Pinterest MCP Server
by terryso
A Model Context Protocol (MCP) server for Pinterest image search and information retrieval. It allows users to search for images and retrieve detailed information about them directly from Cursor IDE.
Last updated: N/A
Pinterest MCP Server
A Model Context Protocol (MCP) server for Pinterest image search and information retrieval.
Features
- Search for images on Pinterest by keywords
- Retrieve detailed information about Pinterest images
- Seamless integration with Cursor IDE through MCP
- Support for headless browser mode
- Limit control for search results
Prerequisites
- Node.js (v18 or higher)
- Cursor IDE for MCP integration
Installation
Installing via Smithery
To install mcp-pinterest for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install mcp-pinterest --client claude
Manual
-
Clone this repository:
git clone https://github.com/terryso/mcp-pinterest.git pinterest-mcp-server cd pinterest-mcp-server
-
Install dependencies:
npm install
Usage
Command Mode (Recommended)
Build the server:
npm run build
You can now use this server as an MCP server in Cursor.
Configuring as MCP Server in Cursor
-
Open Cursor IDE
-
Go to Settings (⚙️) > Extensions > MCP
-
Click "Add Server"
-
Enter the following details:
- Name: Pinterest MCP
- Type: Command
- Command:
node
- Args:
["/path/to/mcp-pinterest/dist/pinterest-mcp-server.js"]
或者直接编辑Cursor的MCP配置文件(通常位于
~/.cursor/mcp.json
),添加以下内容:"pinterest": { "command": "node", "args": ["/path/to/mcp-pinterest/dist/pinterest-mcp-server.js"] }
-
Click "Save"
Available MCP Functions
The server exposes the following MCP functions:
-
pinterest_search
: Search for images on Pinterest by keyword- Parameters:
keyword
: Search term (required)limit
: Number of images to return (default: 10)headless
: Whether to use headless browser mode (default: true)
- Parameters:
-
pinterest_get_image_info
: Get detailed information about a Pinterest image- Parameters:
image_url
: URL of the Pinterest image (required)
- Parameters:
Example Usage in Cursor
Once configured, you can use the Pinterest MCP functions directly in Cursor's AI chat:
Search for robot images on Pinterest
The AI will use the MCP server to search Pinterest and display the results.
Example Screenshot

Pinterest Search Example
Screenshot showing a search for 20 images of 三上悠亚 with all images successfully downloaded.
Development
Project Structure
pinterest-mcp-server.ts
: Main server filedist/pinterest-mcp-server.js
: Built JavaScript file for productionpackage.json
: Project configuration and dependencies
Adding New Features
To add new MCP functions:
- Modify
pinterest-mcp-server.ts
- Register new functions using the MCP SDK
- Implement the function logic
- Rebuild with
npm run build
Troubleshooting
- If the server fails to start, check if the port is already in use
- Ensure all dependencies are correctly installed with
npm install
- Make sure TypeScript is properly configured with a
tsconfig.json
file - If you encounter build errors, try running
npm install -D typescript @types/node
- Verify network connectivity for Pinterest access
License
This project is licensed under the MIT License - see the LICENSE file for details.