Illustrator MCP

Overview Schema Source Related Servers Discussions Admin

illustrator_execute_task

Destructive

Execute structured Illustrator tasks to create or modify elements, batch shapes, and target items with selectors, dry-run previews, and error reports.

Instructions

Execute a structured task using the Task Protocol v2.1.

CONTRACT: readOnly=False, destructive=True, idempotent=False, openWorld=False

WHEN TO USE:

Creating/modifying elements with declarative ops (element_create, style_set, etc.)
Batch element creation (element_create_batch)
Any operation that benefits from structured error reports and target selectors

EXAMPLES: Smooth curve: illustrator_execute_task(payload={task: "element_create", params: { type: "path", points: [[0,50],[50,0],[100,50],[150,0]], smooth: true, tension: 0.5, fill: {r: 0, g: 150, b: 136}}}) Batch shapes: illustrator_execute_task(payload={task: "element_create_batch", params: { template: {type: "ellipse", rx: 4, ry: 3}, array: {count: 47, startX: 180, spacingX: 15}}}) Grid layout: illustrator_execute_task(payload={task: "element_create_batch", params: { template: {type: "rect", w: 8, h: 8}, array: {count: 50, cols: 10, spacingX: 15, spacingY: 15}}})

TARGET SELECTORS: {type: "selection"} — current selection (default) {type: "layer", layer: "Layer 1"} — all items on layer {type: "query", itemType: "PathItem", pattern: "axis_*"} — pattern match {type: "all", recursive: true} — all items in document {type: "id", ids: ["A1", "A2"]} — stable MCP ID targeting

OPTIONS: dryRun: true — compute actions without applying trace: true — include execution trace in report assignIds: true — write unique IDs to item.note (opt-in)

NOTES:

All task+params must be wrapped in a 'payload' field
For boolean ops use illustrator_path_boolean, not execute_task
For raw SVG path data use illustrator_path_import_svg

Input Schema

TableJSON Schema

Name	Required	Description	Default
`params`	Yes

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 13, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare destructive=True, readOnly=False, idempotent=False, and the CONTRACT line merely restates them (no added credit). Beyond that the description adds real behavioral context: dryRun computes without applying, trace adds an execution trace, assignIds is opt-in, and results come with structured error reports — useful for a mutating tool.

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?

Clearly front-loaded and sectioned (purpose, contract, when-to-use, examples, selectors, options, notes), and the length is defensible for a tool this complex. The CONTRACT line wastes space by duplicating the annotations, and the examples are generous, but overall it is well organized rather than bloated.

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?

An output schema exists, so return-value documentation is not required, and the description covers the declarative entry points, target selection, and safety options. It does not surface the apply_fn/compute_fn JSX escape hatch or preview modes, which an agent only discovers in the schema, but the core call path is adequately described.

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?

At the top level the schema exposes only a single undocumented `params` field (0% coverage per signals), so the description must compensate — and it does, showing the payload wrapping rule, the task/params shape, worked payload examples, target-selector syntax, and the dryRun/trace options. It still omits apply_fn/compute_fn/collect_fn, includes, and preview_mode, which are passed through to the rich nested schema.

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?

The opening line ("Execute a structured task using the Task Protocol v2.1") is somewhat abstract on its own, but WHEN TO USE immediately specifies the concrete job: creating/modifying elements with declarative ops and batch element creation. The NOTES section further distinguishes it from siblings by routing boolean ops to illustrator_path_boolean and raw SVG paths to illustrator_path_import_svg.

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

Usage Guidelines5/5

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

Explicit when-to-use bullets (declarative element ops, batch creation, operations needing structured error reports/target selectors) combined with two explicit when-not-to-use redirections to named sibling tools. Nothing is left to inference about which tool to pick.

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

Deploy Server