mcpField
V
Variafy

Variafy

Remote
variafy.comBusiness & Marketing0Updated 2w ago

About Variafy

Variafy connects AI clients to Meta ad accounts for advertisers and agencies to review performance, find wasted spend, and prepare campaigns. Changes are previewed and applied only after confirmation.

Key features

  1. 01Review ad results and payments
  2. 02Find wasted ad spend
  3. 03Explain rising cost per result
  4. 04Build paused campaigns
  5. 05Preview changes before applying
  6. 06Provide seven ad workflows

Use cases

  1. 01Check account performance and spend
  2. 02Investigate rising cost per result
  3. 03Prepare and launch campaigns
  4. 04Create client ad reports

MCP support

Variafy provides a remote MCP server at https://www.variafy.com/mcp, connecting Meta ad accounts and exposing ad capabilities to AI clients. Changes are previewed and applied only after confirmation.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://www.variafy.com/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

Variafy plugin

Variafy connects Claude, ChatGPT, Codex, Cursor and Gemini CLI to your Meta (Facebook and Instagram) ad accounts. Read results and payments, find wasted spend, explain why cost per result rose, build paused campaigns and report to clients. Every change comes back as a preview first and is applied only when you confirm it.

The plugin brings two things:

  • The Variafy connector (https://www.variafy.com/mcp). You sign in with your Variafy account the first time it is used.
  • The variafy-ads skill: how to work with Variafy, and seven workflows — morning check, wasted spend, why cost per result rose, launching a campaign, refreshing creatives, a client report and a tracking check.

You need a Variafy account with a Meta ad account connected: variafy.com.

Claude Code

/plugin marketplace add DenysVolynskyi/variafy-plugins
/plugin install variafy@variafy

Then run /mcp, choose variafy and sign in.

Codex

codex plugin marketplace add DenysVolynskyi/variafy-plugins

Then type /plugins, open Variafy and choose Install plugin. Codex asks you to sign in to Variafy.

Cursor

Issue a token in the Variafy console under Assistant connection and add it to ~/.cursor/mcp.json:

{ "mcpServers": { "variafy": { "url": "https://www.variafy.com/mcp", "headers": { "Authorization": "Bearer sk_live_YOUR_TOKEN" } } } }

Gemini CLI

gemini extensions install https://github.com/DenysVolynskyi/variafy-plugins

Then run /mcp auth variafy and sign in. The extension adds the connector and the variafy-ads skill with the same seven workflows.

Other assistants

Claude, ChatGPT, Gemini, Copilot, Perplexity and others connect to the same address. Steps for each: variafy.com/help.

Check that it works

Ask the assistant: "Call start_here and show my ad accounts." It answers with the connected ad accounts and your plan.

Links

The connector is listed in the official MCP Registry as com.variafy/variafy.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.