Start free

Platforms MCP server

MCP server · 3 tools · 3 endpoints

Pinterest MCP server

Pin details, keyword search and the save count for any URL you publish, read by Claude or Cursor.

Get a free key Connect in a minute

100 credits on signup · No card · Sign in with OAuth or paste a key

scrapersocial-pinterest mcp.scrapersocial.com/pinterestconnected
you

Search Pinterest for "<niche keyword>" and describe what the top 20 pins have in common.

agent
calls search 2 credits / pin
{ "query": "<keywords>" }
server
returns
pins [{ … }] · one per pin
Shape only. Keys follow the tool's summary; a real call returns the full record. 1 call · 2 credits

Connect

One URL. Your client already knows what to do with it.

The first call opens a sign-in. New accounts get 100 credits, no card. Every client below shares one account and one balance.

Get a free key
server url https://mcp.scrapersocial.com/pinterest
claude.aiOAuth

Settings → Connectors → Add custom connector, then paste the server URL.

mcp.scrapersocial.com/pinterest

Web, desktop and mobile. Nothing else to paste.

Claude Codeone command

Run this in a terminal.

$ claude mcp add --transport http scrapersocial-pinterest https://mcp.scrapersocial.com/pinterest

Approve the sign-in prompt on first use.

Cursorone click

Installs the server and opens the MCP panel.

Add to Cursor
or paste the JSON into .cursor/mcp.json
{ "mcpServers": { "scrapersocial-pinterest": { "url": "https://mcp.scrapersocial.com/pinterest", "headers": { "Authorization": "Bearer sk_live_..." } } } }
Other clients · VS Code, Windsurf, Gemini CLI, anything that speaks MCP
VS Codeone click or JSON
Add to VS Codeor run MCP: Add Server, choose HTTP and use:
{ "name": "scrapersocial-pinterest", "type": "http", "url": "https://mcp.scrapersocial.com/pinterest" }
Windsurf~/.codeium/windsurf/mcp_config.json
{ "mcpServers": { "scrapersocial-pinterest": { "serverUrl": "https://mcp.scrapersocial.com/pinterest", "headers": { "Authorization": "Bearer sk_live_..." } } } }
Gemini CLI~/.gemini/settings.json
{ "mcpServers": { "scrapersocial-pinterest": { "httpUrl": "https://mcp.scrapersocial.com/pinterest", "headers": { "Authorization": "Bearer sk_live_..." } } } }
Any clientStreamable HTTP · OAuth 2.1 or Bearer
$ npx add-mcp https://mcp.scrapersocial.com/pinterest

One account and one balance across every client and the every-platform hub at mcp.scrapersocial.com.

What it does

What your agent can do with Pinterest

The most useful number on this server costs 1 credit: how many times a given URL has been saved to Pinterest. It works for any address, not just pages you own, which makes it a quiet distribution signal for competitor content as well as your own. That endpoint, /v1/pinterest/url-stats, sits behind call_endpoint, reached by its path, and it is the reason to connect https://mcp.scrapersocial.com/pinterest even if you never run a keyword search.

The keyword search is there too. search, the one wrapped tool, takes a query and returns pins, 2 credits per pin, paginated. The third path, /v1/pinterest/pin, takes a pin URL and returns that pin’s details for 2 credits. list_endpoints, which is free, shows all three to the agent so it can choose.

Pinterest sits closer to a visual search engine than to a feed, and the jobs people bring to it reflect that: what is trending visually in a niche, how a product is being pinned, and whether a page is getting shared. Each of those maps to one call. The agent gets the same envelope it sees from every other ScraperSocial platform, so a content report that mixes Pinterest saves, Instagram engagement and search rankings is one conversation rather than three integrations.

Four jobs it finishes on its own

01

Measure a page's Pinterest traction

Give the agent a list of your URLs and have it call /v1/pinterest/url-stats on each. Fifty pages is 50 credits, and the result is a ranked table of which content is actually being saved.

02

Benchmark against a competitor

The same endpoint takes any URL, so run it on a rival's top pages. The model can tell you which of their formats earns saves and which do nothing, which is a cheap way to decide what to make next.

03

Visual trend research

search a niche phrase and let the model describe what the top pins have in common: colours, formats, hooks. Twenty pins is 40 credits, and the descriptions are more useful than a scroll.

04

Read a pin someone shared

A user drops a pin link into the chat. /v1/pinterest/pin returns its details for 2 credits so the agent can answer questions about it without opening a browser.

Limits · read before you connect

What this does not do

Written by a person, not generated. If something here is wrong, tell us.

Public pins and public counts only; no account is signed in, so nothing creates pins, boards or saves, and there are no account analytics. Boards aren’t covered: there is no endpoint for a board or for an account’s list of boards, so pins, search and URL stats are the whole surface. search pages at 20 pins, or any limit up to 50, and meta’s next_cursor fetches the following page. url-stats and pin each return a single record. Save counts are cached for a while, so add fresh when you need today’s figure rather than last week’s. Billing floors at 1 credit per successful call, so a query with no pins still costs 1.

Tools

3 tools, same names as the every-platform hub

One does one Pinterest thing each. The last two reach all 3 endpoints by path, so nothing in the catalog is out of an agent's reach.

Full credit table →

Search a platform

search

Keyword search over one platform's public content.

2 credits / pin
Reaches the other 2 endpoints

List every Pinterest endpoint

list_endpoints

Browse every Pinterest endpoint, its input and its credit cost. Free, and calls nothing upstream.

free

Call any Pinterest endpoint by path

call_endpoint

Run any Pinterest endpoint by its path, so nothing Pinterest offers is out of reach of an agent.

endpoint's own cost

Pricing

100 free credits is 50 search results.

Then $5 a month for 1,000 credits, or $4 per 1,000 as a top-up. No card to start. Calls cost between 1 and 2 credits on Pinterest.

50 search resultssearch · 2 each
Get a free key 100 credits on signup · $5 for 1,000 · full credit table

Prompts

Things to ask once it is connected

Copy one, swap the placeholder, paste it into your client.

How many times has <url> been saved to Pinterest?

Check Pinterest save counts for these pages and rank them: <url 1>, <url 2>, <url 3>

Search Pinterest for "<niche keyword>" and describe what the top 20 pins have in common.

Read this pin and tell me what it links to and how it is described: <pin url>

Compare Pinterest saves for my page <url> against this competitor page <url>.

Questions

Before you connect

How much does a save count cost? #

1 credit per URL through /v1/pinterest/url-stats. A pin's details are 2 credits, and keyword search is 2 credits per pin returned. A new account's 100 credits are enough to audit a small site.

Can I check URLs I don't own? #

Yes. The count is public, so any address works, including a competitor's. That is what makes it a benchmark rather than just an analytics figure.

Why is there no board endpoint? #

Boards aren't served today. Pins, keyword search and URL save counts are the three paths that work, and list_endpoints reports only those.

Can the agent create pins or save things? #

No. Every call is read-only. Pinterest's own API is the place for writes.

Is this run by Pinterest? #

No. Pinterest has no involvement; ScraperSocial is an independent company with no affiliation to Pinterest, reading public pins and counts.