Back to MCP Directory
Fetcher
Model Context Protocol moderate risk

Fetcher

Fetcher MCP retrieves web page content using Playwright, supporting JavaScript execution, content extraction, and flexible output formats, enabling dynamic web scraping.

Connections & Capabilities

Connects To

GitHubDockerPlaywright

Capabilities

readexec

Quickstart

Install

npx -y fetcher-mcp

Config

{
  "mcpServers": {
    "fetcher": {
      "command": "npx",
      "args": ["-y", "fetcher-mcp"]
    }
  }
}

Exposed MCP Tools (3)

moderate
fetch_url

Retrieves web page content from a specified URL using Playwright.

Executes JavaScript and fetches content from arbitrary URLs.

moderate
fetch_urls

Batch retrieves web page content from multiple URLs in parallel.

Parallel fetching increases the risk of resource exhaustion and potential abuse.

high
browser_install

Installs the Playwright Chromium browser binary automatically.

Installs binaries, potentially introducing malicious software if the source is compromised.

Safety Assessment

Fetcher MCP is relatively safe for read operations, but the ability to execute JavaScript from fetched web pages introduces potential risks. It's crucial to sanitize inputs and monitor resource usage to mitigate potential security vulnerabilities. Running it in a sandboxed environment is recommended.

  • Uses Playwright in a sandboxed environment.
  • Resource optimization reduces bandwidth usage.
  • Comprehensive error handling ensures reliable operation.
  • Supports disabling media resources to minimize data retrieval.
  • Internet access required to fetch web pages.
  • Can execute JavaScript from untrusted sources.
  • Potential for SSRF (Server-Side Request Forgery) if not carefully managed.
  • Exposure to vulnerabilities in Playwright and its dependencies.