Skip to content
Agent Search Engine.
Submit a tool
Menu

Record · fetcher-mcpMCP serverCosts not checkedNo recent recorded pushRecord checked Sep 23, 2026

Fetcher MCP

Fetch JavaScript-rendered web pages with a headless browser and return their main content as HTML or Markdown.

Visit Fetcher MCP →View repository

Sources and review

Checked against public documentation on . Suitability guidance is our editorial judgment; this is not a performance benchmark or an endorsement.

Best for

Reading modern, script-heavy pages that plain HTTP fetch tools return empty.

About Fetcher MCP

Fetcher MCP fetches web pages with a headless Playwright browser, so dynamic, JavaScript-rendered sites work, and extracts the main content with the Readability algorithm, dropping navigation and ads. It returns HTML or Markdown, fetches several URLs in parallel and blocks unneeded resources to save time. HTTP and SSE transports and Docker deployment are supported.

Fetcher MCP is listed in this index written primarily in TypeScript, with 1.1k stars on GitHub. Its latest recorded repository push was in January 2026; that is not an ASE editorial review date.

Before connecting: access and data

This record's specific permissions have not been reviewed by ASE. Read the publisher's documentation before copying setup or connecting.

  • List the accounts, files and services the enabled tools can read, change or execute. Check your actual credentials and discovered tools.
  • Use narrowly scoped credentials and read-only mode where supported. Review proposed writes before approving them; a generated configuration does not apply these limits for you.
  • Local launch is not local-only data processing. External services receive requests, and your client may pass tool results to its model provider. Check both destinations before sharing private data.
  • Keep keys and browser session files out of shared config, repositories and screenshots. Know how to disconnect the server and separately revoke its credentials or account sessions.

Read the setup guide →

Add Fetcher MCP to your MCP client

Generated from the launch command in the project's README. Your client starts the server on demand.

Claude CodeRun in your terminal
claude mcp add fetcher-mcp -- npx -y fetcher-mcp
Cursor~/.cursor/mcp.json or .cursor/mcp.json
{
  "mcpServers": {
    "fetcher-mcp": {
      "command": "npx",
      "args": ["-y", "fetcher-mcp"]
    }
  }
}
VS Code.vscode/mcp.json
{
  "servers": {
    "fetcher-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "fetcher-mcp"]
    }
  }
}
Claude Desktopclaude_desktop_config.json
{
  "mcpServers": {
    "fetcher-mcp": {
      "command": "npx",
      "args": ["-y", "fetcher-mcp"]
    }
  }
}
Codex~/.codex/config.toml
[mcp_servers.fetcher-mcp]
command = "npx"
args = ["-y", "fetcher-mcp"]

Check the project's README for required accounts, keys and permissions before connecting. Setup guide for each client →

For agent buildersMake your product part of the discovery.Explore advertising