Automate workflows

• Daily Slack digests with yesterday’s revenue, orders, and conversion rate.
• Weekly channel breakdowns comparing spend, ROAS, and CPA across ad platforms.
• Google Sheets exports that append a row of key metrics to a spreadsheet on a schedule.

​

How it works

1. Trigger: A schedule fires at a set interval (daily, weekly, hourly).
2. AI Agent + MCP: The trigger invokes an AI Agent (e.g. ChatGPT, Claude) that calls the Converge MCP server to pull your analytics data.
3. Output: The AI Agent formats the results and sends them to a destination like Slack, or email.

​

Set up automated reports

• n8n
• Zapier

n8n is an open-source workflow automation platform. It has built-in support for AI agents and MCP tool calling.

1

Create a new workflow with a Schedule Trigger

In n8n, create a new workflow. Add a Schedule Trigger node and set the interval (e.g., every day at 9:00 AM, every Monday at 8:00 AM, or every hour).In the node’s Settings tab, optionally enable Retry On Fail. MCP calls can occasionally time out, and retries make sure your report still goes out.

2

Configure the AI Agent

Add an AI Agent node and connect it to the Schedule Trigger. Set Source for Prompt to Define below, then, add your desired prompt, or paste one of the example prompts into the Prompt field.Then configure two sub-nodes:

1. Chat Model: Choose OpenAI (GPT) or Anthropic (Claude) and connect it with your API key from that provider.
2. Tool: Add an MCP Client Tool sub-node with the following settings:
   • Endpoint: https://app.runconverge.com/api/mcp
   • Server Transport: Streamable HTTP
   • Authentication: MCP OAuth2
   • Credential for MCP OAuth2 API: Click to create a new credential, n8n will open the Converge OAuth flow.
   • Tools to include: All
   • Under options, optionally set a timeout

Before proceeding, we recommend testing this part of the workflow with Execute step (available on the AI agent node). You should see your report in the output panel.

3

Add an output node

Add an output action after the AI Agent: for example, Slack (send a channel message), Gmail (send an email), or Google Sheets (append a row). Map the AI agent’s output to the message body using the expression {{ $json.output }}.See output recommendations below for tips on formatting per destination.

4

Test and activate

Click Execute workflow to run it once and verify the output. When everything looks good, publish your workflow to Active.

Zapier is a workflow automation platform that connects thousands of apps. Its MCP Client integration lets you call tools on any MCP server — including Converge — directly from a Zap.

1

Create a new Zap with a Schedule trigger

In Zapier, create a new Zap. Choose Schedule by Zapier as the trigger and set the frequency (e.g., every day, every week, or every hour).

2

Add the MCP Client action

Add a new action step and select MCP Client by Zapier as the app. Then configure it:

1. Account: Connect the Converge MCP. Enter the server URL https://app.runconverge.com/api/mcp, set transport to Streamable HTTP, and choose OAuth for authentication. Zapier will open the Converge OAuth flow in your browser. Sign in with the same Google account you use for Converge.
2. Tool: Pick the Converge tool you want to call (e.g., Get Analytics View Data or Analytics Query). Each MCP Client action is tied to one specific tool.
3. Options: Fill in the tool’s parameters (workspace ID, date range, metrics, etc.). The fields shown here depend on the tool you selected.

Click Test step to verify the tool returns data.

3

Format the results with AI

The MCP Client returns unstructured data. To turn it into a readable report, add an AI step after the MCP step. Zapier supports several AI providers, pick whichever you prefer:

• AI by Zapier: Built-in option that lets you pick from popular models (including Claude and GPT) without bringing your own API key. Includes a prompt generator and templates.
• Anthropic (Claude) or OpenAI (ChatGPT): Connect your own API key for more control over model selection and parameters.

Set the action event to Send Message (or the equivalent for your chosen provider). Then fill in:

• User Message: Write your formatting instructions, then click the + button to insert the MCP step’s Content Text output. For example: “Format the following data as a Slack message with bold metric names and bullet points. Keep it under 300 words. No code fences. Data:” followed by the inserted MCP output.
• Model: Pick the model you want to use (e.g., claude opus 4.6).
• System (optional): Add a system prompt like “You’re a marketing analyst. Output only the formatted report, no extra commentary.”

Leave Memory Key empty, it’s not needed for one-off formatting tasks.Check writing good prompts and output recommendations for more tips on getting clean, destination-ready output.

4

Add an output action

Add a final action to send the formatted report somewhere: Slack, Gmail, Google Sheets, or any other Zapier-supported app. Map the AI step’s output to the message body.For example, in a Gmail action: in the Body field, click the + button to insert data from the previous AI output step (for example, Response Content Text). Make sure Body type is set to HTML if your prompt asks the model to produce HTML output.See output recommendations for format tips per destination.

5

Test and publish

Test each step end-to-end by clicking Test step on every action in sequence. When everything looks good, click Publish to activate the Zap.

​

Output recommendations

• Email (Gmail, Outlook): Ask for HTML output. Email clients render HTML natively, so you get clean tables, color coding, and metric cards without any extra work. Some email clients require you to set the Email Type to HTML. Include a note in your prompt like: “Output raw HTML only, no markdown fences and no prose.”
• Slack: Ask for Markdown output. Slack supports a subset of Markdown (bold, lists, code blocks) but doesn’t render HTML. Keep reports concise, as long messages get truncated. Use bullet points and bold text for scanability.

​

Writing good prompts

• Be specific about data. If you want a specific view, use its exact ID (available in the URL of the view in Converge). Instead of “pull my pacing sheet”, say “pull the Pacing data (view_id: 12) for workspace .”
• Specify the output format. Tell the agent exactly how to structure the result: HTML table, Markdown bullets, CSV, etc. Make clear that the output will be directly used in the next step, so it shouldn’t include extra prose or commentary.
• Be explicit about comparisons. If you want week-over-week or month-over-month changes, spell it out. Don’t leave it as optional, LLMs tend to skip anything that’s framed as “nice to have.”
• Set formatting constraints. If the output goes straight to email or Slack, add rules like “no code fences,” “no markdown around the HTML,” or “keep it under 500 words.”

​

Example prompts

Pull yesterday's data for workspace {your_workspace_id}. Include:
revenue, total orders, average order value, and conversion rate.
Compare each metric to the same day last week and show the percentage
change in parentheses.

Format as a Slack message using bold for metric names and bullet
points. Keep it under 300 words. No code fences.

Pull last week's performance for workspace {your_workspace_id},
broken down by channel. For each channel, include: spend, revenue,
ROAS, and cost per acquisition. Sort by revenue descending. Compare
each metric to the previous week and show the change as a percentage.

Format as an HTML table with color-coded percentage changes (green
for positive, red for negative). Output raw HTML only, no code
fences, no markdown, no surrounding prose.

Fetch the Pacing data (view_id: {your_view_id}) for workspace
{your_workspace_id}. Format the results as a clean HTML table with
headers.

Output raw HTML only, no code fences, no markdown, no extra text.