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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.