A Model Context Protocol (MCP) server for integrating the Pinterest API with AI agents and LLMs.

Installation

Run this command in your terminal to add the MCP server to Claude Code.

Run in terminal:

Command

claude mcp add --transport stdio collactivelabs-pinterest-mcp-server node server.js \
  --env PORT="3052" \
  --env PINTEREST_APP_ID="your_pinterest_app_id" \
  --env PINTEREST_APP_SECRET="your_pinterest_app_secret"

How to use

This MCP server enables AI agents to interact with the Pinterest API through a standardized MCP interface. It exposes tools to retrieve user information, manage boards, and handle pins: pinterest.user.get_info, pinterest.boards.list, pinterest.boards.create, pinterest.boards.get, pinterest.pins.list, pinterest.pins.create, and pinterest.pins.get. Agents connect using a compatible MCP client over Socket.IO and can perform actions such as listing boards, creating boards, listing pins on a board, and creating pins. The server authenticates via Pinterest OAuth, and, on first run, will prompt you to complete authentication in a browser. After successful authentication, the server is ready to accept requests from AI agents.

To connect an AI agent, point your MCP client to the server URL (for example, http://localhost:3052). You can then issue commands mapped to the tools above, such as asking to list boards, create a new board, or pin an image to a board. The example in the README shows how tools are invoked via natural language prompts or direct MCP client calls depending on your integration. When using Claude or other MCP clients, select the Pinterest MCP server and use the available tool names to perform actions like:

pinterest.boards.list
pinterest.boards.create
pinterest.pins.list
pinterest.pins.create
pinterest.pins.get

How to install

Prerequisites:

Node.js v14 or newer
A Pinterest Developer account with an app and credentials (APP ID and APP SECRET)

Setup steps:

Clone the repository git clone https://github.com/yourusername/pinterest-mcp-server.git cd pinterest-mcp-server
Install dependencies npm install
Create and configure environment variables cp .env.template .env

Edit .env and add your credentials

PINTEREST_APP_ID=your_pinterest_app_id PINTEREST_APP_SECRET=your_pinterest_app_secret

Optional: set the port the server will listen on (default 3052)

PORT=3052
Run the server npm start
Open the authentication flow if prompted in your browser and complete OAuth with Pinterest. After authentication, the server will be ready to accept MCP connections.

Additional notes

Tips and common issues:

Ensure your Pinterest app has the proper redirect URI configured (e.g., http://localhost:3052/).
If the OAuth flow does not automatically open, manually navigate to http://localhost:3052 to start authentication.
The MCP tools are named with a pinterest.* prefix to reflect their scope; ensure your MCP client uses these exact tool names.
If you change the listening port, update the PORT variable and your client connection URL accordingly.
Environment variables in production should be secured; consider using a secrets manager and not committing .env files.
Check server logs for any API rate limits or authentication errors from Pinterest and adjust credentials as needed.

Related MCP Servers

zen

1.1k

Selfhosted notes app. Single golang binary, notes stored as markdown within SQLite, full-text search, very low resource usage

MCP -Deepseek_R1

A Model Context Protocol (MCP) server implementation connecting Claude Desktop with DeepSeek's language models (R1/V3)

mcp-fhir

A Model Context Protocol implementation for FHIR

mcp

Inkdrop Model Context Protocol Server

mcp-appium-gestures

This is a Model Context Protocol (MCP) server providing resources and tools for Appium mobile gestures using Actions API..

dubco -npm

The (Unofficial) dubco-mcp-server enables AI assistants to manage Dub.co short links via the Model Context Protocol. It provides three MCP tools: create_link for generating new short URLs, update_link for modifying existing links, and delete_link for removing short links.

pinterest