Extract web pages, search the web, and follow bulk or crawl jobs through WellMarked’s local package or hosted OAuth connection.
WellMarked brings web extraction into an MCP conversation. You can read a known page, search for relevant pages, or collect a larger set without passing raw HTML between tools.
Use extract for one URL and search when you need to find sources first. bulk processes a supplied list of URLs; crawl explores a site from a starting page. For asynchronous work, get_job checks progress and wait_for_job waits for the result. get_usage shows the account’s remaining quota.
The local wellmarked-mcp npm package uses stdio and a WELLMARKED_API_KEY. The hosted endpoint at https://mcp.wellmarked.io uses Streamable HTTP and browser-based OAuth sign-in. Choose the connection your client supports; the hosted route does not require copying a local API key.
Crawling, JavaScript rendering, output formats and batch sizes depend on the WellMarked plan. Check those limits before starting a large collection. Inspect each result’s completion and error fields instead of treating an accepted job as a finished crawl.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| extract | Read one URL and return its main content as Markdown with metadata. |
| bulk | Extract a supplied batch of URLs. Batch size depends on the account plan. |
| crawl | Explore a site from a starting URL and return an asynchronous crawl job. |
| search | Find web pages and return their extracted content. Result limits depend on the account plan. |
| get_job | Check the progress and results of a bulk extraction or crawl job. |
| wait_for_job | Wait for a job to finish and return its results. |
| get_usage | Check the account plan, used quota, limit and remaining allowance. |
{
"mcpServers": {
"wellmarked": {
"command": "npx",
"args": [
"-y",
"wellmarked-mcp"
],
"env": {
"WELLMARKED_API_KEY": "YOUR_WELLMARKED_API_KEY"
}
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
Local: an environment that can run npx and a WellMarked API key. Hosted: a remote MCP client with OAuth support and a WellMarked account.
| Variable | Description | Required |
|---|---|---|
| WELLMARKED_API_KEY | API key for the local stdio connection. | Yes |
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.