Windsor.ai MCP Server — Connect AI Agents to Marketing Data

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

Overview

Windsor.ai MCP Server is a remote MCP server that exposes Windsor.ai's 350+ data connectors to any MCP-compatible AI client. Use it to pull live marketing performance data, query your data warehouse, build dashboards, calculate ROAS, and combine multi-channel data — all from natural-language prompts in your AI assistant.

Compatible AI Clients

Windsor.ai MCP works with any MCP-compatible client. Per-client setup guides live at windsor.ai/documentation/windsor-mcp/.

• Claude (Desktop, Web, Code) — listed in the Claude connector directory. One-click install · setup guide.
• ChatGPT — install as a ChatGPT app · setup guide.
• Microsoft Copilot — uses the Windsor.ai Power Platform connector. Setup guide.
• Perplexity — setup guide.
• Claude Code — install with claude plugin install windsor-ai. Source; ships slash commands and an analyst agent.
• Cursor — dedicated plugin or paste the standard MCP config below · setup guide.
• Manus — add https://mcp.windsor.ai/ as an MCP server. Setup guide.
• Google Gemini — standard MCP server config (url: https://mcp.windsor.ai/) · setup guide.
• Google Antigravity — add https://mcp.windsor.ai/ via Manage MCP Servers · setup guide.
• Grok (xAI) — add https://mcp.windsor.ai/ as a Custom Connector at grok.com/connectors.
• Lovable — add https://mcp.windsor.ai/ as a Custom MCP · setup guide.
• Base44 — add https://mcp.windsor.ai/ under Settings → MCP connections (OAuth).
• n8n — add an MCP Client Tool node pointing at https://mcp.windsor.ai/ · setup guide.
• Windsurf, Cline, GitHub Copilot — standard MCP server config (url: https://mcp.windsor.ai/) · generic setup guide.
• mcp-proxy and any application built on the MCP open standard.

Available Tools

• get_current_user — Return the authenticated user's profile (username, email, and current subscription plan).
• get_connectors — List Windsor.ai connectors, their connected accounts, the write actions each connector supports, and the read options each exposes. Pass include_not_yet_connected=True to also see connectors the user can set up.
• get_connector_connect_info — Describe how to grant access to a connector and return its direct connect URL.
• get_connector_authorization_url — Get a browser link to connect, add, authorize, replace, or reconnect a connector account.
• get_subscription_url — Get a clickable Markdown auto-login link to start or upgrade a paid plan.
• get_options — List available fields, date filter columns, and connector-specific options.
• get_fields — Get descriptions, types and tables for specific fields.
• get_data — Run a query with date ranges, accounts, options, and nested filters.
• list_actions — Discover the write actions a connector exposes and their JSON schemas. Meta Ads: create / pause / enable / update campaigns, ad sets, and ads, set budgets, boost posts, and set Click-to-Message welcome messages. Google Ads: create campaigns / ad groups / ads, pause / enable them, set budgets and bidding, manage keywords (add / update / remove), push negative keywords, and manage Customer Match audience lists. TikTok Ads, LinkedIn Ads, and Microsoft Ads: pause / enable and set budgets. Instagram: create image posts. Google Business Profile: posts, review replies, photos, hours, and open status. Klaviyo: create flows and set flow status. Amazon Seller Central: update listings.
• execute_action — Run a write action against a specific account. Reach for this whenever you would otherwise recommend a platform change; confirm intent with the user first.
• get_destinations — List destinations that can receive scheduled exports of connector data (BigQuery, Google Sheets, Snowflake, databases, storage) and any reusable OAuth credentials.
• get_destination_tasks — List the scheduled export tasks the user already created, each with its destination, connector, schedule, and status.
• get_destination_setup_info — Describe a destination's target fields, allowed schedules, and an auto-login link to its setup form.
• create_destination_task — Create a recurring export of a connector's data to a destination, reusing OAuth the user already granted.
• get_windsor_login_url — Return an auto-login link into the Windsor.ai dashboard, optionally deep-linked to a specific page.
• contact_windsor — Send feedback, a support request, or a feature request to Windsor.ai and return a reference ID.

Supported Data Sources

350+ marketing, advertising, analytics, e-commerce, CRM, and database sources. The full list is available at /datasources or by calling get_connectors(include_not_yet_connected=True). Highlights:

Advertising

Analytics & Search

Social Organic

CRM & Marketing Automation

E-commerce & Payments

Databases, Warehouses & Files

Use Case Examples

• "Pull last month's Meta Ads spend by campaign and compare to the previous period."
• "Show me Google Ads ROAS by campaign for the last 30 days."
• "Combine Meta, Google and TikTok Ads spend into a unified weekly report."
• "Pull Shopify orders and Klaviyo email engagement so I can attribute revenue."
• "Query my BigQuery warehouse for last quarter's pipeline data."
• "Build a Looker Studio-ready dataset combining GA4 sessions and ad spend."

Setup Instructions

Prerequisites

• An MCP-compatible client (Claude Desktop, Cursor, ChatGPT with developer mode, Manus, Windsurf, etc.).
• A Windsor.ai account — sign up at onboard.windsor.ai.

Server Endpoints

Authentication

OAuth 2.0 (recommended)

The MCP server implements the full MCP OAuth flow. Clients that support MCP OAuth — including Claude, ChatGPT, Cursor and Manus — discover the endpoints automatically and walk the user through a one-time login at Windsor.ai. Dynamic Client Registration is supported.

API key

Pass a Windsor.ai API key as a Bearer token:

Authorization: Bearer <your_windsor_api_key>

Get an API key from your Windsor.ai account at onboard.windsor.ai.

Tool Reference

get_connectors

List Windsor.ai connectors and their connected accounts. By default returns only connectors with at least one connected account. Pass include_not_yet_connected=True to also include connectors the user can set up. Each connector also carries an actions list of write-action ids (skip with include_actions=False) and an options list of read-option ids that change what a get_data read returns (skip with include_options=False).

get_connector_connect_info

Describe how to grant access to a connector, including the auth type, direct connect URL, and any manual credential fields. Use it for connect, grant access, authorize, add, replace, or reconnect requests, including adding another account to an already-connected connector. Never ask users to paste secrets into chat; send them to the connect URL form.

get_connector_authorization_url

Returns a URL the user can open in their browser to set up a connector. Always call get_connectors(include_not_yet_connected=True) first to get the correct connector ID. Works for both OAuth-based and manual-credential connectors. Use it for connect, grant access, authorize, add, replace, or reconnect requests, including adding another account to an already-connected connector. Do not substitute dashboard navigation steps for the returned link.

get_subscription_url

Returns a clickable Markdown auto-login link to the Windsor.ai pricing page, or to a specific plan's upgrade page. Optional target_plan values are BASIC, STANDARD, PLUS, PROFESSIONAL, and ENTERPRISE.

get_options

For a connector and a set of accounts, return the available fields, the columns that can be used as date filters per table, and connector-specific options (e.g. attribution windows for Meta Ads).

get_fields

Get descriptions, types and tables for specific fields. Field types NUMERIC and PERCENT are metrics (aggregated); other types are dimensions.

get_data

Run a query against a connector. Supports date ranges (date_from/date_to or date_preset), account filtering, connector-specific options, and nested filter conditions.

Filter operators: eq, neq, gt, gte, lt, lte, contains, ncontains, null, notnull, in. Conditions can be nested with "and" and "or". A condition is a [field, operator, value] list or a {"field": ..., "operation": ..., "value": ...} dict.

Warehouse connectors (mysql, postgresql, redshift, mongodb, snowflake, big_query) require date_filters when filtering by date.

list_actions

Discover the write actions a connector exposes and their JSON schemas. Meta Ads (facebook): create / pause / enable / update campaigns, ad sets, and ads, set campaign and ad set budgets, boost posts, and set Click-to-Message welcome messages. Google Ads (google_ads): create campaigns, ad groups, and responsive search ads, pause / enable them, set campaign budget, bidding strategy, target CPA, max CPC, and CPC bid ceiling, add / update / remove keywords, push negative keywords, and manage Customer Match audience lists (create, upload members, rename, delete, and attach / detach them to ad groups). TikTok Ads (tiktok), LinkedIn Ads (linkedin), and Microsoft Ads (bing): pause / enable and set budgets. Instagram (instagram): create image posts. Google Business Profile (google_my_business): create / update local posts, reply to reviews, upload photos, update location info, set regular / special hours, and set open status. Klaviyo (klaviyo): create flows and set flow status. Amazon Seller Central (amazon_sp): update product listings. Other connectors return an empty list.

execute_action

Execute a write action returned by list_actions against a specific connector account, with params matching the action's JSON schema. Write actions modify external platform state — confirm intent with the user before invoking.

get_destinations

List destinations that can receive a scheduled export of connector data (BigQuery, Google Sheets, Snowflake, databases, cloud storage), with any reusable OAuth credentials the user already connected.

get_destination_tasks

List the scheduled export tasks the user already created, each with its destination, source connector, schedule, status, and a link to manage it in the dashboard.

get_destination_setup_info

Describe a destination's target fields, allowed schedules, reusable credentials, and an auto-login link to its dashboard setup form. Sensitive fields are entered by the user in that form, never in chat.

create_destination_task

Create a recurring export of a connector's data to a destination, reusing OAuth the user already granted. Confirm the source, target, and schedule with the user first.

get_current_user

Return the authenticated user's profile (username, email, and current subscription plan). Useful as a sanity check that the auth token is working.

get_windsor_login_url

Return an auto-login URL into the Windsor.ai dashboard that signs the user in without a password, optionally deep-linked to a specific page.

contact_windsor

Send feedback, a support request, or a feature request to Windsor.ai and return a reference ID the user can share with support.

Troubleshooting

Authentication failures (401)

• Confirm the Authorization header is Bearer <token> with no quotes.
• For API keys, get one from onboard.windsor.ai.
• For OAuth, clear cached tokens and re-authorize.

"Requested data exceeds size limit"

Narrow the date range, reduce fields, filter by accounts, or add filter conditions to get_data.

"Connector requires specifying date filters"

Warehouse connectors need an explicit date_filters argument when filtering by date.