How to Build Your Marketing Intelligence Agent
Building the agent isn't a development project — it's four decisions. Here's exactly how it works.
Pick the platform you already use, add your marketing data, and connect our MCP. After that, the agent returns ranked STOP / SCALE / SHIP / WAIT actions — which channel is paying, which products buy together, whether a test is real — not a last-click dashboard you have to interpret yourself.
Step 1: Find an Agent Builder
Pick the platform you already use, or the one your team is standardizing on. Common choices:
- Microsoft Copilot Studio
- AWS Bedrock
- Google Gemini Enterprise
- Salesforce Agentforce
- Cursor — the walkthrough below uses Cursor; Claude Desktop works the same way
- More platforms being added as they gain adoption
You're not locked in — the same underlying intelligence connects to whichever builder your organization runs on.
Step 2: Add a Data Source
Every agent builder needs to know where your marketing data lives. There are two ways to connect it:
CSV / Excel
Export what you already have — ad spend and store sales, order lines, a test's visitor and conversion counts — and upload it. Fastest way to get started, no setup required.
MCP
Connect through a standard protocol built for secure, structured access. The agent queries live calculated intelligence instead of a file that went stale the moment you exported it.
What Is MCP, and How Does It Work?
MCP (Model Context Protocol) is an open standard that lets an AI agent connect directly to a live source — instead of you exporting a file and hoping it's still accurate by the time someone reads it.
In plain terms:
- Your agent builder (Copilot Studio, Bedrock, Gemini Enterprise, Agentforce, Cursor, etc.) acts as the client.
- Our MCP acts as the server — it exposes marketing intelligence (channel contribution, bundles, test verdicts, launch ramps, what a customer is worth vs what you paid) in a structured, secure format the agent can query directly.
- When your agent needs an answer — "what should we STOP, SCALE, SHIP, or WAIT on this week?" — it asks the MCP server directly, instead of working off a static file someone uploaded weeks ago.
- Because it's a standard protocol, not a custom integration, it works the same way across every agent builder — connect once per platform, and every query after that pulls current, calculated numbers.
The result: your agent isn't reading a snapshot. It's asking a live, governed source of truth every time — which is what keeps the briefing accurate and the access controlled.
Step 3: Choose MCP Where Possible
CSV upload works, but MCP is the preferable path — it's the secure, standardized way for an agent to access live data, rather than a static file that goes stale the moment you export it.
Step 4: Connect Our MCP
This is the step that turns a generic agent builder into a Marketing Intelligence Agent. Connecting our MCP is what makes the data behind every answer deterministic — not a guess dressed up as an insight, a calculated briefing you can trust twice.
Pick your platform below. Connecting our MCP is the same idea on each one — you add it once, then sign in with your Saifs AI account.
Steps to Enable MCP on AI Platforms
Open Claude and reveal the main menu
Launch Claude Desktop. In the top-left corner, click the three-dot menu to open the app's main menu.
Go to Settings
From the three-dot menu, hover over File. Click Settings (or press Ctrl + Comma).
Open the Developer config editor
In Settings, select the Developer tab. Click Edit Config at the bottom of the panel.
Locate the config file
A File Explorer window will open at the Claude config folder. Click to select claude_desktop_config.json.
Paste the Marketing Intelligence MCP
With the config file open, add this server — not the generic Saifs AI MCP. This one is Marketing Intelligence only. Then restart Claude.
{
"mcpServers": {
"marketing-intelligence": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://marketing-analysis-mcp.saifs.ai/mcp"
]
}
}
}
Launch Cursor
Open the Cursor application on your desktop. On the home screen, choose Open project, Clone repo, or Connect via SSH to begin working on a project.
Settings → Tools & Integrations
Click the gear icon (top right) or go to File → Settings. In the left panel, click Tools & Integrations. Scroll to MCP Tools and click Add Custom MCP.
Add the Marketing Intelligence MCP
After clicking Add Custom MCP, Cursor opens the MCP config file. Add this server — not the generic Saifs AI MCP. This one is Marketing Intelligence only.
{
"mcpServers": {
"marketing-intelligence": {
"url": "https://marketing-analysis-mcp.saifs.ai/mcp"
}
}
}
Click Connect
Click Connect next to the new MCP server under MCP Tools to start the integration.
Allow extension access
When prompted, select Open so Cursor can process the URI and start the login flow.
Choose a login method
On the authentication page, sign in with Google, Microsoft, Apple, or Facebook — the same Saifs AI account you already use.
Complete authentication
After you sign in, a prompt will ask to finish the connection. Click Open to complete the MCP integration in Cursor.
Verify the agent is on
The toggle should be ON. That confirms the Marketing Intelligence Agent is connected.
Open ChatGPT Settings
From the ChatGPT home page, go to Settings.
Open Connectors
Click Connectors in the settings menu.
Create a connector
Click Create in the browse connectors section.
Add the Marketing Intelligence MCP
Enter this server — not the generic Saifs AI MCP. This one is Marketing Intelligence only. Then click Save.
Server URL: https://marketing-analysis-mcp.saifs.ai/mcp
Name: Marketing Intelligence
Save and start asking
Click Save. You can now ask for STOP / SCALE / SHIP / WAIT briefings in ChatGPT.
Install an MCP-compatible client
Open the VS Code marketplace and install an MCP-compatible client.
Open the command palette
Open the command palette, type MCP: add, and select MCP: Add Server to start the wizard.
Choose HTTP server
Search MCP: Add Server and choose HTTP (HTTP or Server-Sent Events) to connect to a remote MCP server.
Enter the Marketing Intelligence MCP URL
Input this server URL — not the generic Saifs AI MCP. This one is Marketing Intelligence only. Press Enter to confirm.
https://marketing-analysis-mcp.saifs.ai/mcp
Choose installation scope
When prompted, choose Global (all workspaces) or Workspace (this workspace only).
Allow authentication
Allow the server to authenticate so VS Code can talk to the Marketing Intelligence MCP.
Verify the server is running
The MCP server should show as Running. That confirms the Marketing Intelligence Agent is connected in VS Code.
Open Windsurf
Launch Windsurf, then open an existing project folder or create a new one from the welcome screen.
Configure the MCP server
Open or create mcp_config.json in your project or settings directory and add the server.
Access MCP server settings
Open Windsurf settings and go to Cascade or MCP Servers. Click Manage MCPs or Open MCP store.
Add the Marketing Intelligence MCP
Use Manage MCP servers or View raw config. Add this block — not the generic Saifs AI MCP. This one is Marketing Intelligence only.
{
"mcpServers": {
"marketing-intelligence": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://marketing-analysis-mcp.saifs.ai/mcp"
]
}
}
}
Verify the agent is on
The toggle next to the server should be ON. That confirms the Marketing Intelligence Agent is connected in Windsurf.
What Our AI Agent Can Actually Do
Once connected, our AI Agent isn't answering from a static file — it's querying live, calculated intelligence every time. Here's what that looks like in practice.
Say you run paid social plus a Shopify store. You export Meta and Google spend alongside store sales. Every time you ask, without anyone rebuilding a dashboard, the MCP scores the mix:
- Every channel gets a real contribution — not last-click. Ads Manager says Meta got the clicks. The briefing says extra Meta spend is buying less. The channel is tired — pouring more in won't move sales the way it used to.
- Our AI Agent flags what last-click would miss. Last-click says Google wins. The mix says Google is getting credit for sales that were already coming, while another channel still returns and Meta is over-funded. Nobody complained. The dashboard still looks busy. The underlying signal has shifted — and by the time you find out after the month closes, that budget is gone.
- Our AI Agent converts that signal into a dollar figure. Cut the tired channel — it looks like you're wasting spend over this period. Move that budget toward the channel that's still returning. Keep the homepage test running — it isn't ready to ship. That's a decision, not a guess.
- You ask our AI Agent a plain question. In Cursor, Copilot Studio, or wherever the agent lives, you type: "What should we STOP, SCALE, SHIP, or WAIT on this week?" Our AI Agent queries the MCP in real time and answers: "Cut Channel X — shift that budget toward Channel Z. Keep the homepage test running."
- Our AI Agent explains itself when asked. You follow up: "Why cut Meta?" It doesn't deflect — it shows the why: extra spend is buying less, last-click overstated Google, the test still needs more visitors, and which products people actually buy together if you asked about bundles.
- Your team acts — same day, not next quarter. A mix change prioritized by our AI Agent instead of guessed at is the difference between finding out a channel was saturated after the budget is gone, and moving the next rupee before it's wasted.
That's the shift: from a dashboard you have to remember to check, to an agent that reads the mix, tests, and baskets and tells you — in dollars — exactly where this week's budget is worth the most.
"Here's our Meta/Google spend and Shopify sales — what should we STOP, SCALE, SHIP, or WAIT on this week?"
"We're pouring money into Meta and sales aren't moving. Last-click says Google wins — is that real?"
"Which products should we bundle? Is this landing-page win real, or should we keep the test running?"
Why Connect Our MCP
Deterministic data
Same input, same output, every time. The numbers you get are calculated by proven statistical models, not generated as a plausible-sounding guess.
Privacy
Full SOC 2 compliance. Your marketing data stays where it belongs — no black-box vendor holding a copy you can't audit.
Less token usage
Purpose-built models do the heavy lifting instead of an LLM re-processing your entire export on every query — cheap enough to re-run as your mix evolves.
Battle-tested
Built on statistical models with decades of published, peer-reviewed use — not a new algorithm hoping it works on your mix.
Connect MCP for Creating a Marketing AI Agent
You've seen how it works — deterministic, private, battle-tested, and ready to run on the platform you already use. Connecting takes minutes, and every briefing after that tells you what to STOP, SCALE, SHIP, or WAIT on.
Connect Our MCP →No credit card. No data science team. Just your CSV and a few minutes.
