# FetchMCP API

> FetchMCP API is a freemium MCP server for web search and scraping. Remote MCP server that fetches live web pages as Markdown, text or HTML for agents. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Starting price:** $10 a month
- **Platforms:** API
- **Website:** https://fetchmcp.net/docs/mcp
- **MCP Registry name:** net.fetchmcp/fetchmcp
- **Categories:** web search and scraping
- **Listing updated:** 2026-11-15

## About

Billing is per page: a standard server-rendered page costs 1 credit, a JavaScript-rendered page 3, and failed requests or pages with under 500 characters of visible text cost nothing. Each call takes one URL and can be fetched as seen from a chosen country, which matters for geo-dependent pages.

The server exposes two tools. One fetches a page, the other reports the account's remaining credits, plan and rate limit so an agent can check before a large batch. Errors come back as a single actionable sentence, such as telling the agent to use another source when a site blocks access.

Authentication is a bearer API key shared with the REST API, and the endpoint is a stateless Streamable HTTP server at fetchmcp.net/mcp.

## Features

- **Live page fetch:** Retrieves a public page on each request and returns its main content in Markdown, plain text or HTML.
- **Country targeting:** Fetches the page as seen from a chosen ISO country code, defaulting to the US.
- **Output size control:** Caps returned characters between 500 and 100,000 and offers compact or full-body verbosity.
- **Account status tool:** Lets an agent read its credits, plan and rate limit for free before running a batch.
- **Agent-readable errors:** Failures return one instruction the agent can follow, with a note when no credits were charged.

## Good for

- Let a coding agent read documentation pages while it works
- Pull a page as seen from another country to check regional content
- Feed clean Markdown of articles into a research or summarising agent
- Check remaining credits before launching a large crawl

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http fetchmcp https://fetchmcp.net/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://fetchmcp.net/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "fetchmcp": {
      "url": "https://fetchmcp.net/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "fetchmcp": {
      "type": "http",
      "url": "https://fetchmcp.net/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "fetchmcp": {
      "serverUrl": "https://fetchmcp.net/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "fetchmcp": {
      "type": "http",
      "url": "https://fetchmcp.net/mcp"
    }
  }
}
```

## Tools

- `get_page_contents`: Fetch a public web page live and return its main content as clean Markdown, plain text or HTML. Use this when you have a specific URL and need its current content. Works best on articles, docs, product and listing pages. Does not log in, submit forms or execute JavaScript (yet).
- `get_account_status`: Check the remaining credits, plan and rate limit for the connected FetchMCP API account. Use before large batches of fetches.

## FAQ

### How is it billed?

One credit per successful standard page, 3 for a JavaScript-rendered page, and nothing for failures or very short pages.

### How do I connect it from Claude Code?

Run claude mcp add with the HTTP transport, the URL https://fetchmcp.net/mcp and an Authorization bearer header holding your key.

### Is there a free way to try it?

A free test plan gives 250 credits over four weeks with no card.

### Can it fetch several URLs in one call?

The MCP tool takes a single URL per call.

### Is FetchMCP API free?

FetchMCP API has a free plan, with paid plans for more usage or features. Paid plans start at $10 a month.

### How do I add FetchMCP API to Claude Code?

Run this command in your terminal: claude mcp add --transport http fetchmcp https://fetchmcp.net/mcp

### What are the best alternatives to FetchMCP API?

The closest alternatives to FetchMCP API are Scrapling MCP Server, Firecrawl MCP Server, SearXNG Search, NeuralVerge and AI-Powered directory.

## Alternatives

- [Scrapling MCP Server](https://ai-powered.com/mcp/scrapling-mcp-server): Scrapling MCP Server is an open-source MCP server for web search and scraping.
- [Firecrawl MCP Server](https://ai-powered.com/mcp/firecrawl-mcp-server): Firecrawl MCP Server is a freemium MCP server for web search and scraping.
- [SearXNG Search](https://ai-powered.com/mcp/searxng-search): SearXNG Search is an open-source MCP server for web search and scraping.
- [NeuralVerge](https://ai-powered.com/mcp/neuralverge): NeuralVerge is an MCP server for web search and scraping.
- [AI-Powered directory](https://ai-powered.com/mcp/ai-powered-directory): AI-Powered directory is a free MCP server for developer tools.
- [Shopify MCP Server (any store)](https://ai-powered.com/mcp/shopify-mcp-server-any-store): Shopify MCP Server (any store) is a paid MCP server for e-commerce.
- [Chanroll: YouTube Channel Video Scraper (Official API)](https://ai-powered.com/mcp/chanroll-youtube-channel-video-scraper-official-api): Chanroll: YouTube Channel Video Scraper (Official API) is a paid MCP server for design and media.
- [Vidvett: YouTube Video Details Scraper (Official API)](https://ai-powered.com/mcp/vidvett-youtube-video-details-scraper-official-api): Vidvett: YouTube Video Details Scraper (Official API) is a paid MCP server for design and media.

---
Source: https://ai-powered.com/mcp/fetchmcp-api
