Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Sahifa API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fsahifa.dev%2Fsahifa" | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fsahifa.dev%2Fsahifa" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with Sahifa API.
Convert a URL or an HTML string into a PDF with page format, landscape, margin, header, and footer options
Capture a screenshot of a web page or raw HTML, full-page or clipped to an element selector
Inject custom CSS or JavaScript and wait for a selector before rendering a PDF
Block ads, trackers, cookie banners, and chat widgets before taking a screenshot
GET STARTED
Render in Saudi Arabia for data-residency needs, with nothing stored after the response
Swap in for PDFShift v3 or ScreenshotOne calls using their compatible request shapes
Patterns agents use Sahifa API for, with concrete tasks.
★ AI agent report export to PDF
An AI agent that drafts a report in HTML needs to hand the user a finished PDF. Through Jentic the agent searches for 'convert HTML to PDF', loads the Sahifa convertPdf operation with its input schema, and posts the HTML as the required source field while the API key is injected at call time. The response is the rendered PDF, produced in Saudi Arabia and not stored by Sahifa.
POST /v3/convert/pdf with source set to the report HTML, format A4, and landscape false, then return the PDF to the user
Saudi data-residency document generation
Banks and fintechs regulated in Saudi Arabia often must keep customer data in the Kingdom. Sahifa processes every request on Oracle Cloud me-jeddah-1 and does not store request content or rendered documents, which supports SAMA Cyber Security Framework and PDPL residency expectations. Statements, contracts, and receipts can be rendered without sending customer HTML abroad.
Render a customer statement by posting its HTML to POST /v3/convert/pdf with a footer showing page numbers and margin set to 20mm
Website screenshot capture
Monitoring dashboards, link previews, and visual QA all need images of live pages. Sahifa's screenshot operation takes a url or html input with viewport_width, viewport_height, full_page, and selector options, and can block ads, trackers, and cookie banners for a clean capture. Clip coordinates and device_scale_factor control exactly what is captured and at what resolution.
Call GET /take with url set to a landing page, full_page true, block_cookie_banners true, and format png
Migrating off PDFShift or ScreenshotOne
Teams already integrated with PDFShift v3 or ScreenshotOne can move rendering into Saudi Arabia without rewriting requests. POST /v3/convert/pdf also accepts PDFShift-style Basic auth with the API key as the password, and /take also accepts the ScreenshotOne-style access_key query parameter. Changing the host is often the main code change.
Point an existing PDFShift v3 convert request at https://api.sahifa.dev/v3/convert/pdf and confirm the PDF renders with the same source payload
4 endpoints — the sahifa api converts html or a web page url into a pdf and captures screenshots of a url or raw html, with every render processed on servers in jeddah, saudi arabia.
METHOD
PATH
DESCRIPTION
/v3/convert/pdf
Convert HTML or a URL to PDF
/take
Screenshot a URL or HTML
/take
Screenshot with a JSON body
/health
Service status
/v3/convert/pdf
Convert HTML or a URL to PDF
/take
Screenshot a URL or HTML
/take
Screenshot with a JSON body
/health
Service status
What agents get from Jentic-routed access to this vendor.
Setup
Wiring Sahifa by hand means choosing between its X-API-Key header, PDFShift-style Basic auth, and the ScreenshotOne access_key parameter, and adding backoff for 408, 429, and 503. Through Jentic you install once, import Sahifa from the API Directory, store the key once, and your agent calls it.
Permission scoping
Sahifa takes the page or HTML to render in the request body or query string, so rules bound which operations your agent may call, not which pages it renders. You choose the operations it may call, so an agent meant for PDF export does not get the screenshot operations unless you add them.
Credential isolation
Your Sahifa API 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.
Intent-based discovery
Agents search Jentic by intent such as 'convert HTML to PDF' or 'take a screenshot of a page', and Jentic returns the matching Sahifa operation with its input schema so the agent sends the right fields without reading the docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Sahifa API through Jentic.
What authentication does the Sahifa API use?
Per its OpenAPI spec, the Sahifa API accepts an API key in the `X-API-Key` header on every render endpoint. For drop-in compatibility, POST /v3/convert/pdf also accepts PDFShift-style Basic auth with your key as the password, and /take also accepts the ScreenshotOne-style `access_key` query parameter. GET /health needs no credential.
Can I screenshot a single element instead of the whole page with the Sahifa API?
Yes. The /take operation accepts a selector parameter to capture one element, or clip_x, clip_y, clip_width, and clip_height to capture a fixed region. Set full_page to true when you want the entire scrollable page instead.
What are the rate limits for the Sahifa API?
According to the spec, each plan has a monthly render allowance (Sandbox keys also have a daily one) reported in the X-Quota-* response headers. A used-up allowance returns 402, and concurrent renders are queued, with a full queue returning 429. Plan figures are at https://sahifa.dev/en/docs/limits.
Is there a Sahifa MCP server?
You don't need an MCP server to give your agent Sahifa. Jentic connects it directly from the API Directory: import it, store your API key once, and your agent calls the PDF and screenshot operations when it needs them, without extra tool definitions sitting in its context.
How do I convert HTML to PDF with the Sahifa API through Jentic?
Search Jentic for 'convert HTML to PDF', load the POST /v3/convert/pdf operation, and execute it with the required source field set to your HTML or a URL, plus options such as format or margin. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Can I limit what my agent is allowed to do with the Sahifa API?
Yes. If your agent only exports PDFs, write a rule that allows POST /v3/convert/pdf and nothing else, so it cannot spend your allowance on screenshots. Each render it requests is logged for review.
Is it safe to retry a failed Sahifa render?
Yes. The spec notes that a render has no side effects and nothing is stored, so repeating a request never creates a duplicate. Retry 408, 429, and 503 responses with an increasing wait, and do not retry other 4xx errors.
For Agents
Render HTML or a URL to PDF, or capture a PNG or other image screenshot of a page, from servers hosted in Saudi Arabia.
Use for: I need to turn an invoice HTML template into a PDF, Convert this web page URL to an A4 landscape PDF, Take a full-page screenshot of a landing page, Capture a screenshot of just one element on a page
Not supported: Does not store documents, fill PDF forms, or send rendered files by email. Use for rendering HTML or URLs to PDF and screenshots only.
The Sahifa API converts HTML or a web page URL into a PDF and captures screenshots of a URL or raw HTML, with every render processed on servers in Jeddah, Saudi Arabia. Its PDF endpoint follows the PDFShift v3 request shape and its screenshot endpoint follows the ScreenshotOne shape, so existing integrations can switch hosts with few changes. PDF options cover page format, margins, headers and footers, page ranges, and custom CSS or JavaScript, while screenshots support full-page capture, element selectors, clipping, dark mode, and blocking of ads, trackers, and cookie banners. Rendered documents are not stored, which supports Saudi data-residency requirements under the PDPL.
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.
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>