Scrapes, crawls and searches the web for agents through a REST API, SDKs, CLI and hosted MCP server, returning LLM-ready Markdown, structured fields and company brand data.
Use it now
Keep it with up to 9 other tools you're setting up, then share them all as one link.
Try this first
Ask your assistant, with context.dev connected:
- Scrape to Markdown
Use context.dev to turn any URL: ‹what you need›
- Site Crawl
Use context.dev to crawl a website into one Markdown document per reachable page: ‹what you need›
- Web Search and Answers
Use context.dev to search the web: ‹what you're looking for›
Connect it over MCP
Connect context.dev as an MCP server, following its setup instructions at https://www.context.dev/
Its page: context.dev
Install the CLI
Install it as its own instructions say.
Its page: context.dev
Call the API
Auth An API key from context.dev
Its page: context.dev
Compare
Press Compare to add it to the tray at the bottom of the window, then pick up to 2 others anywhere on the site.
- Access
- APIMCPCLI
- Auth
- API Key
- Skills
- 5
Skills
Scrape to Markdown
Turns any URL into Markdown, HTML, screenshots, images or CSS-parsed fields in one POST /v1/web/scrape request.
Site Crawl
Crawls a website into one Markdown document per reachable page with page and depth limits, or batches up to 25,000 URLs asynchronously.
Web Search and Answers
Searches the web with page content via /v1/web/search, or researches a task and returns JSON with sources via /v1/web/answers.
Brand Data
Retrieves logos, colors, fonts and company metadata by domain, email, company name, ticker or transaction descriptor.
Page Monitors
Watches a page, sitemap or a site's key pages on a schedule and reports changes by signed webhook or by polling runs.