Pencil2D Model Context Protocol (MCP) Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DISPLAY | No | X11 display for GUI launching, e.g. :0.0. Used by pencil2d_launch_gui / GUI mode. | |
| PYTHONPATH | No | Path to the source directory containing the pencil2d_mcp module (e.g. /path/to/pencil2d-mcp/src). Needed when running from source via `python3 -m pencil2d_mcp serve`. | |
| PENCIL2D_APPIMAGE | Yes | Path to the Pencil2D Linux AppImage executable (v0.7.2 or newer), made executable with chmod +x. Required for headless rendering and GUI launching. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| pencil2d_inspectA | Inspect a Pencil2D project (.pclx file), returning canvas resolution, FPS, keyframe counts, layers, and palette. |
| pencil2d_createB | Create a new blank Pencil2D project (.pclx) with specified canvas resolution, FPS, and layers. |
| pencil2d_add_frameC | Add or replace a keyframe image in a Pencil2D project bitmap layer. |
| pencil2d_add_frames_batchB | Batch insert multiple animation keyframes into a project from a list or directory in a single operation. |
| pencil2d_add_layerC | Add a new layer (bitmap, vector, sound, or camera) to a Pencil2D project. |
| pencil2d_remove_layerC | Remove a layer from a Pencil2D project by name or ID. |
| pencil2d_add_audioC | Attach a sound clip (WAV/MP3) to a sound layer at a specific keyframe in the animation. |
| pencil2d_set_cameraC | Configure camera keyframe positioning, panning (dx, dy), zooming (scale), and rotation angle. |
| pencil2d_manage_paletteC | Add or update a color swatch in the Pencil2D project palette. |
| pencil2d_create_spritesheetB | Pack animation frames from a Pencil2D project into a single spritesheet image with grid metadata. |
| pencil2d_validateB | Perform deep sanity and health validation on a Pencil2D project, verifying frame continuity, XML integrity, and asset health. |
| pencil2d_extract_framesB | Extract all frame PNG images from a .pclx file into a target directory. |
| pencil2d_exportB | Render a Pencil2D animation project to video (MP4), animated GIF, or image sequence using the Pencil2D AppImage CLI. |
| pencil2d_launch_guiB | Open a project (or a new workspace) inside the Pencil2D GUI for visual animation editing. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 14 tools
Most tools target clearly distinct operations (export, inspect, validate, create, layer/audio/camera edits). The closest overlap is pencil2d_add_frame vs pencil2d_add_frames_batch, but descriptions distinguish single keyframe replace from bulk insert.
Every tool uses the pencil2d_ prefix followed by a snake_case verb_noun pattern (add_frame, remove_layer, set_camera, manage_palette). The convention is uniform throughout all 14 tools.
14 tools is well within the ideal 3-15 range and each maps to a concrete animation workflow step (create, edit, inspect, export, launch). No redundant or filler tools.
Core lifecycle is covered: create, inspect, validate, add frames/layers/audio, and export to multiple formats. Minor gaps exist (no remove/delete frame or update/rename layer aside from removing, no palette removal), but agents can work around them.