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., "@Nasl3yn DataHub MCP Server Trace the lineage of the latest video render"
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.
Apache 2.0 License
An AI agent that gives video generation pipelines full context via DataHub's open-source Context Platform. Tracks video asset lineage, stores cinematic metadata schemas, and exposes MCP Server for autonomous video workflow orchestration.
Related MCP server: studio-state
┌─────────────────┐ ┌──────────────────┐ ┌─────────────────┐
│ Nasl3yn Agent │────▶│ DataHub MCP │────▶│ DataHub Graph │
│ (Orchestrator) │ │ Server + Skills │ │ (Cinematic) │
└─────────────────┘ └──────────────────┘ └─────────────────┘
│ │ │
▼ ▼ ▼
┌─────────────────┐ ┌──────────────────┐ ┌─────────────────┐
│ Video Pipeline │ │ Cinematic │ │ Asset Lineage │
│ (Airflow/DAG) │ │ Skills │ │ (Prompt→Output)│
└─────────────────┘ └──────────────────┘ └─────────────────┘# Install dependencies
pip install -e .
# Configure DataHub connection
export DATAHUB_GMS_URL="https://your-datahub-instance.com"
export DATAHUB_TOKEN="your-token"
# Run the agent
python -m nasl3yn_datahub.agent.main --config config.yamlnasl3yn-datahub-hackathon/
├── LICENSE # Apache 2.0
├── pyproject.toml # Package config
├── config.yaml.example # Configuration template
├── src/
│ └── nasl3yn_datahub/
│ ├── __init__.py
│ ├── api/ # DataHub API client
│ ├── mcp_server/ # MCP Server integration
│ ├── skills/ # DataHub Skills for cinematic ops
│ └── agent/ # Autonomous orchestrator
├── examples/ # Sample outputs for judges
├── tests/ # Unit tests
└── docs/ # Architecture docssrc/nasl3yn_datahub/api/)GraphQL/REST wrapper for DataHub
Asset CRUD, lineage, search
Authentication handling
src/nasl3yn_datahub/mcp_server/)Exposes cinematic operations to agents
Tools: create_asset, trace_lineage, query_metadata, register_pipeline
src/nasl3yn_datahub/skills/)VideoAssetSkill — register/track video assets
PipelineSkill — manage generation pipelines
LineageSkill — trace prompt→model→render→output
MetadataSkill — schema validation for cinematic metadata
src/nasl3yn_datahub/agent/)Autonomous video pipeline orchestration
Reads DataHub context via MCP
Plans and executes generation workflows
Writes results back to DataHub graph
# Video Asset Entity
urn: "urn:li:dataset:(urn:li:dataPlatform:nasl3yn,cinematic_asset,PROD)"
properties:
name: "scene_001_final_render"
description: "Final render of scene 1 - desert dawn"
customProperties:
prompt: "cinematic desert dawn, golden hour, 8k"
model: "veo-2"
resolution: "3840x2160"
duration_seconds: 8
codec: "hevc"
seed: 4294967295
generation_time_ms: 45000
cost_usd: 0.15Apache 2.0 — see LICENSE file.
This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
MCP server for Wan AI video generation
MCP server for Google Veo AI video generation
MCP server for ByteDance Seedance AI video generation
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/ahm22004/nasl3yn-datahub'
If you have feedback or need assistance with the MCP directory API, please join our Discord server