MCP Iconik
MCP server providing tools for the Iconik media asset management API. Supports assets, collections, search, metadata, jobs, users, groups, and more with dual transport (SSE and HTTP) and Docker support.
README
MCP Iconik
MCP (Model Context Protocol) server providing tools for the Iconik media asset management API.
Features
- Dual Transport Support: Both SSE (Server-Sent Events) and Streamable HTTP transports
- Docker Ready: Runs as a containerized service
- Comprehensive API Coverage: Tools for all major Iconik API endpoints
- Claude Code CLI Compatible: Works with Claude Code CLI
- LMStudio Compatible: Works with LMStudio via HTTP transport
Available Tools
Assets
iconik_list_assets- List assets with paginationiconik_get_asset- Get asset detailsiconik_create_asset- Create new asseticonik_update_asset- Update asset propertiesiconik_delete_asset- Delete an asset
Collections
iconik_list_collections- List collectionsiconik_get_collection- Get collection detailsiconik_create_collection- Create new collectioniconik_update_collection- Update collectioniconik_delete_collection- Delete collectioniconik_get_collection_contents- Get collection contentsiconik_add_to_collection- Add items to collection
Search
iconik_search- Search assets and collectionsiconik_list_saved_searches- List saved searchesiconik_get_saved_search- Get/execute saved searchiconik_create_saved_search- Create saved searchiconik_delete_saved_search- Delete saved search
Files & Storage
iconik_list_storages- List storage locationsiconik_get_storage- Get storage detailsiconik_get_asset_files- Get asset filesiconik_get_asset_formats- Get asset formatsiconik_get_asset_proxies- Get asset proxiesiconik_get_asset_keyframes- Get asset keyframes
Metadata
iconik_list_metadata_views- List metadata viewsiconik_get_metadata_view- Get metadata viewiconik_get_asset_metadata- Get asset metadataiconik_update_asset_metadata- Update asset metadata
Jobs
iconik_list_jobs- List jobsiconik_get_job- Get job detailsiconik_create_job- Create jobiconik_update_job- Update job
Users & Groups
iconik_list_users- List usersiconik_get_user- Get user detailsiconik_get_current_user- Get current usericonik_list_groups- List groupsiconik_get_group- Get group detailsiconik_list_shares- List sharesiconik_get_share- Get share detailsiconik_list_projects- List projectsiconik_get_project- Get project detailsiconik_list_webhooks- List webhooksiconik_get_webhook- Get webhook details
Generic
iconik_api_request- Make generic API requestsiconik_get_acls- Get object ACLsiconik_update_acls- Update object ACLs
Quick Start
Using Docker Compose
- Create a
.envfile with your Iconik credentials:
# Option 1: Use JWT API token
ICONIK_API=your_jwt_token_here
# Option 2: Use App ID and Auth Token
ICONIK_APP_ID=your_app_id
ICONIK_AUTH_TOKEN=your_auth_token
# Optional: Custom Iconik URL (default: https://app.iconik.io)
ICONIK_URL=https://app.iconik.io
- Build and run:
docker-compose up -d
- The server will be available at:
- SSE endpoint:
http://localhost:8000/sse - HTTP endpoint:
http://localhost:8000/mcp - Health check:
http://localhost:8000/health
- SSE endpoint:
Using Docker Directly
docker build -t mcp-iconik .
docker run -d \
-p 8000:8000 \
-e ICONIK_API=your_jwt_token \
--name mcp-iconik \
mcp-iconik
Local Development
# Install dependencies
pip install -e .
# Run the server
python -m mcp_iconik.server
Configuration with Claude Code CLI
Add to your Claude Code configuration (~/.claude/mcp.json):
{
"mcpServers": {
"iconik": {
"url": "http://localhost:8000/sse",
"transport": "sse"
}
}
}
Or for HTTP transport:
{
"mcpServers": {
"iconik": {
"url": "http://localhost:8000/mcp",
"transport": "http"
}
}
}
Configuration with LMStudio
LMStudio uses HTTP transport. Configure the MCP server URL as:
http://localhost:8000/mcp
API Endpoints
| Endpoint | Transport | Description |
|---|---|---|
/sse |
SSE | Server-Sent Events connection |
/messages/ |
SSE | SSE message handler |
/mcp |
HTTP | Streamable HTTP transport |
/health |
HTTP | Health check endpoint |
Environment Variables
| Variable | Description | Default |
|---|---|---|
ICONIK_API |
JWT API token (preferred) | - |
ICONIK_APP_ID |
Application ID | - |
ICONIK_AUTH_TOKEN |
Auth token | - |
ICONIK_URL |
Iconik base URL | https://app.iconik.io |
HOST |
Server host | 0.0.0.0 |
PORT |
Server port | 8000 |
DEBUG |
Enable debug mode | false |
Getting Iconik Credentials
- Log in to your Iconik instance
- Go to Admin Panel > Settings > Application Tokens
- Create a new application or use an existing one
- Create a new authentication token
- Copy the App ID and token
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。