely through an MCP Server connection, meaning your agent handles the decision loop locally before pushing the updated tags back to your active project. You don't write custom API glue code; you just define the classification prompt and let the pipeline run.

Map Project Dashboards and Queries

By calling `list_projects` and `list_queries`, the agent maps out your entire workspace structure before running any consumer research tasks. It identifies which active queries are available so it never tries to pull data from a non-existent tracking setup. Linking these tools into a LangChain ReAct agent prevents broken steps during long execution runs. Checking the workspace layout first allows the agent to grab the correct query ID and safely request specific dashboard details using `list_dashboards`.

Setup guide

Set up Brandwatch MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Brandwatch tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "brandwatch-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Brandwatch transactions"
    })
    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 LangChain

You configure your LangChain agent to output the result of `get_mentions` directly into your vector database or next chain node. The schema mapping is handled automatically by the adapter, turning raw JSON into document objects.

Yes, by chaining `list_projects` with specific queries. The agent inspects the project list, selects the correct ID, and runs its search parameters across those distinct workspaces.

The server batches your requests through standard HTTP transport. It feeds `get_volume_aggregates` results directly into your pipeline, letting LangSmith trace the token usage and latency of every single call.

The agent calls `list_queries` first to check availability. If the query isn't there, the chain catches the error, allowing your agent to write a new query or alert you.

Your raw social mentions and query configurations stay inside the Vinkius sandboxed environment. No external servers store your API tokens, and data is only transmitted directly to your running LangChain 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