mcp-pinterest
Allows searching for images on Pinterest by keywords and retrieving detailed information about Pinterest images
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-pinterestsearch for minimalist home office ideas"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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
Search and download images from Pinterest
Related MCP server: FGCLIP-MCP
Prerequisites
Node.js (v18 or higher)
Cursor IDE for MCP integration
Installation
Using NPX (Recommended)
The easiest way to use Pinterest MCP Server is via npx:
npx pinterest-mcp-serverYou can configure the server with command-line options:
# Specify download directory
npx pinterest-mcp-server --downloadDir /path/to/downloads
# Specify filename template
npx pinterest-mcp-server --filenameTemplate "pinterest_{id}"
# Specify both options
npx pinterest-mcp-server --downloadDir ./images --filenameTemplate "pinterest_{id}"Global Installation
To install the package globally and use it directly from the command line:
npm install -g pinterest-mcp-serverAfter installation, you can run the server with:
pinterest-mcp-serverWith the same command line options as the NPX version:
pinterest-mcp-server --downloadDir /path/to/downloads --filenameTemplate "pinterest_{id}"Installing via Smithery
To install mcp-pinterest for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install mcp-pinterest --client claudeManual Installation
Clone this repository:
git clone https://github.com/terryso/mcp-pinterest.git pinterest-mcp-server cd pinterest-mcp-serverInstall dependencies:
npm installBuild the server:
npm run buildRun the server:
npm start
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:
nodeArgs:
["/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"
Alternative: Using NPX for Cursor Configuration
You can also configure Cursor to use the npx version of the server:
Open Cursor IDE
Go to Settings (⚙️) > Extensions > MCP
Click "Add Server"
Enter the following details:
Name: Pinterest MCP
Type: Command
Command:
npxArgs:
["pinterest-mcp-server"]
Click "Save"
Complete Configuration Example with Environment Variables
For the most flexibility, you can configure the server with environment variables in your Cursor MCP configuration:
"pinterest": {
"command": "npx",
"env": {
"MCP_PINTEREST_DOWNLOAD_DIR": "/Users/xxx/Desktop/Images",
"MCP_PINTEREST_FILENAME_TEMPLATE": "pin_{imageId}_{timestamp}.{fileExtension}",
"MCP_PINTEREST_PROXY_SERVER": "http://127.0.0.1:7890"
},
"args": ["pinterest-mcp-server"]
}This configuration:
Uses npx to run the server
Sets a custom download directory on your desktop
Uses a custom filename template with both image ID and timestamp
Configures a proxy server for users in regions where Pinterest might be blocked
Add this to your ~/.cursor/mcp.json file or set up through the Cursor IDE interface.
Available MCP Functions
The server exposes the following MCP functions:
pinterest_search: Search for images on Pinterest by keywordParameters:
keyword: Search term (required)limit: Number of images to return (default: 10)headless: Whether to use headless browser mode (default: true)
pinterest_get_image_info: Get detailed information about a Pinterest imageParameters:
image_url: URL of the Pinterest image (required)
pinterest_search_and_download: Search and download images from PinterestParameters:
keyword: Search term (required)limit: Number of images to return (default: 10)headless: Whether to use headless browser mode (default: true)
Example Usage in Cursor
Once configured, you can use the Pinterest MCP functions directly in Cursor's AI chat:
Search for robot images on PinterestThe AI will use the MCP server to search Pinterest and display the results.
Example Screenshot

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.tsRegister 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 installMake sure TypeScript is properly configured with a
tsconfig.jsonfileIf you encounter build errors, try running
npm install -D typescript @types/nodeVerify network connectivity for Pinterest access
License
This project is licensed under the MIT License - see the LICENSE file for details.
Configuration Options
Command Line Options (NPX Mode)
When using the server via npx, you can configure it using the following command line options:
--downloadDir: Specifies the root directory for downloading imagesnpx pinterest-mcp-server --downloadDir /path/to/downloads--filenameTemplate: Specifies the filename template for downloaded imagesnpx pinterest-mcp-server --filenameTemplate "pin_{imageId}_{timestamp}"--port: Specifies the port for the server to listen on (default: 3000)npx pinterest-mcp-server --port 8080--proxyServer: Specifies the proxy server to use for connecting to Pinterestnpx pinterest-mcp-server --proxyServer "http://127.0.0.1:7890"
You can combine multiple options:
npx pinterest-mcp-server --downloadDir ./images --filenameTemplate "pinterest_{id}" --port 8080 --proxyServer "http://127.0.0.1:7890"Environment Variables
The server also supports the following environment variables for configuration:
MCP_PINTEREST_DOWNLOAD_DIR: Specifies the root directory for downloading images. If not set, the default is the../downloadsdirectory relative to the server script.MCP_PINTEREST_FILENAME_TEMPLATE: Specifies the filename template for downloaded images. If not set, the default ispinterest_{imageId}.{fileExtension}.MCP_PINTEREST_PROXY_SERVER: Specifies the proxy server to use for connecting to Pinterest. Format should beprotocol://host:port, for examplehttp://127.0.0.1:7890orsocks5://127.0.0.1:1080.
These environment variables can be set in several ways:
Directly in your terminal (as shown in the examples below)
In your Cursor MCP configuration through the
envfield (see Complete Configuration Example)In a
.envfile in the project root directoryThrough command line options with npx (as shown in the Command Line Options section)
Usage
Setting Download Directory
Using npx with command line options:
npx pinterest-mcp-server --downloadDir /path/to/your/download/directorySet the download directory using an environment variable:
# Linux/macOS
export MCP_PINTEREST_DOWNLOAD_DIR=/path/to/your/download/directory
npx pinterest-mcp-server
# Windows (CMD)
set MCP_PINTEREST_DOWNLOAD_DIR=C:\path\to\your\download\directory
npx pinterest-mcp-server
# Windows (PowerShell)
$env:MCP_PINTEREST_DOWNLOAD_DIR="C:\path\to\your\download\directory"
npx pinterest-mcp-serverIf the environment variable is not set, the server will use the default download directory (relative to the server script's
../downloads).
Setting Filename Template
Using npx with command line options:
npx pinterest-mcp-server --filenameTemplate "pin_{imageId}_{timestamp}.{fileExtension}"Using an environment variable:
# Linux/macOS
export MCP_PINTEREST_FILENAME_TEMPLATE="pin_{imageId}_{timestamp}.{fileExtension}"
npx pinterest-mcp-server
# Windows (CMD)
set MCP_PINTEREST_FILENAME_TEMPLATE="pin_{imageId}_{timestamp}.{fileExtension}"
npx pinterest-mcp-server
# Windows (PowerShell)
$env:MCP_PINTEREST_FILENAME_TEMPLATE="pin_{imageId}_{timestamp}.{fileExtension}"
npx pinterest-mcp-serverThe template supports the following variables:
{imageId}: The unique ID of the Pinterest image{fileExtension}: The file extension (e.g., jpg, png){timestamp}: Current UTC timestamp in YYYYMMDDHHMMSS format{index}: The index number when downloading multiple images (starts from 1)
Example templates:
pinterest_{imageId}.{fileExtension}(default)pin_{timestamp}_{imageId}.{fileExtension}pinterest_image_{index}_{imageId}.{fileExtension}{timestamp}_pinterest.{fileExtension}
If the template is invalid (e.g., contains unsupported variables or has mismatched brackets), the server will log a warning and use the default template.
Setting Proxy Server
If you need to use a proxy to access Pinterest (especially in regions where Pinterest might be restricted), you can set the proxy configuration:
Using npx with command line options:
npx pinterest-mcp-server --proxyServer "http://127.0.0.1:7890"Using an environment variable:
# Linux/macOS
export MCP_PINTEREST_PROXY_SERVER="http://127.0.0.1:7890"
npx pinterest-mcp-server
# Windows (CMD)
set MCP_PINTEREST_PROXY_SERVER=http://127.0.0.1:7890
npx pinterest-mcp-server
# Windows (PowerShell)
$env:MCP_PINTEREST_PROXY_SERVER="http://127.0.0.1:7890"
npx pinterest-mcp-serverSupported proxy protocols:
HTTP:
http://host:portHTTPS:
https://host:portSOCKS4:
socks4://host:portSOCKS5:
socks5://host:port
The proxy configuration affects both the browser used for searching and the image downloading process.
Notes
The server will verify the existence and writability of the download directory when starting. If the directory does not exist, it will attempt to create it; if it cannot be created or written to, the server will exit.
Clients should not specify download paths or filename templates through parameters when calling download-related tools, as all downloads will use the server's environment variable configuration or defaults.
The server automatically sanitizes filenames by replacing illegal characters (such as
/,\,:,*,?,",<,>,|) with underscores.
Interface Description
The server provides the following MCP tools:
pinterest_search: Search for Pinterest images by keywordpinterest_get_image_info: Get detailed information about a Pinterest imagepinterest_search_and_download: Search and download Pinterest images
For detailed interface parameter references, please refer to the MCP tool definitions.
⭐ Star History
Available Tools
3 toolspinterest_get_image_infoC
Get Pinterest image information
| Name | Required | Description | Default |
|---|---|---|---|
| image_url | Yes | Image URL |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, and the description does not disclose any behavioral traits such as read-only nature, authentication requirements, or rate limits. It merely restates the name.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no unnecessary words. It is appropriately concise, though it could include more information without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple with one parameter and no output schema, but the description does not mention what information is returned. Without output schema, the agent has no indication of the response format or content, making it incomplete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides a description for the single parameter 'image_url' as 'Image URL'. The tool description does not add any additional meaning or context beyond the schema. With 100% schema coverage, baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb 'Get' and resource 'Pinterest image information', distinguishing it from sibling tools like search and search_and_download. However, it does not specify what information is retrieved, which could be improved.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. For instance, it could mention that this is used after searching to fetch details for a specific image.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
pinterest_searchB
Search for images on Pinterest by keyword
| Name | Required | Description | Default |
|---|---|---|---|
| keyword | Yes | Search keyword | |
| limit | No | Number of images to return (default: 10) | |
| headless | No | Whether to use headless browser mode (default: true) |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full responsibility for behavioral disclosure. However, it only states the basic action without revealing key traits such as browser automation (implied by the headless parameter), result format, pagination, or any potential side effects. This minimal transparency is insufficient for agents to understand the tool's operational behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, focused sentence that efficiently communicates the core purpose without any extraneous words. It is appropriately sized and front-loaded, making it quick for an agent to parse.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of output schema and annotations, the description is insufficiently complete for a search tool. It does not specify return values (e.g., image URLs, metadata), result sorting, error handling, or rate limits. The description omits critical operational context that an agent would need to use the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
All three parameters (keyword, limit, headless) are fully described in the input schema with 100% coverage. The description adds no additional meaning beyond the schema; for example, 'by keyword' merely repeats the required parameter. Per guidelines, with high schema coverage, baseline score is 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Search for images on Pinterest by keyword' clearly states the action (search), resource (images on Pinterest), and method (by keyword). It effectively distinguishes this tool from its siblings: 'pinterest_get_image_info' retrieves details of specific images, while 'pinterest_search_and_download' implies additional download functionality, making this tool's purpose unique.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus its siblings or alternatives. It lacks information about prerequisites, limitations, or appropriate contexts, leaving the agent to infer usage from the tool name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
pinterest_search_and_downloadB
Search for images on Pinterest by keyword and download them
| Name | Required | Description | Default |
|---|---|---|---|
| keyword | Yes | Search keyword | |
| limit | No | Number of images to return and download (default: 10) | |
| headless | No | Whether to use headless browser mode (default: true) |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavior. It only states the action, not side effects (e.g., file saving location, format, or any destructive operations). Minimal behavioral transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, efficient sentence with no wasted words. Could be slightly more structured but overall well-sized.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool that downloads images, missing details on output format, file saving behavior, and how it differs from sibling tools. Incomplete for an agent to reliably invoke.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, and the description adds no extra meaning beyond what the schema already provides. Baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'search and download' and resource 'images on Pinterest by keyword'. It distinguishes from siblings by combining both actions, though not explicitly differentiating from pinterest_search.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool vs siblings. The context is implied by the name and description, but lacks when-not-to-use or alternative mentions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
TDQS
Each tool has a distinct purpose: retrieving metadata, searching, and searching with download. The names and descriptions make it easy to distinguish between them.
All tools use the 'pinterest_' prefix and snake_case, but 'pinterest_search_and_download' combines two verbs while the others use a single verb, introducing slight inconsistency.
Three tools is a minimal but reasonable set for an image search and download service. It covers core functionality without being too sparse or excessive.
The set covers basic search and metadata retrieval, but lacks common Pinterest operations like board management, pinning, or user actions, leaving notable gaps for broader use.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Personal knowledge base MCP server with semantic search, auto-categorization, metadata extraction
MCP Server for an Agent Task Marketplace
MCP server for Drosophila neuroscience data from VirtualFlyBrain
Related MCP Servers
- AlicenseDqualityDmaintenanceA Model Context Protocol server that enables searching for similar images by text description, integrating Inspire's backend image search capabilities with LLM interfaces like Claude Desktop.13GPL 3.0
- AlicenseNot gradedqualityDmaintenanceMCP server for FG-CLIP embedding services enabling multi-modal similarity computation for text and images.4Apache 2.0
- AlicenseNot gradedqualityAmaintenanceAn MCP server for capturing, searching, and synthesizing knowledge objects with formal ontology, reasoning, and hybrid retrieval.20MIT
- FlicenseAqualityDmaintenanceMCP server that gives AI agents visual intelligence — search Pinterest, analyze images with LLM vision, build a semantic reference library, and retrieve by style or mood.61
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/terryso/mcp-pinterest'
If you have feedback or need assistance with the MCP directory API, please join our Discord server