SnapForge

SnapForge screenshot

snapforge_screenshot

Read-only

Capture a screenshot of a public URL or raw HTML as a PNG/JPEG image. Full-page by default. Requires a SnapForge API key (no key? call snapforge_signup first).

Input Schema

TableJSON Schema

Name	Required	Description
`url`	No	Public http/https URL to render. Provide either url or html.
`html`	No	Raw HTML to render instead of a URL (max 2MB). Provide either url or html.
`delay`	No	Extra wait in milliseconds before capture (0–10000)
`scale`	No	Device pixel ratio for high-DPI/retina output (1–3)
`width`	No	Viewport width in pixels (100–3840)
`format`	No	Image format: "png" (default) or "jpeg"
`height`	No	Viewport height in pixels (100–2160)
`quality`	No	JPEG quality 1–100 (ignored for PNG)
`fullPage`	No	Capture the full scrollable page (default true)
`waitUntil`	No	When to consider the page ready: "load" (default) or "networkidle"

Output Schema

TableJSON Schema

Name	Required	Description	Default
`bytes`	Yes	Size of the returned image in bytes
`mimeType`	Yes	Image MIME type, e.g. image/png

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

Changed11 schema fields changedJun 15, 2026

addedInput schema / properties / delay / description

Added value: +"Extra wait in milliseconds before capture (0–10000)"

addedInput schema / properties / format / description

Added value: +"Image format: \"png\" (default) or \"jpeg\""

addedInput schema / properties / fullPage / description

Added value: +"Capture the full scrollable page (default true)"

addedInput schema / properties / height / description

Added value: +"Viewport height in pixels (100–2160)"

changedInput schema / properties / html / description

Previous value: -"Raw HTML to render instead of a URL (max 2MB)"New value: +"Raw HTML to render instead of a URL (max 2MB). Provide either url or html."

addedInput schema / properties / quality / description

Added value: +"JPEG quality 1–100 (ignored for PNG)"

addedInput schema / properties / scale / description

Added value: +"Device pixel ratio for high-DPI/retina output (1–3)"

changedInput schema / properties / url / description

Previous value: -"Public http/https URL to render"New value: +"Public http/https URL to render. Provide either url or html."

addedInput schema / properties / waitUntil / description

Added value: +"When to consider the page ready: \"load\" (default) or \"networkidle\""

addedInput schema / properties / width / description

Added value: +"Viewport width in pixels (100–3840)"

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "bytes": {
+      "description": "Size of the returned image in bytes",
+      "type": "integer"
+    },
+    "mimeType": {
+      "description": "Image MIME type, e.g. image/png",
+      "type": "string"
+    }
+  },
+  "required": [
+    "bytes",
+    "mimeType"
+  ],
+  "type": "object"
+}

First observedJun 14, 2026

TDQS

A4.2/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds that full-page is default and that an API key is required, which are useful behavioral details. It does not disclose error modes or rate limits, but given annotation coverage, the description adds reasonable value.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no fluff, directly conveying the core purpose, default behavior, and a key prerequisite. Every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (10 parameters) and the existence of an output schema, the description provides a good summary. It mentions the API key requirement and full-page default. It could mention output format more, but overall completes the context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all 10 parameters. The description adds minimal extra meaning beyond the high-level purpose and default for fullPage. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool captures screenshots of public URLs or raw HTML as PNG/JPEG images. It specifies 'full-page by default' and distinguishes from siblings (snapforge_markdown, snapforge_pdf, snapforge_signup) which serve different purposes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context on when to use the tool (for screenshots) and a prerequisite (SnapForge API key) with an alternative if missing (call snapforge_signup). It does not explicitly exclude cases, but the purpose is well-defined.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All SnapForge tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.4/5.0

Disambiguation5/5

Each rendering tool targets a distinct output format (Markdown, PDF, screenshot), and the signup tool serves a separate purpose. No overlap or ambiguity.

Naming Consistency5/5

All tool names follow a consistent 'snapforge_<format>' pattern, with the signup tool fitting the same convention. No mixing of styles.

Tool Count5/5

With 4 tools covering rendering to three common formats plus account creation, the count is well-scoped for the server's purpose.

Completeness4/5

The set covers the main rendering outputs users need. A minor gap is the lack of a tool to manage API keys or view usage, but the core workflow is complete.

Resources

Need Help?