Skip to main content
Glama

Get screenshot

figma_local_get_screenshot
Read-only

Capture a PNG screenshot of a Figma node from a file, FigJam board, or Slides deck using fileKey and nodeId, with size limits and URL, file, or base64 output.

Instructions

Generate a screenshot for a node. Works on design files, FigJam boards and Slides. maxDimension (default 1024) caps the longer edge of the PNG; the metadata includes the rendered width/height and the node's original_width/original_height. By default returns a short-lived URL plus curl instructions, or a local file path when the companion plugin rendered it; both cost far fewer tokens than an inline image. Set enableBase64Response: true only when you cannot fetch URLs or read files. nodeId and fileKey are required; extract them from the URL (node-id=1-2 -> 1:2). For branch URLs use the branchKey as the fileKey.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "fileKey": "<fileKey>",
      "nodeId": "<nodeId>"
    },
    "name": "figma_local_get_screenshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
nodeIdYesThe ID of the node in the Figma document, eg. "123:456" or "123-456". Extract it from the URL's node-id query parameter. Do not pass an empty or guessed nodeId.
fileKeyYesThe key of the Figma file to use. If a URL is provided, extract the file key from it: for https://figma.com/design/:fileKey/:fileName?node-id=1-2 the fileKey is `:fileKey`. For https://figma.com/design/:fileKey/branch/:branchKey/:fileName use the branchKey. A full URL is also accepted.
contentsOnlyNoWhen true, renders the node in isolation, excluding overlapping content. Defaults to false so the screenshot matches the canvas.
maxDimensionNoMaximum pixel size of the longer edge. Defaults to 1024.
clientLanguagesNoA comma separated list of programming languages used by the client in the current context, e.g. `javascript`, `html,css,typescript`. If you do not know, list `unknown`.
clientFrameworksNoA comma separated list of frameworks used by the client in the current context, e.g. `react`, `vue`, `django`. If you do not know, list `unknown`.
enableBase64ResponseNoWhen true, also include the screenshot inline as base64. Defaults to false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior5/5

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

Annotations only declare readOnlyHint and openWorldHint; the description adds substantive behavior: the URL is short-lived, output may instead be a local file path from the companion plugin, both are token-cheap versus inline images, dimensions appear in metadata, and maxDimension defaults to 1024. This is exactly the context annotations cannot convey.

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

Conciseness4/5

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

Front-loaded with purpose and supported file types, then behavior, then parameter guidance; nearly every sentence carries decision-relevant information. Slightly dense with semicolon-chained clauses, but no filler.

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

Completeness5/5

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

With no output schema, the description takes on the burden of explaining return values and does so: URL+curl, local file path, or base64, plus what the accompanying metadata includes. Required-parameter extraction and the branchKey edge case are both covered, so an agent can call this correctly without further exploration.

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

Parameters4/5

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

Schema coverage is 100%, so baseline is 3, but the description adds real meaning: maxDimension caps the longer edge of the PNG (not the bounding box), the metadata carries rendered width/height plus original dimensions, and enableBase64Response is an explicit last resort. It also restates the URL-extraction rule for nodeId/fileKey in an actionable form.

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

Purpose4/5

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

Opens with a specific verb+resource ("Generate a screenshot for a node") and immediately scopes supported surfaces (design files, FigJam, Slides). It does not explicitly contrast itself with siblings such as get_design_context or download_assets, so the differentiation is implicit rather than stated.

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?

Gives clear conditional guidance: default to the URL/curl response, use enableBase64Response only when URLs cannot be fetched or files cannot be read, and how to derive nodeId/fileKey from URLs including branch URLs. Missing an explicit statement of when to choose this over get_design_context or download_assets.

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