Figma Local MCP

Overview Schema Source Related Servers Discussions Admin

create_scene

Destructive

Create up to 100 native Figma nodes, such as screens or components, in one call using parent/child refs and style-guide IDs. Failed creations are cleaned up.

Instructions

Create up to 100 native nodes in one call (screens or components). refs are unique; parentRef must refer to an earlier FRAME/COMPONENT. Root nodes use parentId or current page. Use style-guide IDs in props. Newly created nodes are cleaned up on failure.

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": {
      "nodes": "<nodes>"
    },
    "name": "create_scene"
  }
}

Input Schema

Name	Required	Description	Default
`nodes`	Yes
`parentId`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.6.4Sep 13, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations declare readOnlyHint=false and destructiveHint=true, and the description adds context beyond them: the 100-node cap, cross-reference ordering rules, and notably the atomicity guarantee ('Newly created nodes are cleaned up on failure'). It does not disclose auth/permission needs or what happens on partial success beyond cleanup.

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?

Four compact sentences, each carrying a distinct rule, with the batch limit and ref semantics front-loaded. No filler or repetition of name/title.

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

Completeness3/5

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

For a destructive batch-creation tool with no output schema, the description covers input rules well but never says what is returned (e.g. created node IDs/refs) so an agent cannot confidently chain follow-up calls. No mention of permissions or rate considerations either.

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 0%, so the description must carry semantic load. It does explain the two trickiest relationships (ref uniqueness, parentRef ordering, parentId for root nodes) and notes that props accept style-guide IDs, but the ~30 props fields are left entirely to the schema's enums and types.

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?

States a specific verb and resource ('Create ... native nodes') plus a distinguishing scope ('up to 100 ... in one call'), which separates it from the single-node sibling create_node. The parenthetical '(screens or components)' clarifies what native nodes are.

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 concrete usage constraints: refs must be unique, parentRef must point to an earlier FRAME/COMPONENT node in the same call, and root nodes use parentId or the current page. It does not explicitly say when to prefer this over create_node or update_node, so guidance is strong but lacks alternative routing.

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