HTML to Image MCP integration for AI agents.
Connect AI agents to HTML to Image through 2 structured actions, including capture website screenshot and convert html to image. Review authentication, input…
- ACTION CONTRACTS
- 2
- AUTHENTICATION
- API key
- SOURCE STATUS
- Provider-backed
CATALOG SOURCE REVIEWED AUGUST 23, 2026 / ACTION NAMES AND SCHEMAS DERIVED FROM WORKING MACHINES PROVIDER SOURCE
CAPABILITY PROFILE
What the HTML to Image integration exposes
The HTML to Image Agent App exposes 2 provider-backed actions for developer tools and design & media work. Its current contract lets an authorized agent capture a public webpage with html to image and return the generated screenshot url and convert raw html and optional css to an image with html to image and return the generated image url. These operations are called through Working Machines as typed capabilities rather than through browser navigation or copied UI steps.
A connection uses API key. Before execution, the agent can inspect the selected action, its required fields, declared scopes, and expected output contract. Provider credentials remain inside the Working Machines runtime; the calling agent receives the capability and its structured result, not the underlying secret.
For reliable operation, start with the narrowest action that satisfies the task, resolve stable provider identifiers before changing state, and validate the returned object or status after execution. Availability still depends on the connected HTML to Image account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real HTML to Image capabilities.
Showing 2 of 2 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
capture_website_screenshotREVIEWCapture a public webpage with HTML to Image and return the generated screenshot URL.
INPUTS: url / selector / css / width / height
convert_html_to_imageREVIEWConvert raw HTML and optional CSS to an image with HTML to Image and return the generated image URL.
INPUTS: html / css / width / height / fullpage
INPUT CONTRACTS
Know what the action needs before it runs.
capture_website_screenshot
urlREQUIRED- The public webpage URL to capture, including the protocol.
selectorOPTIONAL- A CSS selector for capturing a specific element on the target page.
cssOPTIONAL- Additional CSS to inject before the image is rendered.
widthOPTIONAL- The viewport width in pixels from 1 to 5000.
heightOPTIONAL- The viewport height in pixels from 1 to 5000.
convert_html_to_image
htmlREQUIRED- The HTML content to render. This can include inline CSS and JavaScript.
cssOPTIONAL- Additional CSS to inject before the image is rendered.
widthOPTIONAL- The viewport width in pixels from 1 to 5000.
heightOPTIONAL- The viewport height in pixels from 1 to 5000.
fullpageOPTIONAL- Whether to capture the full page height instead of only the viewport height.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect Capture Website Screenshot
Capture a public webpage with HTML to Image and return the generated screenshot URL. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
capture_website_screenshotVerify with Convert Html To Image
Convert raw HTML and optional CSS to an image with HTML to Image and return the generated image URL. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
convert_html_to_imageSAFETY BOUNDARY
Operate HTML to Image with explicit limits
- Authorize HTML to Image with API key and grant only the provider access required by the selected actions.
- The current action names appear read-oriented, but returned HTML to Image data may still be sensitive and should be minimized before it enters model context.
- Do not infer permission from catalog visibility. Workspace policy, connection identity, and upstream authorization still govern execution.
- No provider scope string is declared on the sampled actions. Verify the connected account's actual permissions in HTML to Image rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the HTML to Image task completed successfully.
CONNECTION MODEL
API key
HTML to Image API key sent in the X-API-Key header.
Working Machines stores provider credentials behind the execution boundary. An agent can use an authorized connection identity, but catalog discovery alone does not reveal OAuth tokens, API keys, or provider secrets.
- READ SIGNALS
- 0
- WRITE SIGNALS
- 0
- HIGH IMPACT
- 0
- REVIEW SIGNALS
- 2
EVIDENCE AND AVAILABILITY
Provider reference
Action names, input fields, authentication types, and counts on this page are generated from the Working Machines provider catalog. Provider behavior, quotas, object semantics, account eligibility, and regional availability remain governed by HTML to Image.