ContextFetch
Web search and page-to-Markdown for agents, with a free keyless tier
- Pricing
- Freemium
- Platforms
- CLI, API
- Runs
- Locally or Remotely
- Version
- 1.1.0
- Listing updated
- 2 days ago
About ContextFetch
ContextFetch is a freemium MCP server for web search and scraping. It can run locally on your machine or as a hosted remote server.
ContextFetch is built around returning less text. Its search tool brings back each page cut down to the passages that answer the query, ranked by a cross-encoder, rather than whole pages. Page extraction, similar-page lookup, crawling and a site map tool use the same idea.
The research tool runs several sub-queries on the server, dedupes pages and returns a single Markdown evidence pack with numbered sources quoted verbatim; the answer tool is extractive and generates no text. A free key tool claims the network's free allowance, and balance and auto top-up tools manage credits.
Without a key you get 25 searches a day per network; otherwise it is pay as you go at 1 dollar per 1,000 calls, with an Exa- and Tavily-compatible API underneath. Failed connections and 429 or 5xx responses are retried with backoff.
Install
Run in a terminal
claude mcp add --transport http mcp https://api.contextfetch.dev/mcpAdd to Settings → Connectors → Add custom connector
https://api.contextfetch.dev/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"mcp": {
"url": "https://api.contextfetch.dev/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"mcp": {
"type": "http",
"url": "https://api.contextfetch.dev/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"mcp": {
"serverUrl": "https://api.contextfetch.dev/mcp"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"mcp": {
"type": "http",
"url": "https://api.contextfetch.dev/mcp"
}
}
}Configuration
CONTEXTFETCH_API_KEYContextFetch API key. Leave unset for the free keyless tier (25 requests per day per IP).CONTEXTFETCH_API_BASEAPI base URL, only for a self-hosted engine.
Tools this server provides (11)
Taken from the project documentation; the running server may differ.
- contextfetch_search
- Web search returning query-relevant passages.
- contextfetch_extract_url
- A public page as Markdown, optionally pruned by a query.
- contextfetch_find_similar
- Pages similar to a URL.
- contextfetch_research
- Server-side multi-sub-query evidence pack.
- contextfetch_deep_research
- Earlier name of the research tool, kept for existing setups.
- contextfetch_answer
- Extractive answer from top pages with numbered sources.
- contextfetch_crawl
- Crawls a site and returns pages as Markdown.
- contextfetch_map
- Lists a site's URLs from sitemaps and links.
- contextfetch_balance
- Remaining credits and auto-reload settings.
- contextfetch_get_free_key
- Claims the network's free API key.
- contextfetch_auto_reload
- Turns auto-reload on or off or changes it.
What it does
- Pruned search results
- Returns only passages relevant to the query.
- Page to Markdown
- Extracts public pages with tables kept.
- Server-side research
- One call runs sub-queries and builds an evidence pack.
- Crawl and site map
- Walks a site respecting robots.txt or lists its URLs.
- Free keyless tier
- 25 searches a day with no signup.
- Credit tools
- Balance, free key and auto-reload controls.
Good for
- Research a technical question with cited passages
- Convert a docs page to clean Markdown for a prompt
- Find pages similar to a given URL
- Crawl a documentation site and pull relevant sections
Pricing
Freemium
Free keyless tier; pay as you go at $1 per 1,000 calls, top-ups from $10
Prices change. Check contextfetch.dev before you buy.
ContextFetch FAQ
What does it cost?
1 dollar per 1,000 searches, extractions and similar calls; crawl is per page returned.
Is there a free tier?
Yes, 25 searches a day per network with no key, plus a free key of 2,500 searches.
Does it generate answers?
No. Answers are extractive, quoting passages verbatim.
What does it need?
Node.js 18 or newer for the stdio package.
Is ContextFetch free?
ContextFetch has a free plan, with paid plans for more usage or features.
How do I add ContextFetch to Claude Code?
Run this command in your terminal: claude mcp add --transport http mcp https://api.contextfetch.dev/mcp
What are the best alternatives to ContextFetch?
The closest alternatives to ContextFetch are Scrapling MCP Server, Firecrawl MCP Server, SearXNG Search, NeuralVerge and AI-Powered directory.
Alternatives to ContextFetch

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