Skip to main content
Glama
Sign In
gimp-mcp

gimp-mcp

by mhbxyz
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Gaussian blur

gimp_gaussian_blur
Destructive

Apply a Gaussian blur to a GIMP layer using a pixel radius, optionally with separate X/Y radii, to soften detail or create depth; choose destructive pixel edits or an editable filter.

Instructions

Blur a layer with a Gaussian of standard deviation radius pixels (radius_y defaults to radius). One undo step.

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": {
      "item": "<item>",
      "radius": "<radius>"
    },
    "name": "gimp_gaussian_blur"
  }
}

Input Schema

NameRequiredDescriptionDefault
itemYesItem id (layer, group, mask...) e.g. 'item:5@a1b2c3d4'.
radiusYesStandard deviation in pixels.
radius_yNo
destructiveNotrue: change the layer's pixels (respects the selection). false: add an editable GIMP filter on the layer (pixels untouched, removable, saved in XCF; applied to the whole layer).

Output Schema

NameRequiredDescriptionDefault
itemYes
filterYesId of the editable filter (non-destructive only), verified to exist.
operationYesGEGL/GIMP operation that was applied.
destructiveYesTrue when the layer's pixels were changed.
restricted_to_selectionYesTrue when only the selected area was changed.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already disclose destructiveHint=true; the description adds that the operation costs one undo step. It does not elaborate what pixels or selection are affected, and the non-destructive filter path is left to the schema.

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?

One well-formed sentence front-loads the action and key parameters. There is no filler, and the parenthetical default is efficient.

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?

Given the output schema and annotations, the definition is adequate for invoking the tool, and the schema supplies item and destructive details. It is slightly incomplete because it describes the target as a layer rather than any item and omits the non-destructive mode.

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 75%, with item, radius, and destructive documented in the schema. The description adds that radius is a standard deviation and that radius_y defaults to radius, but says nothing additional about item or destructive.

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?

States a specific verb (blur) and effect (Gaussian, standard deviation radius), so the operation is identifiable. It says 'a layer' though the item parameter also accepts groups and masks, and it does not explicitly differentiate itself from other filter siblings.

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

Usage Guidelines2/5

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

No explicit when-to-use or when-not-to-use guidance is given, no alternatives are named, and the description does not explain when to choose destructive versus editable-filter mode. Usage is only inferable from the verb itself.

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