PDFs, JavaScript pages and ordinary HTML as clean Markdown. Follows robots.txt per RFC 9309.
Url2md is an MCP integration. PDFs, JavaScript pages and ordinary HTML as clean Markdown. Follows robots.txt per RFC 9309.
The registry lists a streamable-http connection at https://url2md.io/mcp.
The published npm package is @url2md-io/mcp, version 0.1.5. Its declared MCP transport is stdio.
The package declares URL2MD_PRIVATE_KEY_FILE: Path to a file holding the 0x-prefixed private key of a wallet with USDC on Base. Preferred over URL2MD_PRIVATE_KEY: a path is not a secret, and a key on a command line is visible to every process on the machine. One of the two key variables is required.; URL2MD_PRIVATE_KEY: The key itself: 0x followed by 64 hex characters. Use URL2MD_PRIVATE_KEY_FILE instead where you can. One of the two key variables is required.; URL2MD_MAX_PRICE_USD: The most this server will commit for one call, in USD, across every payment round of that call. A tolled page takes two rounds and this ceiling covers both.; URL2MD_MAX_SPEND_USD: The most this server will commit in total for as long as the process runs. Restarting resets it.; URL2MD_BASE_URL: The url2md deployment to call. Must be https (only a loopback address may be plain http), because this is the origin every 402 is checked against.; URL2MD_TIMEOUT_MS: How long to wait for one conversion, in milliseconds. The default covers the service's own worst case: 20 s of fetching plus 55 s of headless render. Do not lower it to 30 s — that is the navigation timeout inside the browser, and on a page that needed a browser your payment has already settled by the time the render starts..
Check the maintainer’s instructions for account access, authentication and the supported client configuration. Once connected, inspect the tools your client receives and try a small task that matches the server’s stated purpose. The registry description does not include a verified, complete tool list.
View the publisher’s registry entry · Project website. This profile uses version 0.1.5 from the registry. Registration identifies the publisher namespace; it does not establish that this is a first-party integration for every service it connects.
Browse related other integrations MCP servers for tools that cover the same kind of work.
| Variable | Description | Required |
|---|---|---|
| URL2MD_PRIVATE_KEY_FILE | Path to a file holding the 0x-prefixed private key of a wallet with USDC on Base. Preferred over URL2MD_PRIVATE_KEY: a path is not a secret, and a key on a command line is visible to every process on the machine. One of the two key variables is required. | Optional |
| URL2MD_PRIVATE_KEY | The key itself: 0x followed by 64 hex characters. Use URL2MD_PRIVATE_KEY_FILE instead where you can. One of the two key variables is required. | Optional |
| URL2MD_MAX_PRICE_USD | The most this server will commit for one call, in USD, across every payment round of that call. A tolled page takes two rounds and this ceiling covers both. | Optional |
| URL2MD_MAX_SPEND_USD | The most this server will commit in total for as long as the process runs. Restarting resets it. | Optional |
| URL2MD_BASE_URL | The url2md deployment to call. Must be https (only a loopback address may be plain http), because this is the origin every 402 is checked against. | Optional |
| URL2MD_TIMEOUT_MS | How long to wait for one conversion, in milliseconds. The default covers the service's own worst case: 20 s of fetching plus 55 s of headless render. Do not lower it to 30 s — that is the navigation timeout inside the browser, and on a page that needed a browser your payment has already settled by the time the render starts. | Optional |
Retrieve public web pages as readable Markdown with the reference Fetch MCP server, including pagination for longer responses.
Use Firecrawl MCP to retrieve website content and extract information for research through Firecrawl’s API-backed web tools.
The original Chromium automation reference server — simple, screenshot-driven browser control.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Automates browsers and APIs, enabling Large Language Models (LLMs) to interact with web pages for tasks like screenshot capture and JavaScript
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.