MCP App Store
by KeenEthics
HTML/CSS to Image API icon

HTML/CSS to Image API MCP Server for ChatGPT

By Code Happy, LLC

Overview

The HTML/CSS to Image MCP server lets AI assistants create production-ready images, website screenshots, and PDFs through natural-language instructions. Use it to: - Render HTML and CSS into PNG, JPG, WebP, or PDF - Capture screenshots of public URLs - Generate images from reusable templates and variables - Create batches of multiple image variations - Create, update, list, and version image templates - Configure viewport size, device scale, selectors, render delays, and other rendering options

How to connect

  1. ChatGPT: Open the HTML/CSS to Image API listing in the ChatGPT app directory and choose Connect. ChatGPT listing HTML/CSS to Image API exposes 36 tools here.

Tools

check_usage

ChatGPT
Returns the connected organization's current image-credit usage in item: images_used, images_allowed, overages_enabled, and next_reset. Use this to check capacity before rendering or explain a usage-limit error. When images_allowed is greater than zero, included credits remaining are max(0, images_allowed - images_used); overages_enabled indicates whether usage beyond that allowance is permitted.

create_batch_images

ChatGPT
Creates multiple image assets from shared default_options and individual variations. Call get_max_batch_size first and keep the number of variations within the returned plan limit; a limit of 0 requires individual image calls. Each variation overrides corresponding defaults. Returns per-image asset IDs, URLs, and format information in item. Use the individual creation tools when only one image or an inline preview is needed.

create_batch_templated_images

ChatGPT
Creates multiple images from one or more saved templates. Set template_id in default_options or each variation; resolve unknown IDs with list_templates. Call get_max_batch_size first and keep variations within the plan limit. Shared template_values merge recursively with each variation; arrays, scalars and explicit null replace defaults. Overriding a template_id resets the inherited version unless a version is also supplied. Identical images reuse existing assets. Returns IDs, URLs and format information in response order. Use create_templated_image for a single image or inline preview.

create_htmlcss_recording

ChatGPT
Creates a video or animated GIF from HTML, CSS, and JavaScript. Returns id, status_url, and recording_url in item before capture completes. Use get_recording_status to check readiness.

create_image

ChatGPT
Creates an image from supplied HTML and CSS. Use this for a single graphic, card, or document; use create_url_image to capture an existing web page, or create_template to save a reusable design. Set content.selector to crop to a specific element. Returns asset ID, URL, and format information in item. Set include_image_data only when an inline preview is needed.

create_og_config

ChatGPT
Saves a new Open Graph (social preview) image configuration for pages on an HTTPS website. Use config_type: html_css to render source pages with default rendering options, or templated to render an existing template using values extracted from page metadata. Returns the saved configuration in item, including id for later management and domain_id for its Open Graph image URLs. Requires a plan that supports OG configurations. Use create_url_image for a single page screenshot and update_og_config to change an existing configuration.

create_template

ChatGPT
Saves a reusable HTML/CSS image template for rendering multiple images with different values. Put Handlebars placeholders such as {{title}} in the HTML; substitutions are evaluated in HTML only. Returns item.template_id and item.template_version. Call create_templated_image with that ID and template_values to render an image. Use create_image for a single image from supplied HTML/CSS, or update_template to revise an existing template.

create_templated_image

ChatGPT
Creates an image from a saved template using template_values for its variable substitutions. Use a known template_id directly, or call list_templates to find one by name. Omit version to use the latest version. Returns asset ID, URL, and format information in item; include_image_data requests an inline preview. Use create_template to save a new reusable design before rendering it.

create_url_image

ChatGPT
Creates a screenshot of an existing web page at content.url. Rendering loads the page and its resources in a browser and executes its JavaScript. Set content.full_screen for the entire scrollable page, or content.selector to capture a particular element. Returns asset ID, URL, and format information in item; include_image_data requests an eager inline preview. Use create_image when supplying HTML/CSS directly, or create_templated_image when rendering a saved template.

create_url_recording

ChatGPT
Records a website as MP4, WebM, or animated GIF, with optional scrolling and interactions. Returns id, status_url, and recording_url in item before capture completes. Use get_recording_status to check readiness.

delete_og_config

ChatGPT
Deletes an Open Graph image configuration. Returns true on success.

delete_proxy

ChatGPT
Deletes an organization's proxy so it can no longer be used for rendering. Repeated deletion of the same proxy succeeds. Returns true on success.

delete_recording

ChatGPT
Deletes a recording and removes its HCTI-hosted media. The recording can no longer be retrieved or rendered. Files already saved to customer storage are not deleted. Repeating deletion of the same owned recording succeeds. Returns true when deletion is accepted.

delete_storage_destination

ChatGPT
Deletes the storage destination configuration and its stored credentials. Does not delete the bucket or files already stored there. Repeated deletion succeeds. Returns true on success.

delete_webhook

ChatGPT
Deletes a webhook. Deliveries that have not been sent yet are not sent. Repeated deletion succeeds. Returns true on success.

get_aws_storage_external_id

ChatGPT
Returns the current organization's external_id and HCTI writer_role_arn. Use external_id as sts:ExternalId and writer_role_arn as Principal.AWS in the AWS IAM role trust policy when configuring S3 storage. No storage destination ID is required.

get_max_batch_size

ChatGPT
Get the maximum number of images that can be created in a single batch according to the user's plan. Returns 0 when batching is not supported; create images individually instead.

get_og_config

ChatGPT
Retrieves one Open Graph image configuration by ID. Returns its mode, enabled state, domain_id, and mode-specific rendering options or template settings in item. Use this before update_og_config to preserve existing settings; use list_og_configs to discover an ID.

get_proxy

ChatGPT
Gets an organization's proxy configuration, including whether it is enabled and whether authentication is configured. The configured username is returned; passwords are never returned.

get_recording

ChatGPT
Retrieves saved source, actions, output settings, and recording metadata without rendering or downloading media. Use get_recording_status for progress checks.

get_recording_status

ChatGPT
Returns current status, attempt count, errors, stored duration, and media URL. Does not start rendering. Use store_recording to start a deferred recording.

get_storage_destination

ChatGPT
Gets a storage destination's configuration, enabled state, and most recent connection test result. Secret access keys are never returned.

get_webhook

ChatGPT
Gets a webhook's endpoint, subscribed events, parameters, signing setting, and enabled state. Secret parameter values and the signing secret are never returned.

get_webhook_event

ChatGPT
Gets one webhook event: its payload, and each destination's delivery status and attempts with HTTP results. data is null and payload_withheld is true when you can't read the event's resource.

list_og_configs

ChatGPT
Lists the organization's Open Graph configurations in descending creation order, including disabled configurations. Results are in item.data. Pass item.pagination.next_page_start as page_start to continue; a null cursor marks the last page.

list_proxies

ChatGPT
Lists the organization's proxies, including disabled proxies. Returns configuration without passwords in item.data. Use an entry's id as proxy_id in image or template requests. Pass item.pagination.next_page_start as page_start to continue; a null cursor marks the last page.

list_recordings

ChatGPT
Lists the organization's non-deleted recordings, newest first, in item.recordings. Returns next_page_token and has_next_page for pagination. Use get_recording_status for current progress.

list_storage_destinations

ChatGPT
Lists the organization's storage destinations, including disabled destinations. Returns configuration without secret access keys in item.data. Use an entry's id as storage_destination_id in image or template requests. Pass item.pagination.next_page_start as page_start to continue; a null cursor marks the last page.

list_template_versions

ChatGPT
Lists saved versions of one template, newest first, with their content and rendering settings in data. Use this to inspect a template before updating it or select an older version for create_templated_image. Pass pagination.next_page_start as max_version to continue; stop when data is empty or the cursor is null.

list_templates

ChatGPT
Lists the connected organization's templates with their latest versions, newest first. Use this to find a template by name and inspect its content and rendering settings. Results are in data; pass an entry's id as template_id to create_templated_image. For more results, pass pagination.next_page_start as max_version. Stop when data is empty or the cursor is null.

list_webhooks

ChatGPT
Lists the organization's webhooks, including disabled webhooks. Returns endpoints, subscribed events, and parameters in item.data; secret parameter values and signing secrets are never returned. Pass item.pagination.next_page_start as page_start to continue; a null cursor marks the last page.

send_webhook_test_event

ChatGPT
Sends a webhook_test delivery to an enabled webhook's endpoint, signed and with its parameters like any other delivery. Each webhook accepts one test every 30 seconds, including the test sent when it is created or its delivery settings change. Returns the event ID; check delivery status with get_webhook_event.

store_recording

ChatGPT
Starts a deferred recording or stores it using its configured destination. Reuses stored media without resetting attempts. Returns the latest status, which may still be processing.

submit_feedback

ChatGPT
Sends feedback to the HCTI team about HTML/CSS to Image, its API, or its MCP tools. Use this to report bugs or unexpected rendering results, request features, describe confusing behavior or documentation, and suggest improvements. Include relevant context such as what you tried, what you expected, and what happened. If the user did not ask you to send feedback, ask them before submitting. Do not include API keys, credentials, tokens, or personal or confidential data. Returns a confirmation message and feedback ID.

update_og_config

ChatGPT
Replaces an existing Open Graph image configuration and returns the saved configuration in item. Call get_og_config first to inspect settings that should be preserved; omitted optional settings are cleared or reset to defaults. Supply the complete configuration for the chosen config_type. Changes affect subsequent image requests using this configuration. After a plan downgrade, only disabling is accepted and other changes are ignored.

update_template

ChatGPT
Updates an existing HTML/CSS image template. Replaces its latest version when that version has not been rendered; otherwise creates a new version. Returns item.template_id and item.template_version. Call create_templated_image with the returned ID and version to render the updated design. Use list_template_versions to inspect existing content before replacing it.

Capabilities

Writes

Example Prompts

Click any prompt to copy it.

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/html-css-to-image-api"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/html-css-to-image-api)