What can you do with this server?

This server provides tools for generating, managing, and downloading PWA icon sets and iOS splash screens using the Imagcon API — all from within an AI assistant. * Generate PWA Icons (generate_pwa_icons): AI-generate a source image from a text description, resize it to all PWA sizes, and extract the full icon set (including manifest.json and maskable assets) to a local output directory (default: ./public/icons). * Generate Splash Screens (generate_splash_screens): AI-generate a source image and produce iOS splash screens with a configurable background color (default: #ffffff), extracted to a local output directory (default: ./public/splash). * List Saved Icon Sets (list_saved_icon_sets): Retrieve a list of all previously saved PWA icon sets in your gallery. * Download Icon Set (download_icon_set): Re-download a previously saved PWA icon set ZIP by its set ID and extract it to a specified directory (default: ./public/icons). * Download Splash Screens (download_splash_screens): Re-download a previously saved splash screen set ZIP by its set ID and extract it to a specified directory (default: ./public/splash). * Check Credit Balance (get_credit_balance): View the remaining Imagcon API credits on your account.

Which integrations are available for this server?

Allows generation of PWA icon sets including various sizes, maskable assets, and manifest.json using the Imagcon API.

imagcon-mcp

by Explorer-64

Overview Schema Related Servers Score Discussions

Python

Remote

# imagcon-mcp

Local MCP server that wraps the Imagcon API so assistants can generate PWA icon sets (all sizes, maskable assets, manifest.json) and iOS splash screens without opening the site. Runs as a stdio process via uvx — no hosted service dependency, no persistent connections.

Requirements

Python 3.11–3.12
uv (provides uvx)
An Imagcon API key starting with ic_live_ from imagcon.app/api-keys

Related MCP server: Nano Banana

Install

The package is self-hosted (not on PyPI). Install directly from the wheel:

claude mcp add imagcon -- uvx --from https://imagcon.app/downloads/imagcon_mcp-0.3.0-py3-none-any.whl imagcon-mcp --api-key ic_live_...

Or with the key in the environment instead of on the command line:

claude mcp add imagcon -- uvx --from https://imagcon.app/downloads/imagcon_mcp-0.3.0-py3-none-any.whl imagcon-mcp

export IMAGCON_API_KEY=ic_live_...

For other MCP clients (Cursor, Windsurf, VS Code, Cline, Zed, Warp, Continue.dev), use the equivalent stdio config:

{
  "mcpServers": {
    "imagcon": {
      "command": "uvx",
      "args": ["--from", "https://imagcon.app/downloads/imagcon_mcp-0.3.0-py3-none-any.whl", "imagcon-mcp", "--api-key", "ic_live_..."]
    }
  }
}

Per-client config file locations and full examples: see CLIENT-CONFIGS in imagcon.app/.well-known/blueprint.txt.

Tools

Images

generate_image — AI-generate a source image from a text description. Returns image_key and a preview URL. Show the preview to the user and confirm before generating icons.
save_image — Save a generated image to your gallery by image_key and name.
list_saved_images — List all saved source images with keys and preview URLs.
create_icons_from_key — Generate a PWA install pack from an already-saved image_key. Returns html_head + a signed ZIP URL; local stdio also extracts to output_dir (default ./).
install_pwa_pack — Same builder as create_icons_from_key. Splash is a second credit and defaults to false.

Icon sets

generate_pwa_icons — AI-generate a source image, then a droppable public/ tree. Extract to output_dir (default ./). Do not pass ./public/icons — that nests.
create_pwa_icons_from_image — Same PWA pipeline from an existing local PNG/JPEG/WebP at image_path (no AI generation).
list_saved_icon_sets — List saved icon sets with IDs.
download_icon_set — Download a saved icon set ZIP by set_id, extract to output_dir.
get_icon_set_download_url — Get an authenticated download URL for a saved icon set ZIP by set_id.

Splash screens

generate_splash_screens — AI-generate a source image and produce 16 iOS splash screens, extract to output_dir (default ./public/splash).
create_splash_screens_from_image — Same splash pipeline from an existing local PNG/JPEG/WebP at image_path (no AI generation).
create_splash_screens_from_key — Same splash pipeline from an existing image_key (e.g. from generate_image or list_saved_images) — composites the icon on each canvas size without re-generating.
download_splash_screens — Download a saved splash screen set ZIP by set_id, extract to output_dir.
get_splash_screen_download_url — Get an authenticated download URL for a saved splash screen set ZIP by set_id.

Account

get_credit_balance — Returns remaining Imagcon credits.
setup_wallet_profile — Activate a permanent Imagcon account after a pay-per-call x402 payment. Pass wallet address, profile token from X-Imagcon-Token, name, terms_confirmed (after reading https://imagcon.app/terms-of-service), and a wallet signature over imagcon.app/profile/activate:{profile_token}:{unix_timestamp}.

AI image generation (generate_image, generate_pwa_icons, generate_splash_screens) and icon/splash set exports use credits. create_pwa_icons_from_image, create_splash_screens_from_image, create_splash_screens_from_key, and create_icons_from_key skip AI generation credits but still charge for export.

Configuration

Source	Variable / flag
Environment	`IMAGCON_API_KEY`
CLI	`--api-key` (overrides the env var)

If the key is missing, the process exits with an error pointing to imagcon.app/api-keys.

API base URL

All requests go to https://imagcon.app (no other base URL is supported).

Available Tools

6 tools

download_icon_setBInspect

Re-download a previously saved PWA icon set ZIP by its set ID.

ParametersJSON Schema

Name	Required	Description	Default
`set_id`	Yes
`output_dir`	No		./public/icons

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

B3.1/5.0

Behavior2/5

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

With no annotations, the description must fully disclose behavior. It only states 're-download', implying a read-like operation, but does not explain file overwrite behavior, file size implications, auth requirements, or what happens if the set_id is invalid. Lacks detail beyond basic action.

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?

Single sentence, no wasted words. It is concise, but could front-load the key purpose more effectively. Still, it earns its place with clear intent.

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 output schema exists (though not shown), the description need not detail return values, but it does not explain what the agent gets back (e.g., file path, binary data). For a simple 2-parameter tool, it is marginally complete but lacks usage context and parameter semantics.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% (no parameter descriptions). The description mentions 'set ID' but does not explain format or source. 'output_dir' is not explained despite having a default. The description adds minimal meaning beyond the schema's property names.

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 'download' and the resource 'previously saved PWA icon set ZIP', with the key identifier 'set ID'. It distinguishes itself from siblings like 'generate_pwa_icons' (generates new icons) and 'download_splash_screens' (downloads different resource).

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

Usage Guidelines2/5

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

No explicit guidance on when to use this tool versus alternatives. It does not mention prerequisites (e.g., need a saved set from generate_pwa_icons) or how to obtain the set_id (e.g., via list_saved_icon_sets). No exclusions or when-not-to-use context.

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

download_splash_screensCInspect

Re-download a previously saved splash screen set ZIP by its set ID.

ParametersJSON Schema

Name	Required	Description	Default
`set_id`	Yes
`output_dir`	No		./public/splash

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

C2.9/5.0

Behavior2/5

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

No annotations provided, so description carries full burden. Only states the action without disclosing behavior like file overwriting, directory creation, or any side effects.

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?

Single sentence with no extraneous words. However, it may be overly terse given the need for parameter explanation.

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?

For a simple download tool with output schema, description covers core action. But lacks context about obtaining set_id and default output behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%. Description adds no meaning beyond parameter names; fails to explain format or constraints for set_id or output_dir.

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?

Clearly states the verb (re-download), resource (splash screen set ZIP), and identifier (set ID). Distinguishes from sibling tools like download_icon_set.

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

Usage Guidelines2/5

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

No guidance on when to use this tool versus alternatives (e.g., generate_splash_screens, list_saved_icon_sets). Implies need for a set ID but doesn't specify prerequisites.

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

generate_pwa_iconsDInspect

ParametersJSON Schema

Name	Required	Description	Default
`description`	Yes
`output_dir`	No		./public/icons

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

D1/5.0

Behavior1/5

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

Tool has no description.

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

Conciseness1/5

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

Tool has no description.

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

Completeness1/5

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

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

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

Usage Guidelines1/5

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

Tool has no description.

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

generate_splash_screensBInspect

Generate iOS and Android splash screens from a text description and download as a ZIP. background_color must be a hex color string (e.g. '#ffffff').

ParametersJSON Schema

Name	Required	Default
`description`	Yes
`background_color`	No	#ffffff
`output_dir`	No	./public/splash

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

B3.4/5.0

Behavior2/5

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

With no annotations, the description carries full burden but only discloses that it generates and downloads a ZIP, and a hex color constraint. It omits behavioral traits like whether files are overwritten, rate limits, or authentication needs.

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?

Two concise sentences with front-loaded purpose and a specific parameter constraint. No unnecessary words or redundancy.

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 basic purpose and output (ZIP download) and a key parameter constraint. Given an output schema exists, return values are not required. Missing are prerequisites or limitations, but overall adequate for a simple generation tool.

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 description adds meaning for background_color by specifying hex format, but provides no additional context for description or output_dir beyond the schema. Since schema coverage is 0%, the description partially compensates.

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 iOS and Android splash screens from a text description and downloads them as a ZIP, with a specific verb and resource that distinguishes it from sibling tools like download_icon_set or generate_pwa_icons.

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

Usage Guidelines2/5

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

No explicit guidance on when to use this tool versus alternatives such as download_splash_screens or list_saved_icon_sets. The description implies use for splash screen generation but lacks when-not-to-use or alternative suggestions.

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

get_credit_balanceDInspect

ParametersJSON Schema

Name	Required	Description	Default
No parameters

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

D1/5.0

Behavior1/5

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

Tool has no description.

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

Conciseness1/5

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

Tool has no description.

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

Completeness1/5

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

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

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

Usage Guidelines1/5

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

Tool has no description.

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

list_saved_icon_setsAInspect

List all PWA icon sets previously saved in the user's gallery.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A3.8/5.0

Behavior3/5

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

No annotations provided; description states it lists 'all' but lacks details on pagination, limits, or read-only nature. Adequate for simple listing.

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?

Single sentence, no fluff. Front-loaded with action and scope.

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?

Output schema exists, so return value details are covered. Lacks minor context like ordering or filtering, but sufficient for a simple list.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Zero parameters, so baseline 4. Description adds meaning by specifying 'saved in gallery' beyond empty schema.

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?

Description clearly specifies verb 'list' and resource 'PWA icon sets' saved in gallery. Distinguishes from sibling tools like generate_pwa_icons (creation).

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

Usage Guidelines2/5

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

No guidance on when to use this tool vs alternatives (e.g., download_icon_set). No context about prerequisites or fallbacks.

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.

6 tool updatesv0.1.0May 27, 2026
- First observeddownload_icon_set
- First observeddownload_splash_screens
- First observedgenerate_pwa_icons
- First observedgenerate_splash_screens
- First observedget_credit_balance
- First observedlist_saved_icon_sets

Install Server

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

TDQS

C2.6/5.0

Disambiguation4/5

Tool names clearly differentiate between icon and splash screen operations, but two tools have empty descriptions, which could cause confusion for an agent.

Naming Consistency4/5

Most tools follow a verb_noun pattern in snake_case, but get_credit_balance uses 'get' instead of 'list' or 'download', causing slight inconsistency.

Tool Count5/5

Six tools is well-scoped for a PWA icon and splash screen generation service, covering core operations without being overwhelming.

Completeness4/5

The set covers generate, download, list, and credit checking, but is missing update/delete for saved sets, though that aligns with a generation-focused service.

Maintenance

ActivityActive

ResponsivenessNo issues

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

Logospell A
com.logospell
AI-agent image generation: cohesive sets & illustrations. Resize a set or export icons, free.
AI & Machine Learning Image & Video Processing
83
designforyou A
org.swapp1990.designforyou
Generate logos, social posts, app screenshots, comic panels & visual-novel assets from prompts.
Design Tools Image & Video Processing
412
MascotLab AOAuth
io.mascotlab
Generate your app's mascot, then props, poses and animations that stay on-model.
Image & Video Processing Design Tools
2
Supericons A
io.github.curlymolelabs
Multilingual semantic SVG icon search with previews for AI coding agents. 20,000+ icons.
Search Developer Tools Design Tools
521

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
Nano Banana
Image & Video Processing Multimedia Processing
Aeven-AI
A
license
B
quality
C
maintenance
Generate, edit, and restore images using natural language prompts through the Gemini 2.5 Flash image model. Supports creating app icons, seamless patterns, visual stories, and technical diagrams with smart file management.
Updated 10 months ago (2025-11-05 11:03 UTC)
8
222
10
Apache 2.0
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 23 days ago (2026-08-13 05:59 UTC)
19
MIT
icogenie-mcp
albertnahas
A
license
Not graded
quality
C
maintenance
AI-powered SVG icon generation MCP server. Generate production-ready SVG icons from text descriptions with customizable styles, sizes, and themes.
Updated 6 months ago (2026-03-06 08:23 UTC)
44
6
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/Explorer-64/imagcon-mcp'

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