Start free

Platforms MCP server

MCP server · 2 tools · 1 endpoint

Linktree MCP server

Resolve any public Linktree into its links and profile details, one credit a page, through your MCP client.

Get a free key Connect in a minute

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

scrapersocial-linktree mcp.scrapersocial.com/linktreeconnected

you

Resolve the Linktree for <handle> and list the links

agent

calls list_endpoints free

server

endpoints [{ path, input, credits }] · /v1/linktree/page is 1 credit

agent

calls call_endpoint 1 credit · the endpoint's own cost

{ "path": "/v1/linktree/page", "handle": "<handle>" }

server

returns

page object · the full page record

agent

Lists the links, grouped by what they point at.

Shape only. Keys follow the tool's summary; a real call returns the full record. 2 calls · 1 credit

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/linktree

claude.aiOAuth

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

mcp.scrapersocial.com/linktree

Web, desktop and mobile. Nothing else to paste.

Claude Codeone command

Run this in a terminal.

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

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-linktree": {
      "url": "https://mcp.scrapersocial.com/linktree",
      "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-linktree",
  "type": "http",
  "url": "https://mcp.scrapersocial.com/linktree"
}

Windsurf~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "scrapersocial-linktree": {
      "serverUrl": "https://mcp.scrapersocial.com/linktree",
      "headers": {
        "Authorization": "Bearer sk_live_..."
      }
    }
  }
}

Gemini CLI~/.gemini/settings.json

{
  "mcpServers": {
    "scrapersocial-linktree": {
      "httpUrl": "https://mcp.scrapersocial.com/linktree",
      "headers": {
        "Authorization": "Bearer sk_live_..."
      }
    }
  }
}

Any clientStreamable HTTP · OAuth 2.1 or Bearer

$ npx add-mcp https://mcp.scrapersocial.com/linktree

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 Linktree

When you’re building a profile of a creator, the first thing to open is their Linktree. It usually lists every platform they’re active on, their store, and their business contact, which makes it the cheapest way to find out where to look next. ScraperSocial’s Linktree spoke makes that first step a single tool call.

One endpoint, reached by path. Call list_endpoints and it reports /v1/linktree/page, its input (a handle) and its cost (1 credit). Call call_endpoint with that path and the handle, and the response holds the profile details and every link on the page. There’s no wrapped capability tool because there’s nothing to wrap: the whole platform is one read.

Linktree is a link page, not a social network. ScraperSocial covers it as public web data, fetching what any visitor sees and returning it structured. No account is used.

At 1 credit, the 100 credits a new account starts with resolve a hundred pages. Pair that with the social spokes and your agent can go from a Linktree handle to a cross-platform picture of a creator in a few prompts. The server address is https://mcp.scrapersocial.com/linktree.

Four jobs it finishes on its own

Mapping a creator's presence

Resolve the Linktree, then let the agent fan out to the social spokes for each platform it finds. One prompt produces follower counts and recent posts across every network the creator actually uses.

Sponsor and affiliate tracking

Links on a Linktree change when deals start and end. Resolve a set of pages weekly, diff the results, and the agent reports new brand links and dropped ones.

Lead enrichment

Given a list of handles from a campaign or a spreadsheet, resolve each page and extract the website, store and contact links. At a credit a page it's practical for a long list.

Verifying identity

When you're unsure which account on another platform belongs to a creator, their Linktree settles it. Resolve it and check whether the handle you have is one they link to.

Limits · read before you connect

What this does not do

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

The server reads the public page and returns its links and profile details. Owner analytics (clicks, views, referrers) aren’t published and can’t be retrieved. A call that fails to find a page still costs 1 credit. This is a single-item endpoint, so nothing paginates and limit and cursor don’t apply. LinkMe is a separate service with its own spoke; handles aren’t interchangeable between the two. Cached responses are possible; fresh: true re-fetches at the same cost. There is no login, so anything a visitor can’t see, the agent can’t see either.

Tools

2 tools, and one endpoint behind them

Linktree has one endpoint, so there is nothing to wrap. list_endpoints tells the agent the path; call_endpoint runs it at the endpoint's own price.

Full credit table →

List every Linktree endpoint

list_endpoints

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

free

Call any Linktree endpoint by path

call_endpoint

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

endpoint's own cost

What list_endpoints returns

/v1/linktree/page · input: handle 1 credit / page

Pricing

100 free credits is 100 Linktree pages.

Then $5 a month for 1,000 credits, or $4 per 1,000 as a top-up. No card to start. Every call costs 1 credit.

100 Linktree pages/v1/linktree/page · 1 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.

Resolve the Linktree for <handle> and list the links

Which social platforms does <handle> link to on Linktree? Then get their follower count on each

Resolve these Linktree handles and extract the store and contact links: <handle 1>, <handle 2>

Has <handle>'s Linktree changed since last week? Here's last week's list: <links>

Find the newsletter link on <handle>'s Linktree

Questions

Before you connect

How much does resolving a Linktree cost? #

1 credit per page. You start with 100 free, and after that 1,000 credits are $5, so a thousand pages for five dollars.

Can I see how many people clicked a link? #

No. Click data is only visible to the page owner in Linktree's dashboard. The server returns the public page.

Is ScraperSocial part of Linktree? #

No. It's an independent service with no connection to Linktree. It reads public pages the same way a browser does.

What do I pass as the handle? #

The username from the URL, without the @ and without the domain. The agent can usually extract it from a pasted link.

Does it work for LinkMe pages too? #

No; LinkMe has its own server at https://mcp.scrapersocial.com/linkme with the same shape: one endpoint, 1 credit.

Go further

A Linktree is the index page of a creator’s internet presence, and now your agent can read it as data. Add https://mcp.scrapersocial.com/linktree, resolve a page you already know, and let it tell you which of the other spokes to call next, and in what order.

Get a free key 100 credits, no card

ScraperSocial is independent and not affiliated with, endorsed by or connected to Linktree. Publicly available data only.