Crawlforge MCP Server runs on your own machine — the client starts it, so there is no endpoint to ping. 1 876 installs a week from npm. Last commit 2 Nov 2026.
Web scraping, crawling, deep research & autonomous extraction — 31 MCP tools, clean Markdown/JSON
We read the source, 21 h ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
postinstall: echo ' CrawlForge MCP Server installed! Quick start: run "npx crawlforge init" to configure your API key, install skills, and register the MCP server with your AI clients. Or run "npx crawlforge-setup" to configure your API key only. '
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add crawlforge-mcp-server -e 'CRAWLFORGE_API_KEY=<CRAWLFORGE_API_KEY>' -- npx -y crawlforge-mcp-server
{
"mcpServers": {
"crawlforge-mcp-server": {
"command": "npx",
"args": [
"-y",
"crawlforge-mcp-server"
],
"env": {
"CRAWLFORGE_API_KEY": "<CRAWLFORGE_API_KEY>"
}
}
}
}
[mcp_servers.crawlforge-mcp-server]
command = "npx"
args = ["-y", "crawlforge-mcp-server"]
env = { CRAWLFORGE_API_KEY = "<CRAWLFORGE_API_KEY>" }
{
"mcpServers": {
"crawlforge-mcp-server": {
"command": "npx",
"args": [
"-y",
"crawlforge-mcp-server"
],
"env": {
"CRAWLFORGE_API_KEY": "<CRAWLFORGE_API_KEY>"
}
}
}
}
{
"servers": {
"crawlforge-mcp-server": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"crawlforge-mcp-server"
],
"env": {
"CRAWLFORGE_API_KEY": "<CRAWLFORGE_API_KEY>"
}
}
}
}
Put your own value in place of
<CRAWLFORGE_API_KEY> (CrawlForge API key for authentication and usage/credit tracking. Get a free key at https://www.crawlforge.dev).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
DATAFORSEO_LOGIN (DataForSEO account login. Optional — only needed to enable the serp_rank tool (real Google organic rank lookups); billed separately to the caller's own DataForSEO account), DATAFORSEO_PASSWORD (DataForSEO account password. Optional — only needed to enable the serp_rank tool).
Web scraping for agents: scrape, crawl, map, search and extract pages as clean markdown or JSON.
Web scraping MCP — extract clean markdown, links, and metadata from any URL.
Web search, URL content extraction to Markdown, site mapping, and recursive web crawler.
Give AI agents clean, LLM-ready web data — scrape any URL to markdown or extract structured JSON.
AI-powered web scraping MCP. Distill pages to Markdown or extract structured data via JSON Schema.
AI-powered web scraping MCP. Distill pages to Markdown or extract structured data via JSON Schema.
Pay-per-call MCP tools: web search, scraping, on-chain wallet intel, extraction. x402 USDC on Base.
Firecrawl web data: scrape, map, search, crawl, extract, research, and llms.txt.
Answers built from our own checks of this server.