tapcolor-mcp
OfficialClick on "Deploy 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., "@tapcolor-mcpShow me TapColor's animal coloring collections"
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.
@tapcolorapp/mcp
MCP server for the TapColor Developer API — let AI assistants (Claude, ChatGPT, …) browse TapColor coloring categories and collections.
📚 Docs & live explorer: https://developer.tapcolor.app
🔑 Request an API key: https://tapcolor.app/contact/
Tools
Tool | Description |
| All 25 categories with collection & page counts. |
| Collections with optional |
Related MCP server: Civitai MCP Server
Use with Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"tapcolor": {
"command": "npx",
"args": ["-y", "@tapcolorapp/mcp"],
"env": { "TAPCOLOR_API_KEY": "YOUR_API_KEY" }
}
}
}Restart Claude Desktop, then ask: "List TapColor's animal coloring collections."
Use with any MCP client
The server speaks MCP over stdio. Run it directly:
TAPCOLOR_API_KEY=YOUR_API_KEY npx -y @tapcolorapp/mcpConfiguration
Env var | Required | Description |
| yes | Your TapColor API key (sent as the |
Built on the official @tapcolorapp/api client.
License
MIT © TapColor
Available Tools
2 toolslist_categoriesA
List all 25 TapColor coloring categories with the number of collections and pages in each. Use the returned slug as the category argument of list_coloring_pages.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden: 'List all 25' signals a bounded, non-mutating read and discloses the returned fields (counts per category). It omits auth or pagination behavior, but for a fixed-size read-only listing those are minor.
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?
Two tight sentences, no filler. The scope ('all 25 ... with counts') is front-loaded before the workflow hint, so the agent gets the essential facts first.
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?
No output schema exists, so the description must convey returns – it names categories, collection counts, page counts, and the slug. That is sufficient for a no-parameter listing tool, though the exact response shape (list vs object) remains unstated.
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?
Zero parameters, so baseline is 4. The description still adds value by explaining that the emitted `slug` is consumed as the `category` argument of the sibling tool, linking output to downstream input.
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?
States a specific verb ('List') and resource ('TapColor coloring categories') with concrete scope: exactly 25 categories and what each entry contains (collection and page counts). This is clearly distinguishable from the sibling list_coloring_pages.
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?
Explicitly tells the agent how this fits the workflow: the returned `slug` is the `category` argument for list_coloring_pages, implying this is the lookup step before listing pages. It does not state when NOT to use it, but the alternative relationship is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
list_coloring_pagesA
List TapColor coloring collections (subtopics), with optional category filter, name search and pagination. Returns public page URLs and cover images.
| Name | Required | Description | Default |
|---|---|---|---|
| q | No | Search collection names (partial, case-insensitive). | |
| limit | No | Page size 1–100 (default 20). | |
| offset | No | Pagination offset (default 0). | |
| category | No | Category slug, e.g. 'animals', 'disney'. Omit for all categories. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. It does disclose the return payload ('public page URLs and cover images'), which is useful, and 'List' implies a read-only operation. But it says nothing about pagination defaults/limits behavior, result ordering, or rate limits beyond what the schema states.
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?
Two tightly written sentences with the resource and filter set front-loaded and the return content trailing. No filler, though it is short enough that slightly more routing detail could have been added without bloat.
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?
For a four-parameter, no-required-field list tool with a fully documented schema, the description plus schema covers what an agent needs; there is no output schema, and the description compensates by naming the returned fields. The main gap is the absence of sibling-routing 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?
Schema description coverage is 100% (q, limit, offset, category all documented with types, ranges and defaults), so the baseline is 3. The description's mention of category filter, name search and pagination merely restates the schema without adding format or edge-case detail.
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?
States a specific verb ('List') and resource ('TapColor coloring collections (subtopics)') and enumerates the supported filters, so the agent knows exactly what comes back. It does not, however, explicitly distinguish itself from the sibling list_categories beyond the differing resource noun.
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 by listing optional filters, but never states when to choose this tool over list_categories or when not to call it (e.g. when you want category metadata rather than collections). Guidance is 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.
2 tool updates
v1.0.1- First observed
list_categories - First observed
list_coloring_pages
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: list_categories returns category metadata, while list_coloring_pages returns collections with filtering and pagination. There is no overlap, and the description explicitly links them via the category slug.
Both tools follow the same list_* snake_case verb_noun pattern, making the naming predictable and consistent.
With only 2 tools, the server is borderline thin for its apparent purpose of browsing a coloring content library. While each tool earns its place, the surface lacks the breadth typical of a 3–15 tool set.
The tools only cover listing categories and collections, with no way to retrieve individual coloring pages or list pages within a collection. This is a significant gap for an agent trying to access actual coloring content, likely causing workflow failures.
Maintenance
Related MCP Connectors
Create coloring pages and books. OAuth + Business plan required; AI generation uses credits.
Search and read the aicoolies catalog of AI and developer tools via a remote MCP knowledge graph.
Discover and retrieve published Amo.ng Prompts, Workflows, and Skills.
Discover, compare, route, and execute machine-accessible capabilities for AI agents.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceAllows AI agents to interact with a remote TMF620 Product Catalog Management API, enabling operations like listing, retrieving, and creating catalogs, product offerings, and product specifications.3MIT
- AlicenseNot gradedqualityDmaintenanceEnables interaction with the Civitai API to search for AI models, browse images, and access creator information. It provides tools for filtering models by popularity, rating, or type and retrieving detailed version metadata.MIT
- FlicenseNot gradedqualityDmaintenanceEnables agents to browse a catalog of OpenAPI specs, search for operations, and retrieve full operation contracts to build API requests without calling the target APIs.-
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to read-only access Catawiki auction marketplace data, including searching lots, inspecting items, browsing categories, and exploring auctions.MIT