Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@PindouAI MCP Server Show me recent patterns from the gallery."
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.
An official Model Context Protocol (MCP) server for PindouAI.
PindouAI is an advanced web application for converting images into high-quality Perler bead patterns, Hama bead templates, and pixel art blueprints. This MCP server allows AI assistants (like Claude, Cursor, and others) to interact directly with the PindouAI ecosystem.
get_recent_patterns: Fetches the most recent public creations from the PindouAI Gallery. Allows the LLM to showcase real examples of pixel art patterns created by the community.
get_website_url: Returns the official URLs for PindouAI services (Home, Generator, Gallery).
create_pixel_art: A pre-defined prompt that LLMs can use to instruct users on how to convert their images into Perler bead or pixel art patterns using the PindouAI Generator.
Related MCP server: Piskel MCP Server
To use this with Claude Desktop, add the following to your claude_desktop_config.json:
{
"mcpServers": {
"pindouai": {
"command": "npx",
"args": [
"-y",
"pindouai-mcp-server"
]
}
}
}To use this with Cursor, go to Cursor Settings > Features > MCP and add a new server:
Name: pindouai
Type: command
Command: npx -y pindouai-mcp-server
Clone this repository
Install dependencies:
npm installBuild the server:
npm run buildRun locally for testing:
npm startPindouAI (拼豆AI) provides tools for crafting enthusiasts and pixel artists:
AI Cartoonization: Convert photos into cute Chibi-style designs.
Auto Background Removal: Clean up images before pixelation.
Precise Color Matching: Automatically matches your image to real-world Perler, Hama, and Artkal bead palettes.
PDF Blueprints: Export your designs to highly detailed PDF blueprints for printing and crafting.
Visit pindouai.app to start creating!
This project is licensed under the MIT License.
Fetch the most recent public Perler bead and pixel art patterns from the PindouAI gallery.
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | The page number to fetch. Default is 1. |
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 only says 'fetch,' implying a read operation, but does not mention pagination behavior, response format, rate limits, authentication, or what 'most recent' entails. This is a significant gap for safe usage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that front-loads the action and resource, with zero unnecessary words. It is appropriately sized for the tool's simplicity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has one optional parameter and no output schema, and the description covers the core purpose. However, it omits details about the return value (list format, contents) and pagination behavior, making it only minimally complete for the context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides 100% coverage for the single 'page' parameter with a clear description and default value. The tool description adds no additional meaning about the parameter, so the baseline of 3 applies per the rubric.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb 'Fetch' and clearly identifies the resource: 'most recent public Perler bead and pixel art patterns from the PindouAI gallery.' This fully distinguishes it from the sibling tool 'get_website_url', which serves a different purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use this tool (when you need recent patterns) but does not explicitly state when to use it over alternatives or mention any exclusions. There is no guidance on selecting between this and 'get_website_url', leaving usage context only implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get the official URLs for PindouAI tools, such as the pattern generator and gallery.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the behavioral disclosure burden. 'Get' indicates a read-only operation, which is helpful, but the description does not disclose return format, error behavior, or whether the data is static or dynamic. With zero parameters, the tool is straightforward, but more detail would improve transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that clearly states the tool's purpose without unnecessary detail. It is well-structured and front-loaded, providing the key information efficiently.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's low complexity (no parameters, no output schema), the description is mostly complete. It names the resource and gives examples, but it could be more explicit about the return structure (e.g., whether it returns a single URL or a collection). Since the output schema is absent, a tiny bit more detail on the response format would push this to a 5.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema is empty (no parameters), and the description does not discuss parameters because there are none. Per the calibration baseline, zero parameters receive a 4. The description's examples add context but do not need to explain parameter semantics that do not exist.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves official URLs for PindouAI tools, with specific examples (pattern generator, gallery). The verb 'Get' and resource 'official URLs' are precise, and the tool is clearly distinct from its sibling get_recent_patterns, which focuses on patterns rather than URLs.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage when one needs website URLs for PindouAI tools, but it does not explicitly state when to use it versus alternatives or provide any exclusions. Since the tool is simple and the sibling tool serves a different purpose, the implied context is adequate but not explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.0.0get_recent_patternsget_website_urlThe two tools have clearly distinct purposes: one fetches pattern data, the other provides URLs. There is no overlap or ambiguity between them.
Both tools follow the same verb-noun convention with snake_case (get_recent_patterns, get_website_url). The pattern is consistent and predictable.
With only 2 tools, the server feels thin for a general-purpose API. However, the scope appears intentionally narrow, so the count is borderline but not extreme.
The tools cover basic access to recent patterns and URLs, but lack searching, filtering, or detailed retrieval. There are minor gaps that an agent might work around but not critical for the stated purpose.
Generate AI images, videos, music, SFX & speech in any AI assistant. Results appear inline in chat.
MCP tools for AI agents: render URLs to image/PDF, check link health, convert HTML/CSV/JSON.
Generate images, GIFs, and PDFs from HTML, URLs, or templates — from your AI agent.
Enable AI assistants to perform web searches using Perplexity's Sonar Pro.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/double2dev/pindou-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
