holoscrape-mcp

holoscrape-mcp

This MCP server lets AI agents read and extract data from your own logged-in Chrome browser via the HoloScrape extension, enabling private, local automation of web scraping and list extraction without uploading data.

Category
Visit Server

README

holoscrape-mcp

Give an AI agent your own logged-in browser. This runs locally, does not upload anything, and never sees your passwords — the HoloScrape Chrome extension does the actual reading, in your own signed-in Chrome, and this process is only the bridge that lets an MCP-speaking agent (Claude Code, Claude Desktop, Cursor, Windsurf) ask it to.

Use it

You do not install this — your agent's MCP config runs it on demand:

{
  "mcpServers": {
    "holoscrape": { "command": "npx", "args": ["-y", "holoscrape-mcp"] }
  }
}

Then pair it once:

npx -y holoscrape-mcp --code

prints a one-time code. Open the HoloScrape side panel in Chrome and enter it there. That's the whole setup — the code is remembered, so this is a one-time step, not a per-session one.

What it can do

Once paired, an agent can read whatever list is on a page you've allowed — a search results grid, a directory listing, a table — and walk its pages. Nothing runs until you've explicitly allowed the site in the HoloScrape panel; an agent cannot grant that to itself.

Why local

The alternative is a hosted relay that sees every page it reads. This process listens only on 127.0.0.1, and the pairing code is the only thing that can talk to it — printed once, typed once, checked before a socket is even allowed to open.

Tools

Tool What it does
current_page The tab the person has open right now, and whether it can be read.
search_open Turn plain words ("restaurants in cimahi") into a real search, opened in their browser.
tabs_list Every http(s) tab currently open.
tab_open Open a specific URL.
site_probe A cheap check, before committing to a run: is there a list, how many rows, how does it paginate.
page_study Every repeating structure on a tab, ranked with evidence — not one verdict, several candidates so the caller chooses. Flags page furniture (footers, filter sidebars) that a naive reading mistakes for the real list.
page_grow Press a load-more control or scroll, and report the record count before and after — the only honest way to answer "does this load more".
list_extract Start reading a list into a table, following its pages. Returns immediately; poll run_status.
run_status Progress on a run — including waiting_for_user when the site puts up a human check.
run_stop Stop a run early; keeps what it already read.
results_list Tables already extracted in this browser, newest first.
results_get Rows and columns from a saved table.
results_export Write a whole table to CSV in Downloads, for tables too big to read inline.

Try it without an agent

node try.mjs tabs
node try.mjs study <tabId>

Drives the same stdio protocol an agent would, useful for checking the whole chain — this script → the server → the WebSocket → the extension → a real tab — works before pointing a real agent at it.

Requirements

  • Node.js 18+
  • The HoloScrape Chrome extension, installed and paired

License

MIT

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

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.

Official
Featured
TypeScript
Kagi MCP Server

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.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

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.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured