A remote MCP server that renders URLs, HTML or Markdown in a real Chrome browser to capture screenshots, PDFs, GIFs or videos, and converts web pages to Markd
What you can do
Render a URL, raw HTML or Markdown in a real Chrome and capture it as an inline image, PDF, GIF or video link, with options to block cookie banners and ads and to set image width and format for full-page captures. Load a URL in a real browser with JavaScript running and return its content as Markdown without scripts and styles, optionally narrowed to a selector such as main or article to save tokens.
When to use it
Useful when an assistant needs a visual capture of a page or rendered HTML, or needs to read a JavaScript-heavy web page as clean Markdown rather than raw HTML.
Requirements
Remote endpoint at shotkit.net over streamable HTTP. Requires a bearer access key from the shotkit key page, sent in the Authorization header as 'Bearer' followed by the key.
Before you install
The Authorization header carries a secret access key; keep it private. Captured pages and submitted HTML or Markdown are sent to a third-party service for rendering, so avoid sensitive content. Captures may consume a paid or metered quota on the shotkit account.
Connect Authorization token credentials. They are stored privately and never shown on public pages.
Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/net.shotkit%2Fmcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.
Render a URL, raw HTML or Markdown in a real Chrome and capture it as an image (returned inline), PDF, GIF or video (returned as a link). Set block_cookie_banners and block_ads for a clean capture. For a full_page capture to read, keep it small with image_width (e.g. 1024) and format jpg.
Parametersurlhtmlcacheclickdelayhoverproxyclip_xclip_yformatstylescookies+82 more
page_to_markdown
Read a web page as Markdown
Load a URL in a real browser (JavaScript runs) and return its content as Markdown, without scripts and styles. Use selector (e.g. main, article) to keep only the part that matters and save tokens.
Parametersurlhtmlcacheclickdelayproxycookiesheadersscriptstimeoutselectorcache_ttl+11 more
Version history
1
v1.0.0LatestOct 16, 2026
Score
72%
72% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
Reached in the last 30 daysRequired25 pts
Auth declaredRequired10 pts
Tools listedRequired15 pts
DescriptionRequired15 pts
Logo10 pts
Publish an icon in the registry entry.
Documentation15 pts
Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.
LicenseNot applicable
A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.