GIMP Agent MCP

Let your AI agent edit in GIMP. Keep the layers. See what changed.

Connect Claude, Codex, Cursor or another MCP client to GIMP 3. The agent can work in your open window, inspect the result, refine an edit and save an XCF you can keep working on. Headless mode runs the same workflows over folders of images.

See it working

Watch the 20-second MP4 · Open the editable XCF · Reproduce the MCP session

This is a captured-step walkthrough of the real GIMP window, with pauses shortened. Three text layers are changed through MCP in one batch. One Ctrl+Z restores all three; Ctrl+Y brings them back. The text, artwork and background stay on separate named layers. This demonstrates actual tool execution, not a claim that every model will follow the same plan from a prompt.

Try asking

“Change the headline and supporting text in this card. Keep them as text layers, group the edits into one undo step, and show me the result before exporting.”

“Make this transparent artwork into a Telegram sticker with a white outline and shadow. Save a 512 × 512 PNG.”

“Pack these equal-sized PNG frames into a sprite sheet. Keep an XCF master, write the atlas JSON and verify the exported pixels against the originals.”

The included skills guide layered artwork, sprite sheets and batch jobs. They tell the agent to inspect and measure the actual output before calling a job complete.

Install

You need GIMP 3.2.x, Python 3.11+, uv and an MCP client. GIMP must be installed on the same machine as the server. Start GIMP once so its user profile exists.

uvx gimp-agent-mcp install-plugin
uvx gimp-agent-mcp install-skills
uvx gimp-agent-mcp doctor

Restart GIMP after installing or upgrading the bridge. In your open GIMP window, choose Filters → Development → Start Agent Bridge.

Add this configuration to your client's MCP settings:

{
  "mcpServers": {
    "gimp": {
      "command": "uvx",
      "args": ["gimp-agent-mcp", "serve"]
    }
  }
}

For Claude Code:

claude mcp add gimp -- uvx gimp-agent-mcp serve

Claude Code can also install the server and skills as a plugin; see skills installation. For AI background removal, install the optional model runtime with uvx --from "gimp-agent-mcp[segmentation]" gimp-agent-mcp serve (use the same arguments in your MCP config). The first use downloads a model; image processing stays local.

Working from source? Run uv sync --extra dev, then uv run gimp-agent-mcp install-plugin. Configure the server as uv run --no-sync --directory /absolute/path/to/repo gimp-agent-mcp serve. --no-sync avoids Windows executable-lock errors when another server is running.

Work in your window, or run a batch

• Your existing window: start the bridge from the menu. Continue editing the same document by hand.
• A shortcut: uvx gimp-agent-mcp shortcut creates a launcher that starts GIMP with the bridge enabled.
• Agent-launched: gimp_launch(mode="gui") opens GIMP; mode="headless" runs without a window.

Use gimp_context(image_id) to read selected layers and selection bounds. With several images open, the agent must choose an explicit image ID; GIMP's public API does not reliably expose which document has keyboard focus. gimp_context(..., present=true) can bring a specified document forward. If multiple bridges run, gimp_status follows the newest bridge file; isolate test profiles when a user session is active.

What makes this useful

Other GIMP MCP projects also provide TCP bridges and visual feedback. This project's emphasis is editable output, measurement, grouped edits and reproducible validation. Generic API access is broad, but does not guarantee that every GIMP procedure or GEGL operation works with every argument combination.

Tools (36)

Images and items use integer IDs. Colours accept hex, common names, CSS RGB strings or component arrays; enums use nicks returned by the describe tools. Call gimp_help("batch") for grouped-edit examples. gimp_run_python may be disabled, reducing the tool count by one.

Recipes

Recipe arguments and examples · Skills

Tested scope and limits

Version 0.4.0, beta. Windows GIMP 3.2.4 and Linux GIMP 3.2.2 (Ubuntu 26.04) pass the real-GIMP smoke suite and targeted capability proof. macOS remains unverified. GIMP 2.10 is unsupported; earlier 3.x releases are not part of the current test matrix.

• gimp_edit_batch accepts bounded layer, text, selection, path, mask and filter edits. It does not keep a transaction open between separate agent calls or automatically roll back a failed batch. The human uses GIMP's Undo/Redo; there is no invented programmatic undo endpoint.
• Some GEGL source operations, including linear gradients, are not drawable filters. Use the PDB gradient-fill procedure instead. Vector warp/liquify parity is not claimed.
• Sprite packing currently takes equal-sized PNG files, without padding or direct open-layer input. It does not align animation or pack mixed-size rectangles.
• Long filters are synchronous. Mid-filter cancellation, progress reporting and render overlays remain follow-up work.

Verify your setup

uvx gimp-agent-mcp smoke
# From the source checkout:
uv run pytest
uv run python scripts/capability_proof.py /path/to/proof-output

CI checks Linux and Windows Python, and separate jobs exercise real GIMP. Release publication depends on both real-GIMP workflows passing. The capability proof measures curves, gradients and brush output and checks batch recovery, document boundaries, nested previews and snapshot cleanup. It is targeted regression evidence, not exhaustive competitor parity. See validation details.

Architecture and trust

MCP client → stdio server → authenticated loopback TCP → plug-in inside GIMP

The plug-in runs operations on its GLib main loop, without worker threads. It uses a per-install token and only binds to 127.0.0.1. PDB calls, recipes and Python can execute code with your user permissions: connect only trusted clients. Disabling gimp_run_python is not a sandbox. Security · Architecture

Clean-room implementation under Apache-2.0; no code copied from other GIMP MCP projects. Roadmap · Changelog · Report a bug