canonical: https://jentic.com/apis/framejet.dev/framejet # Framejet Screenshot API The Framejet Screenshot API turns any public URL into a PNG or JPEG image. It removes cookie and consent banners, sticky headers, and chat widgets by default, so the capture shows the page's main content. The rendered image is returned for download or embedding. ## For AI agents Capture a public URL as a PNG or JPEG screenshot, with cookie banners, sticky headers, and chat widgets removed by default. Returns the rendered image for download or embedding. ## Scope Does not extract page text, generate PDFs, or crawl linked pages. Use for rendering a public URL into a PNG or JPEG screenshot only. ## Capabilities - Capture a screenshot of any public URL as a PNG or JPEG - Remove cookie and consent banners, sticky headers, and chat widgets from the capture by default - Return the rendered image for download or embedding ## Use cases ### Agent Screenshot Capture An AI agent connected through Jentic can turn any public URL into a clean PNG or JPEG, with cookie banners, sticky headers, and chat widgets removed by default, without a developer wiring the Framejet API by hand. The agent calls the capture operation by intent and receives the rendered image. Example prompt: Capture a PNG screenshot of a public product page and return the image ### Visual Monitoring Teams capture how a page looks over time for QA or compliance records. Framejet renders the current page as a PNG or JPEG with distracting overlays removed, so the captured image reflects the main content. Example prompt: Take a JPEG screenshot of a marketing page and store it for a visual record ### Thumbnail Generation Apps that list external links show a preview image. Framejet converts a URL into an image that can serve as a link thumbnail, cleaned of consent banners and chat widgets. Example prompt: Generate a thumbnail image of a URL for a link preview card ## Key resources - **Screenshots** — Capture a public URL as a PNG or JPEG with cookie banners, sticky headers, and chat widgets removed by default ## AI readiness This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use. - **Score:** 61 / 100 - **Maturity:** AI-Aware - **Dimensions:** - Foundational Compliance: 100 / 100 - Developer Experience & Jentic Compatibility: 63 / 100 - AI-Readiness & Agent Experience: 45 / 100 - Agent Usability: 94 / 100 - Security: 50 / 100 - AI Discoverability: 50 / 100 - **View full report:** https://jentic.com/apis/framejet.dev/framejet/scorecard - **How the score is calculated:** https://docs.jentic.com/reference/api-readiness-framework/overview/ - **More about the dimensions:** https://docs.jentic.com/reference/api-readiness-framework/specification/#dimensional-model-overview ### Score it yourself Every API in the directory is allowlisted, so you can re-score it with no key required. - **Score your own API:** https://jentic.com/scorecard.md - **Scoring CLI agent skill:** https://github.com/jentic/jentic-api-scorecard/blob/main/skills/jentic-api-scorecard/SKILL.md ```sh npx @jentic/api-scorecard-cli score ``` ## Why Jentic - **Setup:** Wiring the Framejet Screenshot API by hand means managing its API key header, setting capture parameters, and handling the returned image bytes yourself. Through Jentic you install once, import Framejet from the API Directory, store the key once, and your agent calls it. - **Permission scoping:** Framejet exposes a single screenshot operation, so a rule can allow exactly that operation and nothing else. You choose the operations the agent may call, and because there is only one, its reach is limited to taking screenshots. - **Credential handling:** Your Framejet key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context. - **Discovery method:** Agents search Jentic by intent such as 'capture a screenshot of a URL', and Jentic returns the Framejet capture operation with its input schema so the agent calls the right endpoint without browsing the reference docs. ## Related APIs - **ApiFlash** — Screenshot API that renders a URL into an image with capture options. - **Urlbox** — Rendering API for screenshots and PDFs of web pages. - **Firecrawl** — Web extraction API that turns pages into structured text and data. ## FAQ ### What authentication does the Framejet Screenshot API use? The Framejet Screenshot API authenticates with an API key sent in the `X-Api-Key` request header, per its OpenAPI spec. Through Jentic the key is stored encrypted by your own Jentic One instance and injected at call time, so it never reaches the agent's context. ### Can I remove cookie banners from a Framejet screenshot? Yes. Framejet removes cookie and consent banners, sticky headers, and chat widgets by default, so the captured PNG or JPEG shows the page's main content. ### Can I limit what my agent is allowed to do with the Framejet Screenshot API? Yes. The API exposes a single screenshot operation, so a rule allows exactly that operation and nothing else, and every call the agent makes is logged. ### Is there a Framejet MCP server? You do not need an MCP server to give your agent the Framejet Screenshot API. Jentic connects it directly from the API Directory: import Framejet, store your key once, and the agent calls its screenshot operation by intent without loading another server's tool definitions into its context. ### What are the rate limits for the Framejet Screenshot API? The OpenAPI spec does not specify numeric rate limits for the Framejet Screenshot API. Check the Framejet documentation at https://framejet.dev for current plan limits. ### How do I capture a screenshot with the Framejet Screenshot API through Jentic? Search Jentic for an intent like 'capture a screenshot', and it returns Framejet's capture operation with its input schema so your agent can pass a URL and get back a PNG or JPEG. To run it on your own infrastructure, install Jentic One from its GitHub repo.