Automate AI visibility reports with n8n
n8n's AI Agent can call MCP servers through the MCP Client Tool node. Point it at Data AI Search and a workflow can read your brand's Insights and audits on a schedule, then post the summary wherever your team reads it.
Connect n8n to Data AI Search
- 1
Copy your server URL
Sign in to the Data AI Search dashboard, open Integrations → MCP and copy the server URL. Your API key is already in it.
- 2
Add an AI Agent
Create a workflow with a trigger (a Schedule Trigger for a weekly report, or a Chat Trigger to ask questions) and an AI Agent node with a chat model attached.
- 3
Attach the MCP Client Tool
On the AI Agent's Tool input, add an MCP Client Tool. Paste your server URL as the endpoint, set Server Transport to HTTP Streamable and Authentication to None, because the key is in the URL. For a read-only report, set Tools to Include to Selected → brand_insights.
MCP Client ToolEndpoint: https://api.dataaisearch.com/mcp?api_key=YOUR_API_KEY Server Transport: HTTP Streamable Authentication: None Tools to Include: All (or Selected → brand_insights) - 4
Give it a job and test it
Prompt the agent, for example "Summarise this week's Insights for [brand]: new questions, mention rate, competitors named". Run the workflow once by hand, then send the output to Slack, email or a sheet.
Replace YOUR_API_KEY with your own key, or copy the full URL from Integrations → MCP in the Data AI Search dashboard, where it is already filled in. The URL is the key: anyone who has it can read your workspace and spend its credits.
What n8n can do with your data
The server has three tools, one per pillar. Each takes a brand name; ask about a brand the workspace doesn't have and the tool replies with the names it does have.
brand_insights
Read-only. The real questions your brand's buyers ask AI, how AI answers them, who it names instead of you, keywords and segments.
Tool referenceai_visibility_audit
Read the Visibility Score, prompts, clusters and next actions, or set the audit up, add questions and run them.
Tool referencewebsite_audit
Read the site audit, root causes, weakest pages and action list, or start, refresh, re-run and re-check a page.
Tool reference
- “Every Monday: summarise [brand]'s Insights. New buyer questions, how often AI names us, who it names instead.”
- “List the Website Audit actions for [brand] that are still open, highest priority first.”
- “Check the AI Visibility run status for [brand] and report any failed prompts.”
- “For each brand in the workspace, write one line on its latest Insights.”
Before you rely on it
- The key sits in the endpoint URL, so it is saved with the workflow. Anyone who can open or export the workflow can see it; limit who can edit it.
- For scheduled runs, include only brand_insights. The audit tools can start runs that spend credits, and an unattended agent shouldn't make that call.
- Every tool call costs 1 credit, so a weekly report that makes a few calls costs only a few credits a week.
- Name the brand exactly as the workspace does. brand_insights with view brands lists the names.
- "Could not connect" in the MCP Client Tool
- Check that the transport is HTTP Streamable, not SSE, and that the endpoint still has ?api_key= in it.
- There's no HTTP Streamable option
- Update n8n. Older versions of the node only spoke SSE.
- "MCP integrations aren't available on your plan"
- The workspace is on the Free plan. Upgrade to Starter or higher.
n8n and Data AI Search: questions
Do I need the community n8n-nodes-mcp package?
No. n8n's built-in MCP Client Tool node is enough for a remote server like this one.
Can n8n run an audit for me?
It can, if you include ai_visibility_audit or website_audit in the node's tools. We suggest doing that only in workflows a person starts, not on a schedule.
What does it cost?
1 credit per call from your Data AI Search workspace. Setting up or running AI Visibility prompts and starting a Website Audit cost what they cost in the dashboard.