
DeepSFetch
Scrape, search and extract web data as Markdown or validated JSON, with credit caps
- Pricing
- Paid
- Platforms
- API, Web, CLI
- Runs
- Remotely
- Version
- 2.0.1
- Listing updated
- 2 days ago
About DeepSFetch
DeepSFetch is a paid MCP server for web search and scraping. It runs as a hosted remote server, so there is nothing to install locally.
DeepSFetch is a hosted web-data service and its MCP server exposes it to agents using workspace API keys. Collections can be requested as Markdown, HTML or links, or as structured JSON by defining a schema for the fields you want. Search covers Web, News and Images sources at 30 credits per source, a fresh HTTP fetch costs 3 credits, a cached result 1, and a browser fetch 8.
Spend is controlled by estimates before a run, credit caps and a history of each run. Pages can be grouped into collections, synced and monitored for changes between versions. Where extraction uses an AI model, you can connect your own OpenAI, Google or DeepSeek key, with model costs billed separately by that provider.
A public developer kit holds the JavaScript and Python SDKs, a CLI and n8n workflow templates for price monitoring, catalogue extraction and documentation for RAG; the hosted engine itself is not open source.
Install
Run in a terminal
claude mcp add --transport http deepsfetch https://mcp.deepsfetch.com/mcpAdd to Settings → Connectors → Add custom connector
https://mcp.deepsfetch.com/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"deepsfetch": {
"url": "https://mcp.deepsfetch.com/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"deepsfetch": {
"type": "http",
"url": "https://mcp.deepsfetch.com/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"deepsfetch": {
"serverUrl": "https://mcp.deepsfetch.com/mcp"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"deepsfetch": {
"type": "http",
"url": "https://mcp.deepsfetch.com/mcp"
}
}
}What it does
- Markdown or JSON output
- Returns page content as Markdown or schema-validated JSON.
- Credit caps and estimates
- Shows an estimated cost before a run and enforces limits.
- Search and crawl
- Web, News and Image search, plus URL discovery and crawling.
- Collections and monitors
- Group pages, track syncs and see what changed between versions.
- n8n templates
- Ready workflows for price monitoring, catalogues and RAG documentation.
- Bring your own AI key
- Use OpenAI, Google or DeepSeek for extraction, billed by the provider.
Good for
- Feed clean documentation into a vector store
- Monitor product prices and compare against a baseline
- Extract fields from a catalogue page into JSON
- Give an agent search results with cited pages
- Track when a page changes
Pricing
Paid, from $24 a month
$24/mo for 10,000 credits; $79 and $249 tiers; yearly saves about 20%
Prices change. Check deepsfetch.com before you buy.
DeepSFetch FAQ
How is usage billed?
In credits: 30 per search source, 3 per fresh HTTP fetch, 1 per cached result and 8 per browser fetch.
What do plans cost?
Paid plans listed are $24 a month for 10,000 credits, $79 for 50,000 and $249 for 250,000; a 1,000-credit plan shows contact for pricing.
Is the developer kit open source?
The repository holds client-side SDKs, a CLI and n8n code; the collection engine and hosted service are not included.
Does model usage count against credits?
No. Provider costs for your own AI key are billed by the provider, separate from DeepSFetch credits.
Is DeepSFetch free?
No. DeepSFetch is a paid product. Paid plans start at $24 a month.
How do I add DeepSFetch to Claude Code?
Run this command in your terminal: claude mcp add --transport http deepsfetch https://mcp.deepsfetch.com/mcp
What are the best alternatives to DeepSFetch?
The closest alternatives to DeepSFetch are Scrapling MCP Server, Firecrawl MCP Server, SearXNG Search, NeuralVerge and AI-Powered directory.
Alternatives to DeepSFetch

Scrapling MCP Server
MCP serverMCP server for AI clients to scrape sites with HTTP and stealth browser sessions
Runs locally- 17 tools
- Open source
- 104K GitHub stars
- Web search and scraping

Firecrawl MCP Server
MCP serverMCP server that lets AI agents search, scrape and interact with web pages
- 3 tools
- Remote
- Freemium
- 7.8K GitHub stars
- Web search and scraping

SearXNG Search
MCP serverMCP server for web search and page reading through a SearXNG instance
Runs locally- 3 tools
- Open source
- 1.4K GitHub stars
- Web search and scraping

NeuralVerge
MCP serverStructured, source-tagged business and people data from 300+ sources for agents
- 200 tools
- Remote
- Free trial
- 1 GitHub star
- Web search and scraping

AI-Powered directory
MCP serverSearch AI tools, agents and MCP servers and get install configs from inside your AI assistant.
- 4 tools
- Remote
- Free
- Developer tools

Shopify MCP Server (any store)
MCP serverHosted MCP server that returns any Shopify store's products, prices and stock
Not checked yet- 4 tools
- Remote
- Paid
- E-commerce