Skip to main content
Glama
gimp-mcp-studio
by Onru-Labs

Related Servers

Alternatives to gimp-mcp-studio

No user-submitted related servers found.

    Related Servers

    • A
      license
      B
      quality
      C
      maintenance
      Enables AI agents to drive GIMP 3 over MCP, covering layers, selections, painting, text, color adjustments, GEGL filters, raw PDB procedures, and free-form Python inside GIMP, with image previews so the agent can see the result of each step. It installs its bridge plugin automatically and launches or attaches to a running GIMP instance, which stays open across MCP client restarts.
      42
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI assistants to create, paint, edit, inspect, and export images in a running GIMP 3.2 instance via MCP.
      199 PyPI
      GPL 3.0
    • A
      license
      Not graded
      quality
      C
      maintenance
      MCP server that bridges GIMP 3.0 with natural language commands, enabling conversational image editing through Claude Desktop and other MCP clients. Exposes GIMP's full PyGObject API for AI-powered image manipulation.
      286
      GPL 3.0
    • A
      license
      B
      quality
      B
      maintenance
      Enables AI agents to operate GIMP 3 end-to-end: open and inspect images, call every PDB procedure, apply GEGL filters destructively or as layer effects, measure pixels, render before/after/diff comparisons, cut out subjects with AI segmentation, and run multi-step recipes across folders.
      32
      92 PyPI
      5
      Apache 2.0
    • A
      license
      Not graded
      quality
      D
      maintenance
      An MCP server that allows LLMs to control GIMP programmatically, including images, layers, selections, text, transforms, filters, and arbitrary Script-Fu code.
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      Enables scripted image editing with GIMP 3, including cropping, resizing, aspect-ratio fitting, dimension-spec validation, batch processing, and live control of a running GIMP instance.
      18
      1
      MIT

    TDQS

    B3.2/5.0

    Scored across 89 tools

    Disambiguation3/5

    Most tools map to a distinct operation, but several pairs overlap significantly: blur vs apply_gaussian_blur (both Gaussian blur, destructive vs non-destructive), get_image_bitmap vs get_state_snapshot (both return a PNG of the current image), and scale_image vs scale_to_fit vs batch_resize. The generic escape hatches (pdb_run, call_api, gegl_apply_filter) also overlap with the focused effect tools (sharpen, denoise, apply_pixelate), forcing agents to guess which path is intended.

    Naming Consistency4/5

    The set is overwhelmingly snake_case verb_noun (create_layer, select_rectangle, export_image, apply_noise), which is predictable. Deviations are minor: some filters use a bare verb (sharpen, blur, denoise) while siblings use apply_ (apply_emboss, apply_vignette), and the gegl_/pdb_ namespaces put the qualifier before the verb (gegl_list_filters vs list_layers).

    Tool Count2/5

    89 tools is far beyond the practical range and clearly over-scoped; the effect/filter surface alone is split across dozens of near-duplicate entries (adjust_curves, auto_levels, adjust_brightness_contrast vs the GEGL filter tools). While image editing is a broad domain, a large fraction of these tools could be consolidated without losing capability.

    Completeness4/5

    Coverage is unusually thorough: lifecycle (new/open/save/export/close), layers, selections, transforms, drawing, text, filters, batch operations, and named export presets are all present. Gaps remain around layer masks, channels, and paths, but pdb_run/call_api provide a workaround for those.

    Maintenance

    ActivityMaintained
    ResponsivenessOutdated data