Skip to main content
Glama
alisaitteke

Photoshop MCP Server

by alisaitteke
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

photoshop_play_action

Destructive

Automate repetitive Photoshop edits by replaying a named action from an action set, executing its recorded steps.

Instructions

Play a named action from a named action set in the Actions panel. The action runs whatever steps were recorded; this tool does not limit them.

Use when: the user names an existing action and action set to replay. Do NOT use when: no recorded action exists — use a photoshop_recipe_* tool or an atomic photoshop_* tool. Do NOT use when: you need to run arbitrary JSX — use photoshop_execute_script.

Returns: the action result text. Preconditions: actionName and actionSetName must match the Actions panel; an open document if the action expects one. Side effects: whatever the action recorded (it may delete layers, change pixels, or save). photoshop_undo reverts only the history steps the action left behind.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actionNameYesName of the action to play
document_idYesPhotoshop document id from photoshop_get_state / photoshop_list_documents. Send null or 0 to use the active document. A positive number activates that document before the tool runs. When no document is open, a stale id does not block the call.
actionSetNameYesName of the action set containing the action

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.7.33
    • changedInput schema / properties / document_id / description
      Previous value: -"Photoshop document id from photoshop_get_state / photoshop_list_documents. Send null to use the active document. A number activates that document before the tool runs."New value: +"Photoshop document id from photoshop_get_state / photoshop_list_documents. Send null or 0 to use the active document. A positive number activates that document before the tool runs. When no document is open, a stale id does not block the call."
  2. Changed4 schema fields changedv1.7.32
    • addedInput schema / additionalProperties
      Added value: +false
    • changedInput schema / properties / document_id / description
      Previous value: -"Optional Photoshop document id from photoshop_get_state / photoshop_list_documents. When set, the tool activates that document before running so a UI tab switch cannot retarget the edit."New value: +"Photoshop document id from photoshop_get_state / photoshop_list_documents. Send null to use the active document. A number activates that document before the tool runs."
    • changedInput schema / properties / document_id / type
      Previous value: -"number"New value: +[
+  "number",
+  "null"
+]
    • changedInput schema / required
      Previous value: -[
-  "actionName",
-  "actionSetName"
-]New value: +[
+  "actionName",
+  "actionSetName",
+  "document_id"
+]
  3. First observedv0.1.0

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already declare destructiveHint=true and idempotentHint=false, but the description goes far beyond: it warns that the action may delete layers, change pixels, or save, states that undo only reverts the history steps the action left behind, and lists preconditions around action/action set names and open documents.

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?

The definition is front-loaded with the core action, then uses labeled sections for usage, returns, preconditions, and side effects. Every sentence carries operational value, and nothing is padded.

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?

For a destructive, free-form action player with no output schema, the description is complete: it explains return text, preconditions, side effects, and undo limitations. An agent has everything needed to call it safely and correctly.

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 the baseline is 3, but the description adds useful parameter-related preconditions: actionName and actionSetName must match the Actions panel, and a document is required if the action expects one. This meaningfully supplements the schema without needing to restate field descriptions.

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 states a specific verb and resource: 'Play a named action from a named action set in the Actions panel.' It also clarifies scope ('runs whatever steps were recorded; this tool does not limit them'), which distinguishes it from atomic tools and script execution siblings.

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 'Use when' and two 'Do NOT use when' clauses name the exact alternatives: photoshop_recipe_* / atomic photoshop_* tools for missing actions, and photoshop_execute_script for arbitrary JSX. This is precisely the routing guidance an agent needs.

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

Deploy Server

Other Tools