Which integrations are available for this server?

Generates and transforms Expo assets such as icons, splash screens, and favicons for Expo projects.

How do I use expo-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., "@expo-assets-mcp Generate Expo icons from ~/logo.png" 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.

expo-assets-mcp

by elber-code

Overview Schema Related Servers Score Discussions

Local

expo-assets-mcp

Local MCP server to generate and transform Expo assets. Also includes a CLI script to run it directly from the terminal.

Project structure

src/
├── expo-assets.ts   ← reusable logic (asset definitions, image transformations)
├── index.ts         ← MCP server
└── generate.ts      ← CLI script
dist/                ← compiled output (generated with npm run build)

Related MCP server: Expo MCP Server

Installation

npm install
npm run build

Web Generator

A pure JavaScript version of this tool is available directly in the browser! Open index.html or visit https://elber-code.github.io/expo-assets-mcp/ to access a rich GUI that features:

Interactive Cropper: Perfectly center your icons with a 1:1 aspect ratio.
Live Icon Previews: See how your icon looks in iOS (squircle) and Android (circle) shapes with transparent or solid backgrounds in real-time.
Advanced Banners: Generate App Store mockups or promo banners by placing your Expo assets (e.g. Splash, Icon) inside custom resolutions to download individually.
Custom ZIP Assets: Easily add extra custom-sized assets to the final ZIP.
Bilingual Interface: Seamlessly switch between English and Spanish (index_es.html).

No backend or server required; everything is processed locally in your browser!

CLI usage

Generates all Expo assets from a source image. Creates a folder next to the image named <image>-assets/.

node dist/generate.js <image-path> [options]

Options:

Flag	Description
`--bg "#rrggbb"`	Background color. Omit for transparent
`--no-overwrite`	Skip files that already exist

Examples:

# Transparent background
node dist/generate.js /Users/me/logo.png

# With background color
node dist/generate.js /Users/me/logo.png --bg "#E6F4FE"

Output:

/Users/me/logo-assets/
├── icon.png
├── android-icon-foreground.png
├── android-icon-background.png
├── android-icon-monochrome.png
├── splash-icon.png
├── favicon.png
├── react-logo.png
├── react-logo@2x.png
├── react-logo@3x.png
└── partial-react-logo.png

MCP usage (Claude Desktop)

Copy claude-config.example.json to claude-config.json, fill in the correct path, then merge it into:

~/Library/Application Support/Claude/claude_desktop_config.json

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

Test with MCP Inspector

npx @modelcontextprotocol/inspector node dist/index.js

Available MCP tools

`generate_expo_icons`

Generates all 10 Expo assets into a single assets/images/ folder.

Parameter	Type	Default	Description
`input_image`	string	—	Absolute path to the source image
`output_dir`	string	—	Absolute path to the Expo project's `assets/images/` folder
`background_color`	string	transparent	Background color in hex (e.g. `#E6F4FE`). Omit for transparent.
`overwrite`	boolean	`true`	Overwrite existing files
`proportions`	object	see table	Content proportion per asset (0.1–1.0)

Proportions:

Key	Asset(s)	Default
`icon`	`icon.png`	`0.7`
`android_adaptive`	`android-icon-foreground/background.png`	`0.33`
`android_monochrome`	`android-icon-monochrome.png`	`0.33`
`splash`	`splash-icon.png`	`0.5`
`favicon`	`favicon.png`	`0.8`
`react_logo`	`react-logo.png` + `@2x` + `@3x`	`0.8`
`partial_logo`	`partial-react-logo.png`	`0.5`

`transform_image`

Transforms an image to specific dimensions with optional content proportion and background.

Parameter	Type	Default	Description
`input_image`	string	—	Path to the source image (PNG, JPEG, WebP, TIFF, AVIF)
`output_path`	string	—	Full output path including filename and extension (e.g. `/path/result.webp`)
`width`	number	—	Output canvas width in pixels
`height`	number	—	Output canvas height in pixels
`proportion`	number	`1`	How much of the canvas the content fills (0.1–1.0, 1 = fills everything)
`background_color`	string	transparent	Canvas background color in hex. Omit for transparent.
`format`	`png\|jpeg\|webp`	`png`	Output file format
`quality`	number	`95`	Compression quality for jpeg/webp only (1 = lowest, 100 = highest)

`convert_svg`

Converts an SVG file to PNG, JPEG, or WebP at the specified dimensions.

Parameter	Type	Default	Description
`input_svg`	string	—	Absolute path to the source SVG file
`output_path`	string	—	Full output path including filename and extension
`width`	number	—	Output width in pixels
`height`	number	proportional	Output height in pixels. Omit to scale proportionally from width.
`format`	`png\|jpeg\|webp`	`png`	Output file format
`background_color`	string	transparent	Background color in hex. Omit for transparent (PNG only).
`quality`	number	`95`	Compression quality for jpeg/webp only (1 = lowest, 100 = highest)

Generated assets

Expo handles all platform-specific resizing automatically from these 10 files.

Source image requirements

Format: PNG
Minimum size: 1024×1024 px
Background: transparent (recommended)

Asset table

File	Canvas	Background	Transformation	app.json key
`icon.png`	1024×1024	`background_color` or transparent	`contain`, centered, prop 0.7	`expo.icon`
`android-icon-foreground.png`	512×512	Always transparent	`contain`, centered, prop 0.33	`android.adaptiveIcon.foregroundImage`
`android-icon-background.png`	512×512	`background_color` or transparent	`contain`, centered, prop 0.33	`android.adaptiveIcon.backgroundImage`
`android-icon-monochrome.png`	432×432	Always transparent	White silhouette, prop 0.33	`android.adaptiveIcon.monochromeImage`
`splash-icon.png`	1024×1024	Always transparent	`contain`, centered, prop 0.5	`expo-splash-screen > image`
`favicon.png`	48×48	Always transparent	`contain`, centered, prop 0.8	`web.favicon`
`react-logo.png`	100×100	Always transparent	`contain`, centered, prop 0.8	Decorative UI @1x
`react-logo@2x.png`	200×200	Always transparent	`contain`, centered, prop 0.8	Decorative UI @2x
`react-logo@3x.png`	300×300	Always transparent	`contain`, centered, prop 0.8	Decorative UI @3x
`partial-react-logo.png`	518×316	Always transparent	Right-side crop from top, prop 0.5	Decorative UI partial

Special transformations

`android-icon-monochrome.png` — White silhouette

Every non-transparent pixel is converted to pure white. Android 13+ uses this for Themed Icons, tinting the silhouette with the system color theme.

pixel (r, g, b, a > 10)  →  (255, 255, 255, a)
pixel (r, g, b, a ≤ 10)  →  unchanged (transparent)

`partial-react-logo.png` — Section crop

A section of the source image is cropped without distortion:

Horizontal: right side (end)
Vertical: from the top (start)
The section is scaled proportionally to fit the 518×316 canvas

partial_logo: 0.5 → right half · partial_logo: 0.33 → right third

Android adaptive icon — Safe zone

Keep important content within the 66% center (338×338 px on a 512×512 canvas) to avoid being clipped by any Android launcher shape.

┌─────────────────┐  512×512
│                 │
│  ┌───────────┐  │
│  │  safe     │  │  338×338 (66%)
│  │  zone     │  │
│  └───────────┘  │
│                 │
└─────────────────┘

Scripts

npm run build   # compile TypeScript
npm start       # start MCP server
npm run dev     # run with tsx (no compile needed)

Available Tools

3 tools

convert_svgB

Converts an SVG file to PNG, JPEG, or WebP at the specified dimensions. Supports multiple output sizes in a single call.

ParametersJSON Schema

Name	Required	Description	Default
`width`	Yes	Output width in pixels
`format`	No	Output file format (default: png)	png
`height`	No	Output height in pixels. Omit to scale proportionally from width.
`quality`	No	Compression quality for jpeg/webp only (1 = lowest, 100 = highest, default: 95)
`input_svg`	Yes	Absolute path to the source SVG file
`output_path`	Yes	Absolute path of the output file, including name and extension (e.g. /path/result.png)
`background_color`	No	Background color in hex (e.g. #ffffff). Omit for transparent (only works with png).

TDQS

B3.2/5.0

Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions 'Supports multiple output sizes in a single call' as a behavior, but it does not clarify whether existing output files are overwritten, what permissions are required, or how the multiple-size feature is actually invoked—especially since the schema does not reflect it. This leaves significant behavioral gaps.

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 only two sentences, front-loaded with the core action ('Converts an SVG file to PNG, JPEG, or WebP'). The first sentence is efficient and clear. However, the second sentence introduces a capability with no explanation, and because it may be unsupported by the schema, it slightly undermines the conciseness and value of the sentence.

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 description covers the core conversion behavior but omits crucial context: how 'multiple output sizes' is specified, whether output files are overwritten, and any limitations like transparency only applying to PNG. With seven parameters and no output schema, the description should provide more guidance on usage and edge cases to be fully complete.

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?

The schema provides descriptions for all seven parameters, so baseline is 3. The description adds no parameter-level detail, and the claim about multiple output sizes could mislead the agent into expecting a parameter for it, which does not exist. The schema remains the primary source of parameter meaning.

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?

The description explicitly states the tool converts SVG to PNG/JPEG/WebP at specified dimensions, which is specific and distinguishes it from the icon generation and image transformation siblings. However, the claim 'Supports multiple output sizes in a single call' is not backed by the input schema, introducing ambiguity about the tool's actual capability.

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

Usage Guidelines3/5

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

The intended use case is implied: convert SVG files to raster formats. However, there is no explicit guidance on when to use this tool over the sibling tools (generate_expo_icons, transform_image), no exclusions, and no mention of alternatives. The agent must infer usage from the tool name and description.

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

generate_expo_iconsA

Generates all 10 Expo assets into assets/images/: icon, android adaptive (foreground/background/monochrome), splash, favicon, react-logo (@1x/@2x/@3x) and partial.

ParametersJSON Schema

Name	Required	Description
`overwrite`	No	Overwrite existing files (default: true)
`output_dir`	Yes	Absolute path to the Expo project's assets/images/ folder
`input_image`	Yes	Absolute path to the source image (transparent PNG recommended, minimum 1024×1024)
`proportions`	No	Content proportion per asset (0.1–1.0). Controls how much of the canvas the content fills.
`background_color`	No	Background color in hex (e.g. #E6F4FE). Omit for transparent background.

TDQS

A4/5.0

Behavior3/5

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

With no annotations provided, the description carries the burden of explaining side effects. It clearly states that files are generated into assets/images/, but it does not explicitly warn about overwriting existing files or mention prerequisites like the need for a transparent PNG. The schema documents the overwrite parameter, but the description itself is thin on behavioral details.

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 a single sentence that directly conveys the purpose and enumerates the outputs. Every word earns its place; it is concise and front-loaded.

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?

The description covers the full scope of generated outputs and the target directory. Given the rich schema (including nested proportions and defaults), the description is sufficient for an agent to select and invoke the tool. It could mention the required source image or the fact that it writes files, but those are present in the schema.

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 already documents all parameters and their defaults. The description adds no parameter-specific meaning, so the baseline of 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 uses a specific verb ('Generates') and resource ('all 10 Expo assets'), explicitly listing each output (icon, android adaptive, splash, favicon, react-logo, partial). This clearly distinguishes it from sibling tools like transform_image or convert_svg, which handle generic transformations or conversions.

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 states the tool's output directory and the full set of generated assets, providing clear context for when to use it. However, it does not explicitly mention when not to use it or name alternatives, such as using transform_image for one-off resizing.

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

transform_imageB

Transforms an image to the specified canvas dimensions with optional content proportion and background color.

ParametersJSON Schema

Name	Required	Description	Default
`width`	Yes	Output canvas width in pixels
`format`	No	Output file format (default: png)	png
`height`	Yes	Output canvas height in pixels
`quality`	No	Output compression quality, only applies to jpeg and webp (1 = lowest, 100 = highest, default: 95)
`proportion`	No	How much of the canvas the content fills (0.1–1.0, default: 1 = fills everything)
`input_image`	Yes	Absolute path to the source image (accepts PNG, JPEG, WebP, TIFF, AVIF)
`output_path`	Yes	Absolute path of the output file, including name and extension (e.g. /path/to/result.webp)
`background_color`	No	Canvas background color in hex (e.g. #ffffff). Omit for transparent background.

TDQS

B3.1/5.0

Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It fails to explain how the transformation is applied (cropping, stretching, padding), how 'proportion' affects the layout, how 'background_color' interacts with transparency, or whether the source file is modified. These are significant undocumented behaviors for a tool with multiple options.

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 a single, front-loaded sentence with no filler or redundancy. It efficiently conveys the core purpose, though it could include a bit more detail without becoming verbose.

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

Completeness2/5

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

Given the tool's complexity (8 parameters, 4 required, multiple formats and options), the one-sentence description is insufficient. It does not describe the transformation result, output saving behavior, or how optional parameters interact. Without an output schema or annotations, users face many unknowns.

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?

The schema already provides detailed descriptions for all 8 parameters (100% coverage), so the description adds no extra semantic value. Its mention of 'content proportion' and 'background color' simply restates what the schema already says, without clarifying interactions or edge cases.

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?

The description states 'Transforms an image to the specified canvas dimensions' using a specific verb and resource, clearly indicating a dimension-changing operation. It distinguishes from siblings (generate_expo_icons, convert_svg) by focusing on canvas sizing rather than icon generation or SVG conversion. However, 'transforms' is somewhat generic and could be more specific (e.g., resize, pad).

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

Usage Guidelines3/5

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

The description implies the tool is used when an image needs to be fitted to a specific canvas size, but it does not explicitly state when to use it over sibling tools or provide exclusions. No alternatives or conditions are mentioned, leaving usage guidance implied rather than explicit.

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 updatesv1.0.0Aug 9, 2026
- First observedconvert_svg
- First observedgenerate_expo_icons
- First observedtransform_image

Install Server

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

TDQS

A3.8/5.0

Disambiguation5/5

Each tool has a clearly distinct purpose: generate_expo_icons creates a predefined set of Expo assets, transform_image modifies an existing image's canvas, and convert_svg handles SVG to raster conversion. There is no overlap or ambiguity between them.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern using snake_case: generate_expo_icons, transform_image, convert_svg. This provides a predictable and readable naming convention throughout the server.

Tool Count5/5

With only 3 tools, the server is well-scoped for its specific purpose of handling Expo assets. Each tool is essential and non-redundant, fitting within the ideal range without feeling thin or excessive.

Completeness5/5

The tool surface covers the full lifecycle of asset preparation: generating standard Expo icons, transforming existing images, and converting SVGs to required formats. No obvious gaps exist for the stated purpose, as the set includes both batch generation and bespoke manipulation utilities.

Maintenance

ActivityInactive

ResponsivenessNo issues

Resources

GitHub Repository

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

Imagcon
io.github.Explorer-64
Generate PWA icon sets and iOS splash screens from a text prompt or an existing image.
Image & Video Processing Developer Tools
11
SVG AIOAuth
org.svgai
Generate and vectorize clean, editable SVG graphics from text, images, or both.
AI & Machine Learning Image & Video Processing Design Tools
1
Expo A
io.github.mcp-dir
Your Expo and EAS project in natural language: up to date SDK docs, cloud builds (status, logs, trig
CI/CD & DevOps Documentation Access
251
distribea-mcp A
io.github.Distribea
Generate images, video, music and voice from your CLI or AI agent. On-brand AI media toolkit.
AI & Machine Learning Image & Video Processing Marketing
21

Related MCP Servers

Auto Favicon MCP Server
Web Scraping Developer Tools
dh1011
A
license
A
quality
F
maintenance
Automatically generates complete favicon sets from PNG images or URLs, creating multiple sizes, ICO files, Apple touch icons, and manifest.json for web applications.
Updated a year ago (2025-07-27 23:29 UTC)
2
34
MIT
Expo MCP Server
Developer Tools CI/CD & DevOps App Automation
CaullenOmdahl
A
license
Not graded
quality
D
maintenance
Enables programmatic interaction with Expo/React Native projects and EAS (Expo Application Services) for managing builds, publishing OTA updates, submitting apps to stores, and accessing comprehensive documentation.
Updated 9 months ago (2025-12-12 11:35 UTC)
5
MIT
SVG Maker MCP Server
Image & Video Processing Developer Tools Multimedia Processing
erkamkavak
F
license
Not graded
quality
D
maintenance
Enables creation, validation, rendering, and optimization of SVG images with conversion capabilities to PNG, React components, React Native components, and Data URIs.
Updated 8 months ago (2026-01-04 14:21 UTC)
-
Web Icons Generator CLI MCP
Developer Tools Image & Video Processing
entro314-labs
A
license
Not graded
quality
C
maintenance
Generates all required web app icons and manifest files from a single source image with framework auto-detection. Supports Next.js App Router, traditional web apps, and PWA standards with zero configuration.
Updated 24 days ago (2026-08-13 05:59 UTC)
19
MIT

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/elber-code/expo-assets-mcp'

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

expo-assets-mcp

Project structure

Installation

Web Generator

CLI usage

MCP usage (Claude Desktop)

Test with MCP Inspector

Available MCP tools

generate_expo_icons

transform_image

convert_svg

Generated assets

Source image requirements

Asset table

Special transformations

android-icon-monochrome.png — White silhouette

partial-react-logo.png — Section crop

Android adaptive icon — Safe zone

Scripts

Available Tools

Tool Schema Changelog

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

Latest Blog Posts

MCP directory API

`generate_expo_icons`

`transform_image`

`convert_svg`

`android-icon-monochrome.png` — White silhouette

`partial-react-logo.png` — Section crop