Which integrations are available for this server?

Enables creation of placeholder sprites, UI elements, health bars, and spritesheets for GameMaker game development. Enables creation of placeholder sprites, UI elements, health bars, and spritesheets for Unity game development. Enables creation of placeholder sprites, UI elements, health bars, and spritesheets for Unreal Engine game development.

How do I use 2d-assets-mcp?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@2d-assets-mcp Generate a 64x64 gold coin with radial gradient and 'COIN' label." That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

2d-assets-mcp

by crony-io

Overview Schema Related Servers Score Discussions

TypeScript

Local

2d-assets-mcp

Design your game's feel before you design its art.

npm version npm downloads License: MIT TypeScript

Just like wireframing helps designers visualize user flows before start sketching, 2d-assets-mcp helps game developers visualize timing, frames-per-second (FPS), collision boundaries, and UI layouts before spending hours on final artwork.

This MCP (Model Context Protocol) server lets any AI assistant (Antigravity, Claude Code, Codex, Devin, or any of them as long as it's MCP-compatible) generate advanced 2D mock/placeholder assets in PNG format right into your project folder. Save time and prototype faster, nail your game's feel with 2d-assets-mcp, and then replace the mockups with original artwork when you are ready.

This MCP is engine-agnostic and it works flawlessly with any game engine that supports PNG import, like:

Godot
Unity
Unreal Engine
GameMaker
Construct
RPG Maker
And many more!

Save time and create placeholder health bars, spritesheets, and whatever UI elements you can think of with full support for gradients, patterns, transparency, text rotation, and auto-scaling, all via chat and without ever opening an image editor. The idea behind it is to help you test and iterate how your game feels first by prototiping scale, jump arcs, and animation timing without waiting on final art assets, and also with zero friction: Need that placeholder button to be 20% larger? Just ask your AI client to regenerate it.

TIP

2d-assets-mcp has AI-Friendly Metadata→ meaning each generated PNG embeds rich JSON metadata (dimensions, color, shape, gradient properties, pattern details, text properties, stroke properties, description) directly in its EXIF data, so AI models without vision can still understand what an asset contains.

Generated Assets Examples

Here are some example assets generated by this MCP server:

Character Sprites & Animations

Hero Idle Animation (8 frames, 512x64)

Hero Idle

8-frame idle animation spritesheet with effect

UI Elements

Attack Button (128×48)

Attack Button

Button with red gradient, rounded corners, and "ATTACK" label

Health Bar (200×24)

Health Bar

Health bar at 75% fill with green color and dark gray track

Game Items

Gold Coin (32×32)

Gold Coin

Circular coin with radial gradient, dot pattern overlay, and "COIN" label

Grass and water

Trees

Animation Spritesheets

Fire animation (4 frames, 192x48)

Fire animation

4-frame spritesheet

Security Considerations

Asset Content

Generated assets are pure placeholder graphics and they do not contain malicious code.
Embedded metadata is plain JSON and is not executable.

Because this MCP server writes files directly to your machine to save you time, please review these security best practices:

File System Access

The server can write files to any path specified by the AI assistant.
Recommendation: Configure your AI client to restrict access strictly to your game's project directories.
Warning: Be cautious when asking the AI to generate assets outside your project directory.

Path Traversal

This server validates paths, but you should always be aware of potential path traversal attempts when dealing with MCP servers, and review generated file paths before confirming operations.

Overall Best Practices

Use absolute paths in configurations to prevent ambiguity.
Restrict AI access to your game project directory only.
Review generated assets before committing to version control.
Keep your Node.js dependencies updated.

Related MCP server: ssyubix-pixelart-mcp

Core Features

Instant asset generation: one tool call, one PNG, full visual configuration.
Spritesheet & Batch mode: generate multiple frames or composite them into a single animation-strip spritesheet in one request.
Rich visuals: support for solid fills, linear/radial gradients, stripe/dot/grid pattern overlays, rounded corners, circles, opacity, and stroke control.
Dynamic UI Elements: create partially filled progress/health bars using fillPercent and trackColor for partially-filled assets.
Auto-scaling labels: text automatically scales to fit the asset, or you can override it with explicit fontSize if needed.
Non-vision AI friendly: embedded JSON metadata readable back via read_image_metadata, without loading image pixels, ideal for non-vision AI workflows.
Smart naming: output files are automatically named with their dimensions (e.g. player_idle_128x128.png) to help models with no vision know the dimensions when using the asset.

Tools Reference

This MCP server equips your AI with 3 tools to generate and read 2D asset metadata.

1. `generate_mock_asset`

Generates a single PNG asset and writes it to the disk. It supports gradients, patterns, transparency, text rotation, and embedded metadata.

Required parameters

Parameter	Type	Description
`filename`	`string`	Output filename, e.g. `player_idle.png`
`directory`	`string`	Absolute path to the output folder (created if missing)
`text`	`string`	Label rendered on the asset
`color`	`string`	Background hex color, e.g. `#FF5733`

Optional parameters: shape & size

Parameter	Type	Default	Description
`width`	`number`	`128`	Width in pixels
`height`	`number`	`128`	Height in pixels
`shape`	`rectangle` \| `rounded-rectangle` \| `circle`	`rectangle`	Geometric shape
`opacity`	`number` `0–1`	`1.0`	Background opacity
`strokeColor`	`string`	`#000000`	Border hex color
`strokeWidth`	`number`	`4`	Border width in px; `0` removes the border

Optional parameters: fill & gradient

Parameter	Type	Default	Description
`fillMode`	`solid` \| `linear-gradient` \| `radial-gradient`	`solid`	Background fill type
`secondaryColor`	`string`	auto-derived	Second gradient stop; auto-shaded from `color` if omitted
`gradientAngle`	`number`	`45`	Angle in degrees for linear gradients (ignored for radial)

Optional parameters: progress/health bar

Parameter	Type	Default	Description
`fillPercent`	`number` `0–100`	`100`	How much of the asset is filled (left to right)
`trackColor`	`string`	—	Color of the unfilled portion; transparent if omitted

Optional parameters: pattern overlay

Parameter	Type	Default	Description
`pattern`	`none` \| `stripes` \| `dots` \| `grid`	`none`	Pattern overlay type
`patternColor`	`string`	auto-derived	Pattern color; contrast-auto if omitted
`patternOpacity`	`number` `0–1`	`0.18`	Pattern overlay opacity
`patternScale`	`number` `≥2`	`16`	Pattern tile size in pixels

Optional parameters: text

Parameter	Type	Default	Description
`textPosition`	`center` \| `top` \| `bottom`	`center`	Vertical text alignment
`fontSize`	`number`	auto-scaled	Explicit font size in px; auto-fits if omitted
`textRotation`	`number`	`0`	Text rotation angle in degrees
`textColor`	`string`	auto-contrasting	Hex color for text; auto-calculated if omitted

Optional parameters: metadata

Parameter	Type	Default	Description
`assetDescription`	`string`	—	Human-readable description embedded in the PNG EXIF for non-vision AI context

NOTE

Output filename format

The server automatically appends the dimensions to the filename before writing:

player_idle.png  →  player_idle_128x128.png

2. `generate_mock_asset_batch`

Generates multiple assets in one request. Supports individual PNGs or a single composed spritesheet.

Required parameters

Parameter	Type	Description
`assets`	`AssetConfig[]`	Array of asset configs (same fields as `generate_mock_asset`)

Optional parameters

Parameter	Type	Default	Description
`spritesheetMode`	`individual` \ `spritesheet`	`spritesheet`	`individual` writes separate PNGs; `spritesheet` composes a single PNG
`sheetFilename`	`string`	`spritesheet.png`	Output filename for the composed spritesheet
`sheetDirectory`	`string`	first asset's directory	Output directory for the spritesheet
`sheetMargin`	`number`	`8`	Outer padding around the spritesheet in pixels
`sheetSpacing`	`number`	`8`	Gap between animation frames in pixels

NOTE

Spritesheet layout

All assets are arranged in a single row (traditional animation strip). Each frame cell is sized to the largest asset in the batch; smaller assets are centered within their cell. The output filename includes the total sheet dimensions:

player_run.png  →  player_run_648x136.png

3. `read_image_metadata`

Reads the JSON metadata embedded in the EXIF ImageDescription field of any PNG generated by this server. Useful for AI models that lack vision, because they can understand what an asset contains without decoding the image.

Required parameters

Parameter	Type	Description
`filepath`	`string`	Absolute path to the PNG file

How metadata embedding works

Metadata is stored as a JSON string in the PNG's EXIF IFD0.ImageDescription field using the sharp library's withMetadata API.

Reading it back uses a deliberate bypass of standard TIFF byte-walking: instead of parsing the binary TIFF structure, the raw EXIF buffer is scanned as a UTF-8 string for the known "generator":"2d-assets-mcp" key, then the surrounding JSON object is extracted. This makes the reader immune to TIFF padding, byte-order variations, and unusual IFD layouts across different PNG writers.

{
  "generator": "2d-assets-mcp",
  "type": "asset",
  "name": "player_idle",
  "width": 128,
  "height": 128,
  "color": "#4A90E2",
  "shape": "rounded-rectangle",
  "fillMode": "linear-gradient",
  "fillPercent": 100,
  "trackColor": null,
  "pattern": "none",
  "secondaryColor": "#2E5A8A",
  "gradientAngle": 45,
  "textRotation": 0,
  "textPosition": "center",
  "strokeColor": "#000000",
  "strokeWidth": 4,
  "description": "Player idle placeholder, blue rounded rectangle 128x128",
  "createdAt": "2025-01-15T10:30:00.000Z"
}

Spritesheet metadata fields (additional fields returned for spritesheet files)

{
  "generator": "2d-assets-mcp",
  "type": "spritesheet",
  "totalWidth": 648,
  "totalHeight": 136,
  "columns": 4,
  "rows": 1,
  "frameCount": 4,
  "frameWidth": 128,
  "frameHeight": 128,
  "margin": 8,
  "spacing": 8,
  "frames": [
    {
      "index": 0,
      "x": 8,
      "y": 8,
      "width": 128,
      "height": 128,
      "name": "frame_0",
      "color": "#4A90E2",
      "shape": "rounded-rectangle"
    }
  ],
  "createdAt": "2025-01-15T10:30:00.000Z"
}

Example Prompts for Your AI

Once connected to an AI coding assistant, try these prompts to speed up your workflow:

Single asset

"Create a 128×128 blue rounded-rectangle placeholder for my player character at C:\Users\me\project\assets\sprites\ (Windows) or /home/me/project/assets/sprites/ (Linux) or /Users/me/project/assets/sprites/ (macOS). Label it 'Player' and give it a radial gradient."

Health bar

"Generate a health bar PNG at 200×24 pixels, filled 65%, thin stroke, red fill color, dark gray track, at your project's UI folder. Call the file health_bar.png."

Spritesheet

"Create a 4-frame run cycle spritesheet for my player. Each frame should be 64×64, different shades of blue, labeled Frame 1 through Frame 4. Save it to my project's sprites folder."

Read metadata

"Read the metadata from my project's sprites folder, file player_idle_128x128.png."

Installation

Option 1: Use directly with `npx` (no install required)

The fastest way to connect it to any AI coding assistant:

{
  "mcpServers": {
    "2d-assets": {
      "command": "npx",
      "args": ["-y", "2d-assets-mcp"]
    }
  }
}

Option 2: Manual installation with package manager (pnpm, npm, yarn)

1. Clone the repository

git clone https://github.com/crony-io/2d-assets-mcp.git
cd 2d-assets-mcp

2. Install dependencies

pnpm install   # recommended
# or: npm install
# or: yarn install

3. Build the project

pnpm run build
# or: npm run build
# or: yarn run build

4. Configure your MCP client

{
  "mcpServers": {
    "2d-assets-mcp": {
      "command": "node",
      "args": ["/absolute/path/to/2d-assets-mcp/dist/index.js"]
    }
  }
}

Option 3: Install globally with pnpm or npm

This project works with any Node.js package manager. Choose your preferred one:

npm

npm install -g 2d-assets-mcp

pnpm

pnpm add -g 2d-assets-mcp

Then reference the installed binary:

{
  "mcpServers": {
    "2d-assets": {
      "command": "2d-assets-mcp"
    }
  }
}

Claude Code / Claude Desktop

Add to your Claude Code/Claude Desktop MCP settings:

{
  "mcpServers": {
    "2d-assets-mcp": {
      "command": "node",
      "args": ["/absolute/path/to/2d-assets-mcp/dist/index.js"]
    }
  }
}

Devin

Add to your Devin MCP settings (mcp_config.json):

{
  "mcpServers": {
    "2d-assets-mcp": {
      "command": "node",
      "args": ["/absolute/path/to/2d-assets-mcp/dist/index.js"],
      "disabled": false
    }
  }
}

Cursor

Create .cursor/mcp.json in your project:

{
  "mcpServers": {
    "2d-assets-mcp": {
      "command": "node",
      "args": ["/absolute/path/to/2d-assets-mcp/dist/index.js"]
    }
  }
}

Development

Prerequisites

Node.js 18 or later
pnpm 8 or later or npm 9 or later (any package manager works)

Setup

git clone https://github.com/crony-io/2d-assets-mcp.git
cd 2d-assets-mcp
# Choose your package manager:
pnpm install   # recommended
# or
npm install
# or
yarn install

Scripts

Command	Description
`npm run build` / `pnpm run build`	Compile TypeScript to `dist/`
`npm run dev` / `pnpm run dev`	Run directly from source with `tsx` (no build needed)
`npm run start` / `pnpm run start`	Run the compiled server from `dist/`
`npm run typecheck` / `pnpm run typecheck`	Type-check without emitting files
`npm run check` / `pnpm run check`	Run all checks: format, lint, and typecheck

Adding a new tool

Create src/tools/yourTool.ts and export a registerYourTool(server: McpServer) function
Import and call it in src/server.ts
Add any new Zod schemas to src/schemas.ts and types to src/types.ts

License

MIT — see LICENSE for full text.

Contributing

Issues and pull requests are always welcome. Just please, before you open a PR make sure to:

Run pnpm run check or npm run check (zero errors required).
Keep new tools in their own file under src/tools/.
Export new types from src/types.ts and schemas from src/schemas.ts.
Update this README's Tools Reference section for any new or changed parameters.

Available Tools

3 tools

generate_mock_assetA

Generates a single advanced custom mock 2D PNG asset (supports gradients, patterns, text rotation, transparency, and auto-scaling) for game prototypes. Embeds JSON metadata into the PNG (dimensions, color, shape, description) readable by read_image_metadata.

ParametersJSON Schema

Name	Required	Description	Default
`text`	Yes	Text to display on the asset
`color`	Yes	Background hex color code, e.g., '#FF5733'
`shape`	No	The geometric shape of the asset. Default is rectangle when missing.	rectangle
`width`	No	Width in pixels. Default is 128 when missing.
`height`	No	Height in pixels. Default is 128 when missing.
`opacity`	No	Opacity of the background shape from 0.0 (transparent) to 1.0 (opaque). Default is 1.0 when missing.
`pattern`	No	Optional pattern overlay. Default is none when missing.	none
`filename`	Yes	Name of the file, e.g., 'player_idle.png'
`fillMode`	No	Background fill mode. Default is solid when missing.	solid
`fontSize`	No	Optional explicit font size in pixels. If omitted, it auto-scales to fit.
`directory`	Yes	Absolute path to the target project folder
`textColor`	No	Optional hex color for the text. If omitted, a contrasting color (black or white) will be automatically calculated based on the background.
`trackColor`	No	Background color for the unfilled portion of the asset when fillPercent < 100. Hex code, e.g., '#333333'
`fillPercent`	No	Percentage of the asset to fill, useful for health or progress bars (0-100). Default is 100.
`strokeColor`	No	Color of the asset border hex code. Default is #000000 when missing.	#000000
`strokeWidth`	No	Width of the asset border in pixels. Set to 0 for no border. Default is 4 when missing.
`patternColor`	No	Pattern color. If omitted, a derived contrast color will be used.
`patternScale`	No	Pattern tile size in pixels. Default is 16 when missing.
`textPosition`	No	Vertical alignment of the text. Default is center when missing.	center
`textRotation`	No	Rotation angle for the text in degrees. Default is 0 when missing.
`gradientAngle`	No	Angle for linear gradients in degrees. Ignored for radial gradients. Default is 45 when missing.
`patternOpacity`	No	Pattern overlay opacity from 0.0 to 1.0. Default is 0.18 when missing.
`secondaryColor`	No	Secondary color used for gradients. If omitted, a derived variant of color will be used.
`assetDescription`	No	Human-readable description of this asset stored as image metadata. Useful for models without vision to understand the asset later. E.g. 'Player idle placeholder, blue rectangle 128x128'

TDQS

A4.1/5.0

Behavior4/5

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

With no annotations provided, the description carries the full burden. It discloses several behavioral features (gradients, patterns, text rotation, transparency, auto-scaling) and mentions that JSON metadata is embedded in the PNG. It does not discuss file overwrite behavior or directory handling, but the core generation behavior is transparent.

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?

The description is exactly two sentences, front-loaded with the action verb. It packs capabilities into a compact list and explains the metadata integration without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 24 parameters and no output schema, the description is adequate but has gaps. It provides context about game prototyping and metadata for read_image_metadata, but it does not explicitly mention that a file will be written to disk, nor does it explain prerequisites or relationships to the batch tool beyond 'single'.

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 100%, so the description only needs to add marginal value. It does add 'auto-scaling' context for font size and clarifies the metadata fields (dimensions, color, shape, description), but this is not substantial beyond the schema's detailed parameter descriptions.

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?

The description uses a specific verb 'Generates' with a precise resource: 'single advanced custom mock 2D PNG asset'. It distinguishes from the sibling 'generate_mock_asset_batch' by explicitly stating 'single', and also explains the metadata integration with 'read_image_metadata'.

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

Usage Guidelines4/5

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

The description clearly indicates this tool is for generating a single asset, which implies the batch tool is for multiple assets. However, it does not explicitly state when-not-to-use or direct the user to alternatives beyond the implied distinction.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

generate_mock_asset_batchA

Generates multiple mock 2D PNG assets at once. Can create individual files, a spritesheet, Each PNG has embedded JSON metadata readable by read_image_metadata.

ParametersJSON Schema

Name	Required	Description	Default
`assets`	Yes	An array of asset configuration objects to generate simultaneously
`sheetMargin`	No	Outer margin around the spritesheet in pixels. Default is 8 when missing.
`sheetSpacing`	No	Spacing between spritesheet cells in pixels. Default is 8 when missing.
`sheetFilename`	No	Filename for the generated spritesheet. Default is spritesheet.png when missing.	spritesheet.png
`sheetDirectory`	No	Optional output directory for the spritesheet. Defaults to the first asset directory.
`spritesheetMode`	No	individual = create separate PNGs only, spritesheet = create only a spritesheet PNG. Default is spritesheet when missing.	spritesheet

TDQS

A3.8/5.0

Behavior3/5

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

No annotations are provided, so the description must carry the transparency burden. It adds useful behavioral context by stating each PNG has embedded JSON metadata readable by read_image_metadata. However, it does not disclose file-system side effects such as overwriting behavior, required directory existence, or error conditions, which are relevant for a file-generation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short and front-loaded with the main purpose. It has a grammatical flaw ('a spritesheet, Each' fragment) and is somewhat terse, but it avoids unnecessary verbosity and conveys the core capabilities efficiently.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The schema is rich and covers all parameters, and the description adds the metadata cross-reference to read_image_metadata. However, for a complex batch file-generation tool, the description does not address return behavior, overwrite semantics, or prerequisites (e.g., existing directories), leaving gaps that are not filled by the schema or annotations.

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 100%, so the schema fully documents all parameters. The description adds no parameter-specific semantics beyond mentioning spritesheet and metadata, which are already reflected in schema fields like spritesheetMode and assetDescription. Baseline 3 is appropriate.

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?

The description clearly states the tool 'Generates multiple mock 2D PNG assets at once', specifying the verb, resource, and batch scope. It distinguishes itself from the sibling generate_mock_asset through the word 'multiple' and from read_image_metadata by focusing on generation while also linking to metadata.

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

Usage Guidelines4/5

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

The description implies usage for batch generation with 'multiple mock 2D PNG assets at once' and mentions output options (individual files or spritesheet), giving clear context. It does not explicitly name alternatives or state when-not-to-use, but the batch orientation is evident.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

read_image_metadataA

Reads the embedded JSON metadata from a PNG file generated by this MCP server. Returns the metadata object with dimensions, color, shape, description, etc.

ParametersJSON Schema

Name	Required	Description	Default
`filepath`	Yes	Absolute path to the PNG file to read metadata from

TDQS

A4/5.0

Behavior3/5

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

No annotations are provided, so the description must carry full behavioral disclosure. It discloses that the tool reads embedded JSON metadata and returns an object with specific fields, but does not mention error behavior for missing files or files not generated by this server. This is adequate for a simple read operation but leaves some edge cases unaddressed.

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?

The description is two sentences, front-loaded with the action, and contains no fluff. Every sentence adds value: the first states what it does and the scope, the second states what is returned.

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?

For a simple one-parameter read tool, the description is largely complete. It names the return fields (dimensions, color, shape, description) though there is no output schema, and it clarifies the file type and provenance. It could be more exhaustive about return structure, but given the simplicity, this is slightly above adequate.

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?

With 100% schema description coverage, the parameter 'filepath' is already fully documented in the schema. The tool description adds the context that the file must be a PNG generated by this server, but the schema provides the essential meaning. This is the baseline 3.

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?

The description clearly states the verb 'Reads' and the specific resource 'embedded JSON metadata from a PNG file', immediately distinguishing this tool from its generation-focused siblings. It also scopes the tool to files generated by this MCP server, which is precise.

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

Usage Guidelines4/5

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

The description implies the tool is for reading metadata from already-generated PNG files, contrasting with sibling tools that generate assets. It gives clear context but does not explicitly state when not to use it or name alternatives, so it falls short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

3 tool updatesv0.1.4Aug 7, 2026
- First observedgenerate_mock_asset
- First observedgenerate_mock_asset_batch
- First observedread_image_metadata

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.2/5.0

Disambiguation5/5

Each tool has a distinct purpose: generate single asset, generate multiple assets, and read metadata. The single vs. batch distinction is clear, and read_image_metadata is entirely separate.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern in snake_case: generate_mock_asset, generate_mock_asset_batch, read_image_metadata. The convention is uniform.

Tool Count5/5

Three tools is well-scoped for a niche server focused on generating and inspecting mock 2D assets. Each tool serves a necessary function without redundancy.

Completeness5/5

The tool surface covers the full workflow: generating a single asset, generating batches (including spritesheets), and reading embedded metadata. No obvious gaps for the stated domain.

Maintenance

ActivityStale

ResponsivenessSyncing

Resources

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

SpriteCookOAuth
ai.spritecook
Generate game assets with AI for 2D games, including sprites, tilesets, and animations.
Developer Tools Games & Gamification Image & Video Processing
3
Ludo AI Game Assets A
ai.ludo
Generate game assets with AI: sprites, 3D models, animations, sound effects, music, and voices.
Games & Gamification Image & Video Processing Audio Processing
3126
designforyou A
org.swapp1990.designforyou
Generate logos, social posts, app screenshots, comic panels & visual-novel assets from prompts.
Design Tools Image & Video Processing
412
Sprixen
com.sprixen
AI game assets for agents: consistent sprites, 2D animations, tiles, maps, music and engine exports.
1

Related MCP Servers

ComfyMCP Studio
Image & Video Processing Games & Gamification Developer Tools
tuannguyen14
F
license
A
quality
D
maintenance
Generates 2D game assets (sprites, icons, tilesets, characters, animations) using AI workflows powered by ComfyUI with support for viewpoint control, style presets, and Unity export.
Updated 9 months ago (2025-12-22 03:33 UTC)
13
2
-
ssyubix-pixelart-mcp
Image & Video Processing Design Tools
syuaibsyuaib
A
license
A
quality
A
maintenance
Generate Pixel Art and Tilemap/Tileset
Updated a month ago (2026-08-09 02:42 UTC)
24
1
Apache 2.0
designforyou
Design Tools Marketing
swapp1990
A
license
Not graded
quality
B
maintenance
Generates logos, social media posts, app-store screenshots, comic panels, and visual-novel assets from natural-language prompts using 119 templates.
Updated a month ago (2026-07-29 21:46 UTC)
MIT
Retro Diffusion MCP Serverofficial
Image & Video Processing Games & Gamification AI & Machine Learning
Retro-Diffusion
A
license
Not graded
quality
B
maintenance
Generate real pixel art — sprites, animations, and tilesets — from any MCP-capable AI assistant. Grid-aligned pixels, controlled palettes, transparent backgrounds, with cost estimation always free.
Updated a month ago (2026-08-02 22:01 UTC)
2
MIT

Appeared in Searches

A search for 2D games

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/crony-io/2d-assets-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server

2d-assets-mcp

Generated Assets Examples

Character Sprites & Animations

UI Elements

Game Items

Grass and water

Trees

Animation Spritesheets

Security Considerations

Asset Content

Because this MCP server writes files directly to your machine to save you time, please review these security best practices:

File System Access

Path Traversal

Overall Best Practices

Core Features

Tools Reference

1. generate_mock_asset

2. generate_mock_asset_batch

3. read_image_metadata

How metadata embedding works

Example Prompts for Your AI

Installation

Option 1: Use directly with npx (no install required)

Option 2: Manual installation with package manager (pnpm, npm, yarn)

Option 3: Install globally with pnpm or npm

Claude Code / Claude Desktop

Devin

Cursor

Development

Prerequisites

Setup

Scripts

Adding a new tool

License

Contributing

Available Tools

TDQS

TDQS

TDQS

Tool Schema Changelog

TDQS

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

ComfyMCP Studio

ssyubix-pixelart-mcp

designforyou

Retro Diffusion MCP Serverofficial

Appeared in Searches

Latest Blog Posts

MCP directory API

1. `generate_mock_asset`

2. `generate_mock_asset_batch`

3. `read_image_metadata`

Option 1: Use directly with `npx` (no install required)