pinterest-mcp
Enables AI agents to manage Pinterest boards and pins, create and update pins, and track analytics via the Pinterest API v5.
README
pinterest-mcp
An MCP (Model Context Protocol) server for the Pinterest API v5.
Create pins, manage boards, and track analytics — all from an AI agent.
First open-source Pinterest MCP server.
Features
| Tool | Description |
|---|---|
create_pin |
Create a new Pin with image, title, description, and link |
update_pin |
Edit an existing pin’s metadata |
delete_pin |
Remove a pin |
get_pin_analytics |
Impressions, saves, link clicks, engagement rate |
list_boards |
List your boards |
create_board |
Create a new board |
get_board_pins |
List all pins on a board |
search_pins |
Search public pins by keyword |
get_account_analytics |
Account-level metrics: impressions, saves, engagements |
bulk_create_pins |
Create multiple pins in one call (rate-limited) |
get_trending |
Trending searches and interests in a niche |
Installation
pip install pinterest-mcp
Or run directly with uvx:
uvx pinterest-mcp
Authentication
Pinterest uses OAuth 2.0. You need a Pinterest Business account and a registered app.
- Create an app at developers.pinterest.com
- Add redirect URI:
http://localhost:8089/callback - Copy Client ID + Client Secret to
.env(see.env.template) - Run the auth flow to generate your access token:
pinterest-mcp-auth
This opens a browser, asks you to authorize, and saves your token to .pinterest_token.json.
MCP Client Setup
{
"mcpServers": {
"pinterest": {
"command": "uvx",
"args": ["pinterest-mcp"],
"env": {
"PINTEREST_CLIENT_ID": "your_client_id",
"PINTEREST_CLIENT_SECRET": "your_client_secret",
"PINTEREST_ACCESS_TOKEN": "your_access_token"
}
}
}
}
Rate Limits
Pinterest API v5 rate limits for organic posting:
- 10 pins per minute per account
- 250 pins per day per account
bulk_create_pins automatically respects the per-minute limit.
Development
git clone https://github.com/clugtu/pinterest-mcp
cd pinterest-mcp
pip install -e ".[dev]"
pre-commit install
pytest
This repo uses pre-commit with ruff for linting and formatting. Install pre-commit if you don't have it:
pip install pre-commit
Then run pre-commit install once to register the hooks — they'll run automatically on every git commit.
License
MIT — see LICENSE
Related
- cults3d-mcp — Cults3D marketplace MCP server
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.