vimax-mcp
Leverages Google AI APIs (e.g., Veo) for video generation, controlled via the server's tools.
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., "@vimax-mcpgenerate a video from this screenplay about space exploration"
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.
vimax-mcp
MCP server wrapping ViMax for use across multiple CLI clients (Claude Code, Codex, Gemini, Kimi, …).
Implements proposal §1 of ~/projects/ViMax/docs/MCP_PROPOSAL.md.
Status
Steps 1-3 done: 6 tools, stdio + SSE transports, daily-quota gate, launchd agent template, multi-CLI configuration snippets.
Tools
Tool | Purpose |
| Kick off idea → video. Returns |
| Same, but starting from a screenplay. |
| State + progress (inferred from working_dir contents) + errors. |
| List job output files, filterable by |
| Stop a running or queued job; working_dir preserved. |
| Today's used / limit for chat / image / video (UTC day, resets at midnight UTC). |
Requirements
Python 3.12+,
uvA ViMax checkout at
$VIMAX_HOME(defaults to~/projects/ViMax)ViMax already wired with
MINIMAX_API_KEYandGOOGLE_API_KEYenv vars (see ViMax fork's.env.example)
Run
cd ~/projects/vimax-mcp
uv sync
# stdio (default — used when wired into a CLI client)
uv run python -m vimax_mcp.server
# SSE (HTTP, share across all CLI clients on this machine)
uv run python -m vimax_mcp.server --transport sse --port 7801Wire to Claude Code
stdio (per-CLI subprocess) — ~/.claude/.mcp.json or project .mcp.json:
{
"mcpServers": {
"vimax": {
"command": "uv",
"args": ["run", "--directory", "/Users/zcdeng/projects/vimax-mcp",
"python", "-m", "vimax_mcp.server"]
}
}
}SSE (shared instance, recommended for multi-CLI) — run vimax-mcp --transport sse once (e.g. via launchd in step 3), then point each client at it:
{
"mcpServers": {
"vimax": {
"transport": "sse",
"url": "http://127.0.0.1:7801/sse"
}
}
}Environment
Var | Default | Purpose |
|
| Path to ViMax checkout (added to |
|
| Per-job output root |
|
| Persisted daily-quota counter |
|
|
|
|
| SSE bind host |
|
| SSE bind port |
|
| Log level |
| — | Forwarded to ViMax chat model |
| — | Forwarded to ViMax image/video generators |
Deploy as a launchd agent (recommended on macOS)
./scripts/install-launchd.sh # install or refresh
./scripts/install-launchd.sh status # show launchctl print + log tails
./scripts/install-launchd.sh remove # uninstallThe template at launchd/com.zcdeng.vimax-mcp.plist is rendered into
~/Library/LaunchAgents/com.zcdeng.vimax-mcp.plist with your $HOME
and absolute uv path substituted. The agent runs vimax-mcp
--transport sse --port 7801 and restarts on crash.
Secrets are not stored in the plist. The server loads
$VIMAX_HOME/.env on boot (see vimax_mcp/dotenv.py).
Verify:
curl -sI http://127.0.0.1:7801/sse | head -1 # → 200 OK
tail -f ~/projects/ViMax/.working_dir/logs/mcp.{out,err}.logWire into your CLI clients
Ready-to-copy snippets live in clients/:
File | Target |
|
|
| Append to |
Tests
uv run pytestSmoke tests cover JobRegistry, artifact scanning, FastMCP tool registration, and a full stdio JSON-RPC handshake. They do not invoke ViMax pipelines or consume Veo / MiniMax quota.
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/ZCDeng/vimax-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server