Fetch MCP
This MCP server fetches and extracts web page content using a Playwright headless browser.
Fetch a single URL with
fetch_url, returning Markdown by default or HTML/plain visible text.Fetch multiple URLs in parallel with
fetch_urls.Render JavaScript-heavy and dynamic pages through Playwright.
Extract main readable content automatically or preserve full page/HTML content.
Configure timeout, navigation wait behavior, max returned length, media blocking, and debug mode for manual login.
Install the required Playwright Chromium browser with
browser_install.Run over stdio or HTTP/SSE transport, with REST endpoints for tools in HTTP mode.
Enables fetching and processing of dynamic web content that relies on JavaScript, executing client-side scripts to render full page content that traditional scrapers would miss.
Offers conversion of fetched web content to Markdown format, making it easy to integrate the retrieved information into markdown-based applications.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Fetch MCP fetch the latest AI news from techcrunch.com and summarize it"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
中文 | Deutsch | Español | français | 日本語 | 한국어 | Português | Русский
Fetcher MCP
MCP server for fetch web page content using Playwright headless browser.
🌟 Recommended: OllaMan - Powerful Ollama AI Model Manager.
Advantages
JavaScript Support: Unlike traditional web scrapers, Fetcher MCP uses Playwright to execute JavaScript, making it capable of handling dynamic web content and modern web applications.
Intelligent Content Extraction: Built-in Readability algorithm automatically extracts the main content from web pages, removing ads, navigation, and other non-essential elements.
Flexible Output Format: Supports both HTML and Markdown output formats, making it easy to integrate with various downstream applications.
Parallel Processing: The
fetch_urlstool enables concurrent fetching of multiple URLs, significantly improving efficiency for batch operations.Resource Optimization: Automatically blocks unnecessary resources (images, stylesheets, fonts, media) to reduce bandwidth usage and improve performance.
Robust Error Handling: Comprehensive error handling and logging ensure reliable operation even when dealing with problematic web pages.
Configurable Parameters: Fine-grained control over timeouts, content extraction, and output formatting to suit different use cases.
Related MCP server: mcp-playwright-scraper
Quick Start
Run directly with npx:
npx -y fetcher-mcpFirst time setup - install the required browser by running the following command in your terminal:
npx playwright install chromiumHTTP and SSE Transport
Use the --transport=http parameter to start both Streamable HTTP endpoint and SSE endpoint services simultaneously:
npx -y fetcher-mcp --log --transport=http --host=0.0.0.0 --port=3000After startup, the server provides the following endpoints:
/mcp- Streamable HTTP endpoint (modern MCP protocol)/sse- SSE endpoint (legacy MCP protocol)/openapi.json- OpenAPI 3.1 specification for the REST tool API (HTTP mode only)POST /tools/{name}- REST endpoint for each tool (fetch_url,fetch_urls,browser_install)
Clients can choose which method to connect based on their needs. Stdio mode does not serve the HTTP, SSE, or REST routes.
No authentication.
/openapi.jsonandPOST /tools/{name}do not authenticate callers. That includesbrowser_install, which installs a browser on the host. Use these endpoints only on localhost or a trusted internal network. Do not expose them on an untrusted network (for example by binding--host=0.0.0.0where the port is reachable from outside that network).
Debug Mode
Run with the --debug option to show the browser window for debugging:
npx -y fetcher-mcp --debugConfiguration MCP
Configure this MCP server in Claude Desktop:
On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"fetcher": {
"command": "npx",
"args": ["-y", "fetcher-mcp"]
}
}
}Docker Deployment
Running with Docker
docker run -p 3000:3000 ghcr.io/jae-jae/fetcher-mcp:latestDeploying with Docker Compose
Create a docker-compose.yml file:
version: "3.8"
services:
fetcher-mcp:
image: ghcr.io/jae-jae/fetcher-mcp:latest
container_name: fetcher-mcp
restart: unless-stopped
ports:
- "3000:3000"
environment:
- NODE_ENV=production
# Using host network mode on Linux hosts can improve browser access efficiency
# network_mode: "host"
volumes:
# For Playwright, may need to share certain system paths
- /tmp:/tmp
# Health check
healthcheck:
test: ["CMD", "wget", "--spider", "-q", "http://localhost:3000"]
interval: 30s
timeout: 10s
retries: 3Then run:
docker-compose up -dFeatures
fetch_url- Retrieve web page content from a specified URLUses Playwright headless browser to parse JavaScript
Supports intelligent extraction of main content and conversion to Markdown
Supports the following parameters:
url: The URL of the web page to fetch (required parameter)timeout: Page loading timeout in milliseconds, default is 30000 (30 seconds)waitUntil: Specifies when navigation is considered complete, options: 'load', 'domcontentloaded', 'networkidle', 'commit', default is 'load'extractContent: Whether to intelligently extract the main content, default is truemaxLength: Maximum length of returned content (in characters), default is no limitreturnHtml: Whether to return HTML content instead of Markdown, default is falsereturnText: Whether to return plain text (innerTextof the page body) instead of Markdown. Skips Readability extraction and Markdown conversion. Default is false. When omitted, the response is the same Markdown output as beforewaitForNavigation: Whether to wait for additional navigation after initial page load (useful for sites with anti-bot verification), default is falsenavigationTimeout: Maximum time to wait for additional navigation in milliseconds, default is 10000 (10 seconds)disableMedia: Whether to disable media resources (images, stylesheets, fonts, media), default is truedebug: Whether to enable debug mode (showing browser window), overrides the --debug command line flag if specified
fetch_urls- Batch retrieve web page content from multiple URLs in parallelUses multi-tab parallel fetching for improved performance
Returns combined results with clear separation between webpages
Supports the following parameters:
urls: Array of URLs to fetch (required parameter)Other parameters are the same as
fetch_url
browser_install- Install Playwright Chromium browser binary automaticallyInstalls required Chromium browser binary when not available
Automatically suggested when browser installation errors occur
Supports the following parameters:
withDeps: Install system dependencies required by Chromium browser, default is falseforce: Force installation even if Chromium is already installed, default is false
Tips
Handling Special Website Scenarios
Dealing with Anti-Crawler Mechanisms
Wait for Complete Loading: For websites using CAPTCHA, redirects, or other verification mechanisms, include in your prompt:
Please wait for the page to fully loadThis will use the
waitForNavigation: trueparameter.Increase Timeout Duration: For websites that load slowly:
Please set the page loading timeout to 60 secondsThis adjusts both
timeoutandnavigationTimeoutparameters accordingly.
Content Retrieval Adjustments
Preserve Original HTML Structure: When content extraction might fail:
Please preserve the original HTML contentSets
extractContent: falseandreturnHtml: true.Fetch Complete Page Content: When extracted content is too limited:
Please fetch the complete webpage content instead of just the main contentSets
extractContent: false.Return Content as HTML: When HTML format is needed instead of default Markdown:
Please return the content in HTML formatSets
returnHtml: true.Return Visible Text Only: When Markdown markup is unnecessary:
Please return only the visible textSets
returnText: true.
Request targets
fetch_url and fetch_urls accept only http: and https: URLs. Loopback, private, link-local, and cloud-metadata targets are blocked by default, including numeric IP spellings (decimal, hex, octal, and short forms) and names such as localhost and metadata.google.internal. Set FETCHER_MCP_ALLOW_PRIVATE_IPS=true to allow those targets, including blocked hostnames.
A hostname that is not itself on the block list is not looked up before the browser fetches it, and redirects are not checked again. A name that resolves to a private address, or a redirect onto an internal address, can still reach that address.
Debugging and Authentication
Enabling Debug Mode
Dynamic Debug Activation: To display the browser window during a specific fetch operation:
Please enable debug mode for this fetch operationThis sets
debug: trueeven if the server was started without the--debugflag.
Using Custom Cookies for Authentication
Manual Login: To login using your own credentials:
Please run in debug mode so I can manually log in to the websiteSets
debug: trueor uses the--debugflag, keeping the browser window open for manual login.Interacting with Debug Browser: When debug mode is enabled:
The browser window remains open
You can manually log into the website using your credentials
After login is complete, content will be fetched with your authenticated session
Enable Debug for Specific Requests: Even if the server is already running, you can enable debug mode for a specific request:
Please enable debug mode for this authentication stepSets
debug: truefor this specific request only, opening the browser window for manual login.
Development
Install Dependencies
npm installInstall Playwright Browser
Install the browsers needed for Playwright:
npm run install-browserBuild the Server
npm run buildDebugging
Use MCP Inspector for debugging:
npm run inspectorYou can also enable visible browser mode for debugging:
node build/index.js --debugRelated Projects
g-search-mcp: A powerful MCP server for Google search that enables parallel searching with multiple keywords simultaneously. Perfect for batch search operations and data collection.
License
Licensed under the MIT License

Available Tools
3 toolsbrowser_installA
Install Playwright Chromium browser binary. Call this if you get an error about the browser not being installed.
Inputs: withDeps, force.
fetch_urlC
Retrieve web page content from a specified URL
Inputs: url (required), timeout, waitUntil, extractContent, +6 more.
fetch_urlsC
Retrieve web page content from multiple specified URLs
Inputs: urls (required), timeout, waitUntil, extractContent, +6 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
The tools are mostly distinct, with 'fetch_url' and 'fetch_urls' clearly differentiated by single vs. multiple URLs. However, an agent might initially confuse 'fetch_url' and 'fetch_urls' as similar operations, though the descriptions clarify the distinction. 'browser_install' is completely separate in purpose.
All tool names follow a consistent snake_case pattern with clear verb_noun structure: 'browser_install', 'fetch_url', and 'fetch_urls'. The naming is predictable and readable throughout the set.
With only 3 tools, the server feels thin for a web fetching domain, lacking operations like navigation, interaction, or content parsing. While the core fetching is covered, the scope seems limited compared to typical web automation needs.
For a web fetching server, there are significant gaps: no tools for interacting with pages (e.g., clicking, filling forms), extracting specific content, handling JavaScript, or managing sessions. The surface is severely incomplete for common web automation tasks beyond basic URL retrieval.
Maintenance
Related MCP Connectors
Web scraping MCP server: any URL to Markdown or JSON, with JavaScript rendering and batch jobs.
Web scraping MCP server — scrape, extract structured data, screenshot any site with anti-bot bypass.
MCP server (stdio): fetch web pages as clean readable markdown via the AgentForge API
Hosted Web Crawler MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
Related MCP Servers
- FlicenseNot gradedqualityNot gradedmaintenanceAn MCP server for web content extraction that converts HTML pages into clean, LLM-optimized Markdown using Mozilla's Readability. It supports batch processing, intelligent multi-page crawling, and configurable caching while respecting robots.txt standards.48 npm-
- AlicenseNot gradedqualityDmaintenanceAn MCP server that scrapes content from web pages, including JavaScript-heavy sites, and converts it into high-quality Markdown. It leverages Playwright for headless browser automation and Pypandoc for clean content conversion.Apache 2.0
- AlicenseBqualityDmaintenanceAn MCP server for deep research that extracts clean text from web pages using hybrid extraction strategies and compiles findings into structured markdown reports. It provides tools for single and batch URL content extraction with optional Playwright support for JavaScript-heavy sites.4MIT
- AlicenseAqualityDmaintenanceMCP server for fetching web content with browser fingerprint camouflage, converting HTML to clean Markdown to bypass bot detection.11MIT