Rag Web Browser MCP Server

Enables AI agents and LLMs to interact with the web and extract information from web pages via the RAG Web Browser Actor.

Remote serverstreamable-httpTypeScript 208

What is the Rag Web Browser MCP server?

Connect Rag Web Browser to Claude, Cursor or any other MCP client and it stops being a tab you switch to. Enables AI agents and LLMs to interact with the web and extract information from web pages via the RAG Web Browser Actor. The rag web browser mcp server is what makes that connection.

What the server does

Implementation of an MCP server for the RAG Web Browser Actor. This Actor serves as a web browser for large language models (LLMs) and RAG pipelines, similar to a web search in ChatGPT.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • name — search
  • raw-http — Fast (no JS execution) – good for static pages
  • browser-playwright — Handles JS-heavy sites – slower, more robust
  • Tools — The Tools tool exposed by this server
  • Prerequisites — Clone & install: bash git clone https://github.com/apify/mcp-server-rag-web-browser.git cd mcp-server-rag-web-browser npm install
  • Build — The Build tool exposed by this server
  • Debugging — Since MCP servers operate over standard input/output (stdio), debugging can be challenging. For the best debugging experience, use the [MCP

Installation

Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.

Credentials and setup notes

Configuration is passed through the environment: APIFY_TOKEN. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

  • Node.js (v18 or higher) - Apify API Token (APIFY_TOKEN) Clone & install:

Where it fits

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. Rag Web Browser's toolset — name, raw-http, browser-playwright and 4 more — is a fair guide to whether it matches your workflow. It is maintained by apify; 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.

Worth knowing first

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
namesearch
raw-httpFast (no JS execution) – good for static pages.
browser-playwrightHandles JS-heavy sites – slower, more robust.
ToolsThe Tools tool exposed by this server.
PrerequisitesClone & install: bash git clone https://github.com/apify/mcp-server-rag-web-browser.git cd mcp-server-rag-web-browser npm install
BuildThe Build tool exposed by this server.
DebuggingSince MCP servers operate over standard input/output (stdio), debugging can be challenging. For the best debugging experience, use the [MCP Inspector](https://github.com/modelcontextprotocol/inspector).

How to install the Rag Web Browser MCP server

{
  "mcpServers": {
    "rag-web-browser": {
      "command": "npx",
      "args": ["@apify/mcp-server-rag-web-browser"],
      "env": {
        "APIFY_TOKEN": "your-apify-api-token"
      }
    }
  }
}

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

Configuration

  • Node.js (v18 or higher) - Apify API Token (APIFY_TOKEN) Clone & install:
VariableDescriptionRequired
APIFY_TOKENCredential the server authenticates with.Yes

Example prompts to try

  • Use Rag Web Browser to name.
  • Use Rag Web Browser to raw-http.
  • Use Rag Web Browser to browser-playwright.

Frequently asked questions

The Rag Web Browser is a tool that enables AI agents and LLMs to interact with the web, extract information, and perform web scraping tasks. It allows AI to browse the web like a human, gathering data for various applications.