Start free

Platforms MCP server

MCP server · 2 tools · 1 endpoint

LinkMe MCP server

Read a public LinkMe page as structured data: who the page belongs to and every destination it links out to.

Get a free key Connect in a minute

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

scrapersocial-linkme mcp.scrapersocial.com/linkmeconnected

you

Read the LinkMe page for <handle> and tell me which links point to a store

agent

calls list_endpoints free

server

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

agent

calls call_endpoint 1 credit · the endpoint's own cost

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

server

returns

page object · the full page record

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/linkme

claude.aiOAuth

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

mcp.scrapersocial.com/linkme

Web, desktop and mobile. Nothing else to paste.

Claude Codeone command

Run this in a terminal.

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

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

Windsurf~/.codeium/windsurf/mcp_config.json

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

Gemini CLI~/.gemini/settings.json

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

Any clientStreamable HTTP · OAuth 2.1 or Bearer

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

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 LinkMe

Brands that work with creators spend a lot of time on a dull question: where does this person actually send their audience? A LinkMe page answers it in one screen, and the LinkMe spoke on ScraperSocial’s MCP server lets an agent read that screen as data instead of a human reading it as a web page.

The spoke carries two tools and no wrapper. list_endpoints is the free directory call; on LinkMe it reports a single path, /v1/linkme/page, which takes a handle and costs 1 credit. call_endpoint runs it. What comes back is the owner’s profile information plus the outbound links, in the order the page shows them, as a JSON object your agent can filter, compare or store.

Treat LinkMe as what it is, a hosted bio page and not a social network. ScraperSocial reads it as public web content, the same way it reads a product listing or an app store entry, and no account is signed in on either side.

Because a page costs a single credit, the free allowance on a new account stretches to a hundred of them, which is more than most outreach lists need. Connect https://mcp.scrapersocial.com/linkme and hand it a handle.

Three jobs it finishes on its own

Pre-outreach due diligence

Before a campaign email goes out, resolve each creator's LinkMe and let the agent note whether they link a storefront, a booking form or a competitor's product. Ten pages cost ten credits and the answer lands in a column.

Monitoring brand ambassadors

If you pay creators to feature a link, check that it's still on their LinkMe. A weekly resolve per ambassador shows the agent which links went missing and which new sponsors appeared.

Routing to the right platform spoke

Resolve the page first, then let the agent call only the social spokes the links point at. It avoids paying for lookups on networks the creator doesn't use.

Limits · read before you connect

What this does not do

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

What you get is the public page, parsed: the profile fields LinkMe displays and the links underneath them. Click-through numbers, visitor stats and anything inside the owner’s LinkMe account aren’t published, so the agent can’t fetch them. The page endpoint returns one object, never a list, so there’s no limit or cursor to set. A handle that doesn’t exist still costs the 1-credit minimum. LinkMe and Linktree are unrelated services; a Linktree username won’t resolve here, and the Linktree spoke is a separate server. Reads can be cached; fresh: true fetches again at the same price.

Tools

2 tools, and one endpoint behind them

LinkMe 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 LinkMe endpoint

list_endpoints

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

free

Call any LinkMe endpoint by path

call_endpoint

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

endpoint's own cost

What list_endpoints returns

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

Pricing

100 free credits is 100 LinkMe 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 LinkMe pages/v1/linkme/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.

Read the LinkMe page for <handle> and tell me which links point to a store

Resolve <handle> on LinkMe and list the destinations in order

For these LinkMe handles, note whether each links to a booking page: <first handle>, <second handle>

Is our sponsored link still on <handle>'s LinkMe? Here's the URL: <url>

Which social networks does <handle> link to on LinkMe, and what are their usernames there?

Questions

Before you connect

How much is a LinkMe read? #

A single credit per page. The 100 credits you get at signup are a hundred reads; a further 1,000 are $5.

Are click-through numbers included? #

No. LinkMe shows those only to the page owner inside their account, and the server only sees what a visitor sees.

Who runs this, LinkMe? #

No. ScraperSocial is independent of LinkMe, has no affiliation with it, and isn't run by it. It fetches the page like any visitor would and hands back JSON.

Why isn't there a dedicated page tool? #

Capability tools wrap actions that exist across many platforms, like search or reviews. A bio page is a one-platform read, so it lives behind `call_endpoint` by path and the agent reaches it just the same.

What goes in the handle field? #

The page's username, the segment after the domain in its URL. Leave off any @.

Go further

If part of your week is checking where creators send people, a LinkMe read for a credit is a cheap habit to build into an agent. Add https://mcp.scrapersocial.com/linkme beside the social spokes, resolve one handle, and watch how much of the rest of the research it sets up.

Get a free key 100 credits, no card

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