Remote MCP server that captures desktop and mobile website screenshots and returns compact, agent-readable page context for any public URL.
What you can do
Capture desktop, mobile or both screenshots of a website, with successful results cached until TTL expiry.
Render a public page and get visible text, clean Markdown, headings, links, forms, image metadata and interactive elements with bounding boxes.
Retry failed or blocked captures live on the next call, since those are never cached.
When to use it
Useful when an assistant needs to see how a public page looks on desktop and mobile, or needs a lightweight structured reading of a page's text, links and form elements without writing its own browser automation.
Requirements
A remote streamable HTTP endpoint; no package, environment variable or header is declared. The target pages must be publicly reachable, and the client needs network access to the hosted service.
Before you install
Requests go to a third-party hosted service, which fetches the URLs you submit; avoid pointing it at internal, private or authenticated pages. Captures are cached for a TTL, so results may be stale. No OCR, visual inference, crawling, sessions or advanced action selectors are offered.
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/io.github.AgentForge-Labs%2Fsite-screenshot/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.
Capture desktop, mobile, or both screenshots for a website. Successful screenshots are reused from cache until TTL expiry; failed or blocked captures are never cached and are retried live on the next call.
Render a public web page and return a compact Community agent-readable representation: visible text, clean Markdown, headings, links, forms, basic image metadata and interactive elements with bounding boxes. No OCR, visual inference, crawl, sessions or advanced action selectors.
ParametersurlrequireddelayMsviewportmaxTextChars
Version history
2
v0.3.0LatestOct 5, 2026
v0.2.0Sep 16, 2026
Score
75%
75% 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
Documentation15 pts
Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.
License10 pts
Declare a license in the repository or the registry entry.