dadof3bytes/pinterest-ads-mcp

Developer tools

このページは AI により自動翻訳されています。技術的な詳細は原文をご確認ください。原文を見る

0 stars 0 forks 品質 83 トレンド 14MIT

Repository Install

MCP server for businesses to manager their Pinterest Ads accounts.

概要

Connect your AI assistant (Cursor, Claude Desktop, etc.) to so it can read performance data, run account audits, and make changes (preview first, then confirm). You do not need to write code. You will copy settings, run a few terminal commands, click through Pinterest login once, and paste a small JSON config into your AI tool. a small web app plus an (Model Context Protocol) bridge. MCP is how compatible AI apps call structured “tools” instead of guessing from screenshots. a multi-brand agency dashboard, billing manager, or delete-anything admin panel. One deployment = one ad account. 1. Clone or download this repository to a folder you will keep (e.g. ~/pinterest-ads-mcp). 2. Open Terminal and go to that folder: 1. Copy the template: 2. Open .env.local in a text editor and fill in values (see below). Generate strong random secrets (run in Terminal, paste output into .env.local): Use values for TOKEN_ENCRYPTION_KEY, MCP_AUTH_TOKEN, and OAUTH_STATE_SECRET.

README

以下は原文 README の抜粋です。原文を見る。

Pinterest Ads MCP — setup guide

Connect your AI assistant (Cursor, Claude Desktop, etc.) to one Pinterest ad account so it can read performance data, run account audits, and make guarded changes (preview first, then confirm).

You do not need to write code. You will copy settings, run a few terminal commands, click through Pinterest login once, and paste a small JSON config into your AI tool.

What this is: a small web app plus an MCP (Model Context Protocol) bridge. MCP is how compatible AI apps call structured “tools” instead of guessing from screenshots.

What this is not: a multi-brand agency dashboard, billing manager, or delete-anything admin panel. One deployment = one ad account.

Before you start — checklist

Gather these before installing:

Requirement	Why you need it
Pinterest Business account	Ads API access is tied to business identity.
Ad account you will manage	This server is locked to a single `PINTEREST_AD_ACCOUNT_ID`.
Ad account role: Admin or Campaign Manager (Analyst is read-only)	Write tools need create/update permission; Analyst → 403 on applies.
Valid ads billing on the account (for live ads)	Pinterest may block creation or delivery without billing.
Pinterest developer app	OAuth client ID and secret for login.
Node.js 20+ and npm	Runs the server locally (nodejs.org).
Terminal access on your Mac/PC	For `npm install` and `npm run dev`.

Optional later:

Requirement	Why
Vercel (or similar) account	Host the app on a URL instead of only localhost.
Strong secrets	Protect OAuth and MCP endpoints in production.

Part 1 — Local setup (recommended first)

Step 1 — Get the project on your machine

Clone or download this repository to a folder you will keep (e.g. ~/pinterest-ads-mcp).
Open Terminal and go to that folder:
```
cd /path/to/pinterest-ads-mcp
```

Step 2 — Install dependencies

npm install

Step 3 — Create your environment file

Copy the template:
```
cp .env.example .env.local
```
Open .env.local in a text editor and fill in values (see Environment variables below).

Generate strong random secrets (run in Terminal, paste output into .env.local):

# 32+ characters — used to encrypt the Pinterest refresh token on disk
openssl rand -base64 32

# 16+ characters — protects the MCP HTTP endpoint
openssl rand -base64 24

# 16+ characters — signs OAuth “state” during login (CSRF protection)
openssl rand -base64 24

Use different values for TOKEN_ENCRYPTION_KEY, MCP_AUTH_TOKEN, and OAUTH_STATE_SECRET.

Step 4 — Create a Pinterest developer app

Go to Pinterest Developers and sign in with the same business identity that owns the ad account.
Create an app (or use an existing one).

GitHub で README 全文を見る

インストール

This server does not publish a one-line install command.

Open the repository installation guide MCP 初心者？mcpskill.org のガイドから始めましょう →

設定

{
  "mcpServers": {
    "pinterest-ads": {
      "url": "http://localhost:3000/api/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_MCP_AUTH_TOKEN"
      }
    }
  }
}