Render HTML and CSS to PNG images over HTTP. Send HTML and CSS and get a PNG back.
Glama MCP Gateway
Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.
Full call logging
Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.
Tool access control
Enable or disable individual tools per connector, so you decide what your agents can and cannot do.
Managed credentials
Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.
Usage analytics
See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.
Average 4.1/5 across 2 of 2 tools scored.
Both tools generate visual output, but one renders provided HTML and the other captures a live URL. While both produce images/PDFs, the input method is distinct enough to allow an agent to choose correctly.
Both tool names follow a consistent verb_noun pattern: 'generate-image-from-html' and 'screenshot-url'. The naming clearly indicates the action and the input type, making them predictable and easy to understand.
With only two tools, the set is extremely focused for a server dedicated to converting HTML/URLs to images. Each tool serves a clear, non-overlapping purpose, making the count perfectly appropriate for the narrow scope.
The tool set covers the two primary use cases: rendering static HTML and capturing live URLs. Missing potential features like batch conversion or custom viewport sizes, but the core functionality for an image generation server is well-covered.
generate-image-from-htmlAInspectRender HTML and CSS into a PNG image, or into an A4 vector PDF with format "pdf". Provide complete, self-contained HTML and put styles in an inline block. Remote image URLs load if they are real and publicly accessible; embed generated or local images as base64 data URIs rather than inventing URLs. Returns the rendered image plus a shareable CDN URL; PDF renders return the URL only. Consumes one credit per call.
| Name | Required | Description | Default |
|---|---|---|---|
| css | No | Optional additional CSS to inject into the page. | |
| dpi | No | Scale factor / device pixel ratio (1-4) for higher-resolution output. | |
| html | Yes | The full HTML markup to render. Include CSS in an inline <style> block. Publicly accessible remote image URLs work; use base64 data URIs for images that are not hosted anywhere. | |
| width | No | Viewport width in pixels (1-5000). Defaults to 1920. | |
| format | No | Output format. "png" (default) returns an image sized by width and height. "pdf" returns an A4 portrait vector PDF with selectable, searchable text and automatic pagination; width, height, dpi and fullpage are ignored. Use "pdf" for documents such as invoices, reports, certificates and tickets. Use "png" for social cards, OG images and anything displayed at fixed pixel dimensions. | |
| height | No | Viewport height in pixels (1-5000). Defaults to 1080. | |
| fullpage | No | Capture the full scrollable page instead of just the viewport. | |
| ms_delay | No | Milliseconds to wait before capturing (1-5000), e.g. to let fonts or animations settle. | |
| wait_for_selector | No | Wait until this CSS selector is present before capturing. |
| Name | Required | Description |
|---|---|---|
| url | Yes | Shareable CDN URL of the rendered file, at full resolution. |
| format | Yes | The output format that was rendered. |
| credits_remaining | Yes | Credits left on the plan after this render. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Despite no readOnlyHint/destructiveHint annotations, the description discloses important behavioral traits: credit consumption per call, return values (image + CDN URL for PNG, URL only for PDF), and format-specific parameter ignorance (PDF ignores width/height/dpi/fullpage). This adds context beyond the bare schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Five sentences deliver all critical information: purpose, input requirements, image handling, output details, and credit cost. Each sentence earns its place with no redundancy, and the core purpose is front-loaded: 'Render HTML and CSS into a PNG image, or into an A4 vector PDF...'
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 9 parameters, full schema coverage, and an output schema, the description covers usage guidance, behavioral notes, and constraints. It does not address error cases, rate limits, or output schema details (though output schema exists separately). Still adequately complete for a well-documented tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, and the description adds value by explaining the 'format' parameter's use cases, advising on 'html' content structure (inline CSS, base64 images), and clarifying that 'format: pdf' overrides other sizing parameters. This enhances an already well-described schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states the tool renders HTML and CSS into a PNG image or an A4 vector PDF, using specific verbs and resource targets. It clearly distinguishes between the two output formats and their use cases, which differentiates it from the sibling tool 'screenshot-url' (which captures live URLs).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides concrete guidance: complete self-contained HTML with inline styles, handling of images (public URLs vs base64), and explicit recommendations for when to use PNG (social cards, OG images) vs PDF (invoices, reports). It mentions credit consumption. However, it does not directly contrast with the sibling tool or state when to avoid this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
screenshot-urlAInspectCapture a live web page by URL as a PNG screenshot, or as an A4 vector PDF with format "pdf". Returns the rendered image plus a shareable CDN URL; PDF renders return the URL only. Consumes one credit per call.
| Name | Required | Description | Default |
|---|---|---|---|
| css | No | Optional CSS to inject into the page before capture. | |
| dpi | No | Scale factor / device pixel ratio (1-4) for higher-resolution output. | |
| url | Yes | The fully-qualified URL of the page to capture (https://...). | |
| width | No | Viewport width in pixels (1-5000). Defaults to 1920. | |
| format | No | Output format. "png" (default) returns an image sized by width and height. "pdf" returns the page as an A4 portrait vector PDF with selectable, searchable text and automatic pagination; width, height, dpi, fullpage and selector are ignored. Use "pdf" to archive a page or produce a printable record. Use "png" for anything displayed at fixed pixel dimensions. | |
| height | No | Viewport height in pixels (1-5000). Defaults to 1080. | |
| fullpage | No | Capture the full scrollable page instead of just the viewport. | |
| ms_delay | No | Milliseconds to wait before capturing (1-5000). | |
| selector | No | Capture only the element matching this CSS selector. | |
| wait_for_selector | No | Wait until this CSS selector is present before capturing. |
| Name | Required | Description |
|---|---|---|
| url | Yes | Shareable CDN URL of the rendered file, at full resolution. |
| format | Yes | The output format that was rendered. |
| credits_remaining | Yes | Credits left on the plan after this render. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses important behavioral traits beyond the minimal annotation: credit consumption ('Consumes one credit per call'), return format differences (image+CDN URL vs. URL-only for PDF), and parameter restrictions for PDF renders. No contradictions with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences cover the entire purpose, output, format choice, and cost. Every sentence is essential, and the action is front-loaded. No wasted words or redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with 10 parameters and an output schema, the description covers primary behavior (format differences, credit, return type). It lacks guidance on when to use vs. sibling, error conditions, or rate limits, but overall is adequate given the output schema exists.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description does not add parameter-level meaning beyond what the schema already provides; it focuses on output and credit details. No additional value for parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Capture a live web page by URL as a PNG screenshot, or as an A4 vector PDF' – a specific verb and resource. However, it does not explicitly distinguish from the sibling tool 'generate-image-from-html', which would clarify when each is appropriate.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides internal guidance on PNG vs. PDF usage but offers no context for when to use this tool versus the sibling tool. It does not state prerequisites, limitations, or alternatives, leaving the agent to infer from the name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Claim this connector by publishing a /.well-known/glama.json file on your server's domain with the following structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"maintainers": [{ "email": "your-email@example.com" }]
}The email address must match the email associated with your Glama account. Once published, Glama will automatically detect and verify the file within a few minutes.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
No comments yet. Be the first to start the discussion!