fastCRW MCP server
Commit Nov 14, 2026Converts URLs into clean markdown or structured JSON through web scraping, crawling, mapping, and searching capabilities.
Also known as us/crw, crw
- Stars
- 1,255
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 0.36.0
- Last commit
- Nov 14, 2026
- License
- AGPL-3.0
What is fastCRW MCP?
fastCRW converts URLs into clean markdown or structured JSON through web scraping, crawling, mapping, and searching capabilities.
Summary generated from the project's README
About fastCRW MCP server
CRW Web Scraper provides a way to transform web content into clean markdown or structured JSON. It is designed for developers and AI agents that need to ingest web data through scraping, crawling, mapping, searching, and extraction. Users can run the engine as a local Rust binary for data control and private networks, or utilize a managed API for hosted capabilities like managed proxies and JS rendering.
When used as an MCP server, it integrates with AI coding tools such as Claude Code, Cursor, Codex, Gemini CLI, OpenCode, and Windsurf. Setting up the managed version requires an API key, which is stored in a local config file. The service offers a free tier with 1000 credits and supports macOS and Linux on both Intel and ARM architectures. It distinguishes itself through high truth-recall and low memory usage, idling at approximately 14 MB RAM.
What you can do with it
- 1Convert web pages to markdownAn AI agent can transform a single URL into a clean markdown format for easier processing.
- 2Perform web-wide searchesA developer can instruct a client to search the internet and scrape specific results.
- 3Discover site structuresYou can use the mapping tool to find URLs on a website without the need to scrape every individual page.
- 4Extract structured dataThe engine can pull specific fields from one or many different URLs to create structured datasets.
Written from the project's README. Every use case is checked against a quote from it.
How to install fastCRW MCP
Formats verified 10 Nov 2026Install fastCRW MCP in Claude Code
$ claude mcp add crw -- docker run -i --rm ghcr.io/us/crw:latestInstall fastCRW MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"crw": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/us/crw:latest"
]
}
}
}Install fastCRW MCP in VS Code
.vscode/mcp.json
{
"servers": {
"crw": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/us/crw:latest"
]
}
}
}Install fastCRW MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"crw": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/us/crw:latest"
]
}
}
}Install fastCRW MCP in Codex
~/.codex/config.toml
[mcp_servers.crw] command = "docker" args = ["run", "-i", "--rm", "ghcr.io/us/crw:latest"]
Install fastCRW MCP in Gemini CLI
~/.gemini/settings.json
{
"mcpServers": {
"crw": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/us/crw:latest"
]
}
}
}Configuration
CRW_API_KEY
| Name | Description | |
|---|---|---|
| CRW_API_KEY | — |
Automated checks
Ran Nov 12, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work
- Source repository linked and reachablePass
- Open source license (OSI)Pass
- Commit or release in the last yearPass
- Package name not close to a popular packageNot checked
- Remote endpoint uses HTTPSNot checked
- Destructive tools are labelledNot checked
- No hidden instructions to the modelPass
- No critical advisory in the package or its dependenciesNot checked
README
View on GitHubOne-command install
curl -fsSL https://fastcrw.com/install | sh
Runs local and free, no account needed. To use the Cloud, paste your key into the same command and it installs the binary, connects the key, and registers the MCP server with the AI coding tools you already have:
curl -fsSL https://fastcrw.com/install | CRW_API_KEY=crw_live_... sh
crw search "rust tutorials"
Claude Code, Cursor, Codex, Gemini CLI, OpenCode and Windsurf are picked up
automatically when they are already set up; nothing else is touched, and your
key stays in ~/.config/crw/config.toml rather than being copied into each
tool. Add CRW_NO_AGENTS=1 to skip that step, or run crw setup on its own to
choose interactively.
1000 free credits, no credit card. Managed proxies, JS rendering and search, with nothing to run or keep up to date. Get my free key →
macOS and Linux, Intel and ARM. More install options →
What it does
| Operation | Outcome |
|---|---|
| Scrape | One URL to markdown, HTML, links, screenshots, or schema JSON |
| Crawl | Follow a bounded site crawl and collect its pages |
| Map | Discover URLs without scraping every page |
| Search | Search the web and optionally scrape selected results |
| Extract | Produce structured fields from one or many URLs |
Why fastCRW
On Firecrawl's own public 1,000-URL dataset, fastCRW recovered more truth than Crawl4AI and Firecrawl, matched the fastest median latency, and idled at ~14 MB RAM.
On a different benchmark entirely, answer accuracy rather than scrape recall, fastCRW answers 90.0% of the 600 AA-Omniscience questions correctly. Every product listed on the Artificial Analysis Search Index sits below it.
Choose how you use it
CLI
crw https://example.com # scrape, works right after install
crw search "rust async runtime" # search, after `crw setup`
Python SDK
Using Cloud? Get an API key, then export it once:
export CRW_API_KEY="crw_live_..."
pip install crw
from crw import CrwClient
client = CrwClient()
page = client.scrape("https://example.com", formats=["markdown"])
print(page["markdown"])
npm install crw-sdk
import { CrwClient } from "crw-sdk";
const client = new CrwClient();
const page = await client.scrape("https://example.com", {
formats: ["markdown"],
});
console.log(page.markdown);
Local mode and more SDK examples → · REST API →
MCP for AI agents
npx -y crw-mcp@latest install
Installs the CRW skill and MCP server in your detected AI tools. crw setup can
also do this step, so either path is enough.
Manual setup →
Choose where it runs
| Managed API | Local / self-hosted | |
|---|---|---|
| Best for | Zero infrastructure and managed scaling | Data control, private networks, or custom infrastructure |
| Start | Create an API key, then crw setup |
Install and run crw <URL> |
| Operations | Managed proxies, billing, and hosted capabilities | You choose renderers, search, auth, proxies, and capacity |
Capabilities and response shapes can differ by deployment:
/v1/capabilities · response shapes
Learn more
Contributing
The workspace requires Rust 1.85 or newer:
git clone https://github.com/fastcrw/crw
cd crw
make check-fast
Contributors
crw is better because of these people. Thank you, all of you:
Engine and MCP server: AGPL-3.0. Python and TypeScript SDKs: MIT. Embedding license: hello@fastcrw.com.
Star History
Please respect website policies. Crawl and map follow robots.txt by default.
fastCRW MCP questions
How do I add fastCRW MCP to Claude Code?
Run claude mcp add crw -- docker run -i --rm ghcr.io/us/crw:latest in your terminal. Add --scope user to make it available in every project.
How do I add fastCRW MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
How do I install it?
You can install it using a single curl command, which runs locally for free or connects to the managed API if you provide an API key.
Does it support AI coding tools?
Yes, it automatically detects and integrates with tools like Claude Code, Cursor, Codex, Gemini CLI, OpenCode, and Windsurf.
Can I run it myself?
Yes, you can run it locally as a small Rust binary for data control and private networks, or use the managed API for zero infrastructure.