Connect Salesforce to Cursor

Windsor.ai gives Cursor access to 347 Salesforce fields. These are some of the groups; the Salesforce field reference lists all of them:

• Opportunities: Opportunity Name, Opportunity Amount, Opportunity Stage, Opportunity Probability (%), Opportunity Close Date, Opportunity Type, Opportunity Lead Source, Opportunity Won, Opportunity Owner ID.
• Leads: Lead Source, Lead Status, Lead Company, Lead Industry, Lead Created Date, Lead Converted, Lead Converted Date.
• Accounts: Account Name, Account Industry, Account Type.
• Campaigns: Campaign Name, Campaign Type, Campaign Actual Cost in Campaign, Campaign Leads in Campaign, Campaign Converted Leads in Campaign, Campaign Value Won Opportunities in Campaign.

Cursor works best when you ask it to build something with a clear output. Each of these names the fields to use and the file or canvas you want back:

• Pull Opportunity Name, Opportunity Amount, Opportunity Stage, Opportunity Probability (%) and Opportunity Close Date for open opportunities. Build a canvas with total and probability-weighted amount by stage and by close month for the next two quarters, and list the 10 largest deals under it.

• Pull open opportunities with Opportunity Name, Opportunity Owner ID, Opportunity Stage, Opportunity Amount and Opportunity Close Date. Write a Python script that lists every deal whose close date has passed, groups them by owner with the total amount, and writes stale_deals.md for the pipeline review.

• Pull Lead Source, Lead Created Date, Lead Converted and Lead Converted Date for leads created in the last two quarters. Build a chart of lead count and conversion rate by source, and add the median days from creation to conversion for each source.

• Pull Campaign Name, Campaign Type, Campaign Actual Cost in Campaign, Campaign Leads in Campaign, Campaign Converted Leads in Campaign and Campaign Value Won Opportunities in Campaign. Write a script that calculates cost per lead and won value per unit of cost for each campaign and saves campaigns.csv sorted by return.

• Pull won opportunities this year with Opportunity Amount, Opportunity Type, Account Name and Account Industry. Write a report as won_deals.md with won amount by industry and by opportunity type, and the 10 largest accounts. Keep the script so I can rerun it each month.

Yes. Cursor can render a dashboard, analysis or report as a canvas next to the chat, and it saves the canvas so you can reopen and rerun it later with fresh data. On paid Cursor plans you can publish a canvas to a read-only share link that members of your Cursor team can open. See the Cursor canvas documentation for the current plan requirements.

Yes. Windsor.ai supports 350+ data sources, so you can connect Salesforce alongside tools such as LinkedIn Ads, Google Ads or HubSpot and ask Cursor to work with them together. For example, ask Cursor to put Salesforce won Opportunity Amount by Opportunity Lead Source next to LinkedIn Ads Spend and Google Ads Cost, and write a script that reports won revenue per unit of ad spend for each channel.

Open Settings in Cursor Desktop, go to Tools & Integrations → New MCP Server, and add Windsor to mcp.json:

{
  "mcpServers": {
    "windsor": {
      "url": "https://mcp.windsor.ai/"
    }
  }
}

Save the file, click Authenticate next to Windsor in your MCP list, and sign in to Windsor.ai in the browser.

No. The connection takes no code: connect Salesforce in Windsor.ai, add Windsor to Cursor’s MCP settings, and sign in. After that you describe what you want in plain language, and Cursor writes and runs the code. You can read and edit everything it produces.

The free forever plan covers 1 data source, so connecting Salesforce on its own costs nothing and needs no credit card. Combining Salesforce with other sources, such as LinkedIn Ads or Google Ads, needs a paid plan: $19/month for 3 sources or $99/month for 7. Cursor is billed separately by Cursor. See the pricing page.

Yes. These are the resources to start with for the Salesforce to Cursor integration:

• Salesforce field reference
• Cursor integration documentation
• Windsor.ai connectors for Cursor