Click 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., "@motion-previs-mcp Import this video and run full scene motion analysis."
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.
MCP (Model Context Protocol) stdio bridge for Motion Previs Studio — the open-source desktop app that turns real reference footage into AI-generator control packs. With this server connected, an AI agent can import a shot (local file or URL), trim the range, pick what to preserve (camera move, actor performance, object motion, or the full scene), run the analysis pipeline, watch its progress, export the bundle (depth passes, OpenPose skeleton video + keypoints, camera path, prompts), and send layers straight to the Blockout previs app.
Zero dependencies. Node ≥ 18. One file.
Motion Previs Studio v4.1+ must be running. Get it from the app repo (build from source or use a release DMG).
On launch, the app starts a localhost-only control server on a random port and writes a discovery file to ~/.config/motion-previs/control.json (random bearer token, mode 0600, removed on quit). This bridge reads that file automatically — nothing to configure, no credentials to enter.
Related MCP server: blockout-mcp
Add to ~/.hermes/config.yaml (or install from the Hermes MCP catalog once listed):
mcp_servers:
motion-previs:
command: "node"
args: ["/absolute/path/to/motion-previs-mcp/motion-previs-mcp.mjs"]claude mcp add motion-previs -- node /absolute/path/to/motion-previs-mcp/motion-previs-mcp.mjs{ "mcpServers": { "motion-previs": { "command": "node", "args": ["/absolute/path/to/motion-previs-mcp/motion-previs-mcp.mjs"] } } }get_state · import_file · import_url · set_range · set_mode · set_settings · run_analysis · export_pack · list_bundle · send_to_blockout · screenshot
The agent workflow: import_file/import_url → set_range + set_mode (camera_only | actor_motion | object_motion | full_scene) → run_analysis → poll get_state until analysis.status is done → export_pack → optionally send_to_blockout (reference / depth / ai_depth / pose / openpose).
The app's control server binds to 127.0.0.1 only, uses a per-launch random bearer token, and validates every action against a whitelist. Nothing is exposed off-machine.
Apache-2.0 — see LICENSE. Per the NOTICE file, use, forks, and redistribution must credit Sam Wasserman (wassermanproductions.com).
This server cannot be deployed
Build editable 3D scenes, direct characters and cameras, and export AI video references with MCP.
Video production studio for AI agents: AI media, motion graphics as code, timeline and export.
Plan, compare, price, generate, and recover AI video from compatible MCP clients.
Compose, edit and render video with your AI agent. Turn footage into finished edits with content-aware reframing, word-timed captions and motion graphics. Hosted MCP with OAuth sign-in; cloud processing uses credits.
