OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI APIs & Platforms

fastCRW

fastCRW is a Rust-based web retrieval service with a CLI, API and MCP server for searching, scraping, mapping, crawling and extracting content into Markdown or structured JSON.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

fastCRW — OpenViST project profile in AI APIs & Platforms.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use fastCRW when an application or AI tool needs to retrieve web pages or search results and convert them into content suitable for further processing.

Who it is for

  • Developers building web research or retrieval into AI applications
  • AI coding-tool users who want web search and extraction through MCP
  • Operators who need a local or self-hosted crawler and can configure its supporting services

Documented uses

  • Scrape a page into Markdown, HTML, links, screenshots or schema JSON
  • Crawl a bounded section of a site and collect its pages
  • Discover site URLs without scraping every page
  • Search the web and optionally scrape selected results
  • Extract structured fields from one or multiple URLs
Before you choose

Requirements & limits

The README documents local CLI use without an account. Cloud access requires an API key. It describes a 1,000-credit offer without a credit card; this is a repository claim, not a statement of current offer terms.

  • Local and managed deployments have different operational responsibilities: local users choose renderers, search, authentication, proxies and capacity; managed service includes managed proxies and hosted capabilities.
  • Capabilities and response shapes may differ by deployment; consult the project’s capability and response-shape documentation for the selected mode.
  • The documented installer supports macOS and Linux on Intel and ARM.
  • The repository specifies the AGPL-3.0 license.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install the local CLI and scrape a URL

Set up the documented local CLI and request a page scrape.

Before you start

  • macOS or Linux on Intel or ARM
  • A shell environment

Steps

  1. Run the command below to install the binary.

    Documented command
    curl -fsSL https://fastcrw.com/install | sh

  2. Run crw https://example.com to scrape a URL.

Expected outcome

The CLI requests a scrape of the URL; the repository says this works after installation in local mode.

Guide limitations

  • This recipe covers local CLI scraping, not Cloud setup or search.
  • Available output formats and deployment capabilities can differ.
Documentation 1 ↗
Source-based practical guide

Connect fastCRW through MCP

Install the CRW MCP server in detected AI tools.

Before you start

  • Node.js/npm via npx
  • An AI coding tool supported by the installer

Steps

  1. Run the command below.

    Documented command
    npx -y crw-mcp@latest install

  2. The installer adds the CRW skill and MCP server to detected AI tools.

Expected outcome

The detected tools receive the CRW MCP server setup for using its web retrieval functions.

Guide limitations

  • The documented command installs the MCP integration; it does not describe a particular tool task or result.
  • Tool detection depends on the AI tools already being set up.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
12 October 2026
Original website title
fastcrw/crw · Official homepage title · retained in its source language
How we review sourcesSuggest a correction