RAG Web Browser MCP

MCPOfficialOpen SourceApache-2.061.2

by apify • Search & Retrieval

A local MCP server that lets AI agents search the web or fetch pages via the RAG Web Browser Actor and returns cleaned content (Markdown/Text/HTML).

Example Use Cases

1
Perform Google-style web searches and retrieve cleaned, summarized content from the top N results as Markdown or text.
2
Fetch and extract the content of a single URL, with options for fast raw HTTP scraping or Playwright-based JS rendering.
3
A local stdio-based MCP integration to stream web-extraction results to LLMs or RAG pipelines during reasoning.

Description

This MCP server connects AI agents to the Apify RAG Web Browser Actor in standby mode, enabling Google-style searches, scraping top results, or fetching single URLs and returning cleaned page contents. It supports fast raw HTTP scraping or Playwright-based browser scraping for JS-heavy sites, and streams results back to clients over stdio or HTTP/SSE. The server is intended for local use to provide quick, agent-friendly web browsing/tooling for retrieval-augmented generation pipelines. Note: the project is deprecated in favor of the hosted mcp.apify.com service.

Capabilities(1 total)

Tools (1)

search

Search phrase or a URL at Google and return crawled web pages as text or Markdown. Prefer HTTP raw client for speed and browser-playwright for reliability.

query:string*maxResults:integerscrapingTool:stringoutputFormats:arrayrequestTimeoutSecs:integer

Quick Actions

View on GitHub

Security

Scanned 2 month(s) ago

Risk Level

MINIMAL

Read-only data retrieval, no side effects

Trust Score

C58/100

7/17 checks passed

Scores are informational only and provided “as is” without warranty. AgentHotspot assumes no liability for actions taken based on these ratings.

Quick Stats

Service TypeMCP

Pricing ModelUnknown

Capabilities1 Tools / 0 Prompts / 0 Resources

Ownerapify

CategorySearch & Retrieval

DependenciesStandalone

Set Your Username