Skrapr MCP Server

🎉 Cloud version available! [Fill this form](https://airtable.com/appjnzD8em5Eg1ljz/pag4KfNxEaeFp1s8l/form) to get access.

Local serverstdio

What is the Skrapr MCP server?

Skrapr MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. 🎉 Cloud version available! Fill this form to get access.

What you get

  • No javascript execution: cannot read dynamic content
  • Information may not be present in the loaded page, but in a subpage
  • Load to much information (randomly scrape)
  • Takes to much time to scrape

What the assistant can call

Once Skrapr is connected, these are the calls the assistant has available:

  • scrape_with_schema — - Title: Extract data from a website based on a JSON schema
  • Description — Navigate and scrape the given website to extract data matching the structure of the provided JSON Schema
  • Parameters — - url: The URL of the website to extract data from
  • jsonSchema — The JSON Schema describing the data structure to extract
  • instruction — Optional instructions to guide how the scraping should be performed
  • Read-only — true
  • Local — Setting environment variable PlaywrightMcp__IsLocal=true will make Playwright run locally
  • Remote — Setting environment variable PlaywrightMcp__Endpoint will use Playwright on a remote host

Setting it up

@playwright/mcp on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Choosing this one

Among the browser automation options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Skrapr's toolset — scrape_with_schema, Description, Parameters and 5 more — is a fair guide to whether it matches your workflow. It is maintained by pierregillon; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the skrapr mcp server does with a few real requests.

Available tools

ToolWhat it does
scrape_with_schema- Title: Extract data from a website based on a JSON schema
DescriptionNavigate and scrape the given website to extract data matching the structure of the provided JSON Schema.
Parameters- **url**: The URL of the website to extract data from.
jsonSchemaThe JSON Schema describing the data structure to extract.
instructionOptional instructions to guide how the scraping should be performed.
Read-onlytrue
LocalSetting environment variable PlaywrightMcp__IsLocal=true will make Playwright run locally.
RemoteSetting environment variable PlaywrightMcp__Endpoint will use Playwright on a remote host.

How to install the Skrapr MCP server

{
      "mcpServers": {
        "skrapr": {
          "url": "http://localhost:5000/sse"
        }
      }
    }

Configuration as documented by the project. Restart the client after saving.

Example prompts to try

  • Use Skrapr to scrape with schema.
  • Use Skrapr to Description.
  • Use Skrapr to Parameters.

Frequently asked questions

It connects Skrapr to MCP-compatible AI assistants such as Claude and Cursor, exposing 8 tools (scrape_with_schema, Description, Parameters, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Skrapr directly.