AI 코딩 어시스턴트에게 IMAGIN.studio 문서 전체에 대한 즉각적인 액세스 권한을 부여하세요 — CDN 구성, API 참조, 통합 가이드 등을 포함합니다.
하나의 도구. 하나의 명령어. 모든 주요 AI 코딩 어시스턴트와 호환됩니다.
에이전트의 MCP 구성에 다음을 붙여넣으세요:
{
"mcpServers": {
"imagin-docs": {
"command": "uvx",
"args": ["imagin-studio-api-docs-mcp"]
}
}
}또는 AI 어시스턴트에게 다음과 같이 요청하세요:
이 MCP 서버를 설치해줘: https://pypi.org/project/imagin-studio-api-docs-mcp/
Related MCP server: @ragrabbit/mcp
설치 — uvx imagin-studio-api-docs-mcp (복제, venv, 구성 불필요)
인덱싱 — 처음 실행 시 문서를 복제하고 로컬 벡터 인덱스를 구축합니다 (~30초 소요)
검색 — AI 어시스턴트가 search_docs를 호출하여 관련 문서를 찾습니다
최신 상태 유지 — 상위 문서가 변경되면 인덱스가 자동으로 업데이트됩니다
모든 작업은 로컬에서 실행됩니다. API 키나 외부 서비스가 필요하지 않습니다.
에이전트 | 구성 위치 |
Claude Code | 프로젝트 루트의 |
Claude Desktop |
|
Cursor | 설정 > 도구 & MCP |
Windsurf |
|
VS Code + Copilot |
|
Cline | MCP 서버 패널 |
Zed |
|
각 에이전트에 대한 자세한 설정 지침은 PyPI의 전체 설정 가이드를 참조하세요.
에이전트가 uvx를 찾을 수 없는 경우 (Claude Desktop 및 Cursor와 같은 GUI 앱에서 흔히 발생):
{
"mcpServers": {
"imagin-docs": {
"command": "npx",
"args": ["-y", "@imagin.studio/api-docs-mcp"]
}
}
}설치 후 다음과 같은 프롬프트를 시도해 보세요:
"IMAGIN 문서에서 CDN 캐시 무효화에 대해 검색해줘"
"IMAGIN으로 사용자 지정 도메인을 설정하려면 어떻게 해야 하나요?"
"이미지 변환을 위한 API 엔드포인트를 찾아줘"
"IMAGIN.studio는 어떤 이미지 형식을 지원하나요?"
레지스트리 | 패키지 | 설치 |
PyPI |
| |
npm |
|
Apache License 2.0 — LICENSE를 참조하세요.
Search the official IMAGIN.studio technical documentation, integration guides, and knowledge base.
Use this tool when the user asks 'How do I...' questions, needs explanation on API concepts (CDN, referrers, caching, 360 spinner), or needs to debug integration issues. Rewrite vague queries into specific technical search terms before calling.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Natural language search query. Use specific technical terms rather than vague descriptions. Good: "CDN cache invalidation headers". Bad: "caching stuff". | |
| top_k | No | Number of results to return (1-20, default 5). Use 1-3 for focused lookups, 5 for general questions, 10-20 for broad research. |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint true, idempotentHint true, destructiveHint false. The description adds that it searches specific content types but does not discuss rate limits, authentication, or result format. It adds some context but not rich behavioral detail.
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?
Three sentences, no redundant words. First sentence states purpose, second gives usage examples, third provides query rewriting advice. Front-loaded and efficient.
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 simple read-only search tool with good annotations and output schema, the description covers when to use and what to search. It could mention authentication scope or result limitations, but overall it's reasonably complete.
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 coverage is 100% with detailed descriptions for both parameters. The description does not add per-parameter details beyond the schema, so baseline score of 3 is appropriate.
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 searches official IMAGIN.studio technical documentation, integration guides, and knowledge base. This is specific and complete, with no sibling tools to distinguish from.
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 says when to use ('How do I' questions, API concepts, debug issues) and provides guidance to rewrite vague queries into specific terms. This is optimal usage guidance.
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.
v0.1.23search_docsWith only one tool, there is no possibility of confusion between different tools. The single tool is clearly described for its specific purpose.
The single tool name 'search_docs' follows a consistent verb_noun pattern, which is clear and predictable.
One tool is minimal and may feel insufficient for a documentation set; however, it might be acceptable if the scope is strictly limited to search. Still, it falls into the 'thin' category.
The tool covers the core search functionality, but lacks additional operations like retrieving a specific document or listing available topics, which could be useful for a documentation server.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
AI-native digital asset management: semantic search, generative image edits, and CDN delivery.
Upload, organize, search, and transform images, videos, and files with AI-powered tools.
Search the SiteGPT documentation: setup, features, API reference, troubleshooting.
Car logo API and image CDN: search automotive brands, fetch brand data, and build logo CDN URLs.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/IMAGIN-studio/api-docs-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
