Skip to main content
Glama
alisaitteke

Photoshop MCP Server

by alisaitteke
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

photoshop_undo

Destructive

Revert the last edit or a short run of edits in the active Photoshop document by stepping back through history. Reversible with redo while those states remain.

Instructions

Step the active document back through history (Ctrl/Cmd+Z). Each call moves the active history state earlier by steps (default 1).

Users often say: undo, geri al, ctrl z, cmd z, son değişikliği geri al. Use when: reverting the last edit or a short run of edits. Do NOT use when: you need to reapply an undone edit — use photoshop_redo. Do NOT use when: you only need to inspect the stack — use photoshop_get_history.

Returns: text confirmation with the step count. Preconditions: active document with history. Side effects: restores an earlier state and drops the current one onto the redo stack. Not idempotent — a second call undoes further. Reversible with photoshop_redo while those states remain.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
stepsNoNumber of steps to undo (default: 1)
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.

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"
+]
    • addedInput schema / required
      Added value: +[
+  "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 flag destructive=true and idempotent=false, but the description goes further: it discloses preconditions (active document with history), the redo-stack side effect, non-idempotency across repeat calls, and reversibility via photoshop_redo. This is rich behavioral context beyond the structured hints.

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?

Front-loaded with the core action, then cleanly segmented into aliases, use/don't-use, returns, and preconditions/side-effects. Every line is functional; the alias list aids matching rather than padding.

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 still states the return ('text confirmation with the step count'), and it covers preconditions, side effects, and reversibility. Nothing an agent needs to call this correctly is missing.

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 document_id's null/0/stale-id semantics are already fully documented. The description still adds value by explaining what `steps` actually does ('moves the active history state earlier by steps'), though it largely restates the default of 1.

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+resource: stepping the active document back through its history, with the concrete Ctrl/Cmd+Z mapping. It is unmistakably distinct from siblings like photoshop_redo and photoshop_get_history, which it names.

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?

Provides explicit 'Use when' guidance plus two 'Do NOT use when' clauses that name the correct alternatives (photoshop_redo for reapplying, photoshop_get_history for inspecting). No inference is left to the agent.

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