Overview
Windsor MCP Server enables your LLM to query, explore, and analyze your Windsor.ai data with zero SQL writing or custom scripting. Built on the Model Context Protocol (MCP), it exposes Windsor.ai datasets to Claude, Perplexity, Cursor and other MCP-compatible agents, providing real-time access to performance marketing, sales, and customer data. The MCP server connects to 325+ native Windsor.ai connectors (Facebook Ads, GA4, HubSpot, Salesforce, Shopify, TikTok Ads, and more), allowing natural language questions such as 'What campaigns had the best ROAS last month?' or 'Break down spend by channel over the past 90 days?' to be answered with structured, queryable results inside your LLM chat interface. It supports zero-code setup via Claude Desktop, or flexible configurations through a lightweight mcp-proxy for developer workflows and through Cursor or Gemini CLI options. It's compatible with open standard MCP specs, ensuring interoperability across Claude, Perplexity, Cursor, and other MCP-enabled tools. The beta status indicates ongoing improvements in performance, authentication, compatibility, and feature coverage.
Features
Natural language access to business data
A natural language interface that queries Windsor.ai datasets via MCP, enabling you to ask questions and receive real-time, structured results inside your LLM chat.
Out-of-the-box integration with 325+ sources
Sync data from Facebook Ads, GA4, HubSpot, Salesforce, Shopify, TikTok Ads, and more via native Windsor.ai connectors.
Zero-code setup
Windsor MCP works via Claude Desktop or with a lightweight dev proxy. No custom integrations required.
Open standard compatibility
Built on Anthropic’s open MCP spec; compatible with Claude, Perplexity, Cursor, and more.
Real-time analytics without SQL
Get instant breakdowns, summaries, and performance insights from your integrated data.
Flexible deployment options
Supports Claude Desktop, a developer proxy, Cursor, and Gemini CLI configurations for different workflows.
