- TRENDS
- ALERTS
- AUDIT
- HUMAN
Short answer
How can I use AI to find social mention spikes?
Your AI pulls volume data from Brandwatch to find when brand mentions deviate from the norm. It compares current conversation levels against historical trends to flag sudden surges. You get a clear view of exactly when and where your brand is trending.
The outcomes.
Where your insights land.
The AI processes Brandwatch data to deliver these specific outcomes.
TRENDS
Identify volume shifts
The AI looks at conversation totals to find spikes or drops. You see exactly when a topic starts gaining traction.
ALERTS
Spot sudden surges
Your agent flags unusual activity that breaks your typical volume patterns. This helps you catch PR crises or viral moments early.
AUDIT
Review active queries
The AI lists your existing Brandwatch monitoring setups. You can verify which topics are being tracked and which need more attention.
HUMAN
Manual sentiment check
The AI identifies the spike, but you decide if the sentiment requires a response. You handle the actual brand engagement.
The workflow
What your AI does when the data arrives.
The AI handles the heavy lifting of data retrieval and pattern recognition.
Inventory monitoring
The AI checks your current Brandwatch setup to see which brand topics are already being watched.
list_queriesPull volume data
It pulls the specific conversation counts for your chosen brand or keyword over a set period.
get_volume_aggregatesDetect anomalies
The AI compares recent volume numbers against previous days to find statistical outliers.
get_volume_aggregatesSummarize shifts
The agent explains the magnitude of the spike and identifies which specific queries drove the change.
list_queriesget_volume_aggregates
Try it
Copy these to start.
Use these prompts to begin monitoring your brand.
Starting points
These are starting points. Swap out the bracketed text with your actual Brandwatch query names or brand keywords.
Brandwatch Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_U3iNoOtAHtq2EggV7EV28iaIxEv7vfFgwz5tvTKu/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Brandwatch capabilities are ready to use.
{
"mcpServers": {
"brandwatch-mcp": {
"url": "https://edge.vinkius.com/vk_preview_U3iNoOtAHtq2EggV7EV28iaIxEv7vfFgwz5tvTKu/mcp"
}
}
}List all my current Brandwatch queries so I can see what we are tracking.
Check the volume aggregates for the [Brand Name] query over the last 7 days.
Are there any sudden spikes in volume for [Keyword] compared to last week?
Show me the volume trends for [Campaign Name] to see if it's gaining momentum.
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect Brandwatch once, then ask.
Enter your Brandwatch credentials once. Your connection is encrypted, and you can immediately start asking your AI about your social data.
Connect Brandwatch to your AIFAQ
How this task behaves.
- 01
Can the AI post replies to social media for me?
No. The AI can only read volume and query data from Brandwatch. You must handle all posting and engagement manually.
- 02
Can the AI delete my Brandwatch queries?
No. The AI can list and read your queries, but it does not have the capability to delete or modify your Brandwatch configuration.
- 03
How does the AI know if a spike is a 'crisis'?
The AI identifies mathematical spikes in volume. It cannot determine if a spike is a crisis or a positive trend without you providing the context.
- 04
Does the AI see individual social media posts?
No. This specific workflow uses volume aggregates to track trends, not individual post content.
- 05
Can I use this with any AI client?
Yes, as long as your client is MCP-compatible, like Claude, Cursor, or Windsurf.
More questions about Brandwatch? See everything the Brandwatch Connector can do
Connect Brandwatch to Claude, Cursor, ChatGPT & more
