Generate Wan 3.0 AI videos, estimate credit costs, and track video generation tasks through an AI assistant.
Also known as NotUsingGithub/wan30-mcp, wan30-mcp, @wan30/cli
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 0.1.0
- Last commit
- Nov 12, 2026
- License
- MIT
What is Wan30 MCP?
Wan30 generates Wan 3.0 AI videos, estimate credit costs, and track video generation tasks through an AI assistant.
Summary generated from the project's README
About Wan30 MCP server
Wan30 MCP allows developers to integrate Wan 3.0 AI video generation directly into their AI assistants. By connecting this local stdio server to clients like Claude or Codex, users can manage video creation tasks through natural language. The server requires a wan30.video account with purchased credits to function, as it uses the same credit balance and pricing as the official website.
Users can interact with several specific tools including account_status, list_models, estimate_generation, and generate_video. The system supports text-to-video, image-to-video, and reference-to-video modes with resolutions ranging from 480p to 1080p. It is designed for macOS and Linux environments, utilizing the macOS Keychain or a local file for credential storage. This setup enables automated workflows where an assistant can check account balances and estimate costs before initiating a generation task.
What you can do with it
- 1Estimate video generation costsAsk the assistant to calculate how many credits a specific video request will consume before starting the process.
- 2Create videos from text promptsInstruct the AI to generate a five second 720p video of a paper boat on a rainy street.
- 3Animate static imagesProvide an image URL to the assistant to transform a still photo into a video sequence.
- 4Monitor active generation tasksRequest a list of all current or past video generation tasks to track their progress.
Written from the project's README. Every use case is checked against a quote from it.
How to install Wan30 MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Wan30 MCP in Claude Code
$ claude mcp add wan30-mcp -- npx -y @wan30/cliInstall Wan30 MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"wan30-mcp": {
"command": "npx",
"args": [
"-y",
"@wan30/cli"
]
}
}
}Install Wan30 MCP in VS Code
.vscode/mcp.json
{
"servers": {
"wan30-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@wan30/cli"
]
}
}
}Install Wan30 MCP in VS Code CLI
$ code --add-mcp '{"name":"wan30-mcp","type":"stdio","command":"npx","args":["-y","@wan30/cli"]}'Install Wan30 MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"wan30-mcp": {
"command": "npx",
"args": [
"-y",
"@wan30/cli"
]
}
}
}Install Wan30 MCP in Codex
$ codex mcp add wan30-mcp -- npx -y @wan30/cliInstall Wan30 MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.wan30-mcp] command = "npx" args = ["-y", "@wan30/cli"]
Install Wan30 MCP in Gemini CLI
$ gemini mcp add -s user wan30-mcp npx -- -y @wan30/cliInstall Wan30 MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"wan30-mcp": {
"command": "npx",
"args": [
"-y",
"@wan30/cli"
]
}
}
}Automated checks
Ran Nov 14, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablenotusinggithub/wan30-mcp is public and reachablegithub.com/notusinggithub/wan30-mcp ↗Pass
- Package names this repository as its source@wan30/cli names notusinggithub/wan30-mcp as sourcenpmjs.com/package/@wan30/cli ↗Pass
- Build provenance (Sigstore attestation)No build attestation published for this releaseNot checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-12github.com/notusinggithub/wan30-mcp ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from @wan30/cliPass
- No critical advisory in the package or its dependenciesthe package checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubWan30 MCP and CLI — Wan 3.0 AI Video Generation
Generate Wan 3.0 videos from your terminal or AI assistant with your wan30.video account. MCP and CLI spend the same credit balance as the website, at the same prices. Credits are bought on the website.
Access requires remaining purchased credits. Sign-up, check-in and gift credits alone do not qualify. Buy credits at https://wan30.video/pricing/.
Node 22+, macOS or Linux (including WSL).
Install
npm install -g @wan30/cli
Use
wan30 auth login
wan30 account
wan30 models
wan30 estimate --input request.json
wan30 create --input request.json --wait
wan30 download <taskId> --output result.mp4
wan30 auth logout
On Linux, sign in with wan30 auth login --credential-store file.
request.json examples. Text to video:
{"modelId":"wan30-text-to-video","prompt":"A paper boat on a rainy street","durationSeconds":5,"resolution":"720p"}
Image to video, with one HTTPS image as the first frame:
{"modelId":"wan30-image-to-video","prompt":"The crane takes off","imageUrls":["https://example.org/first-frame.jpg"]}
Reference to video, with 1–10 HTTPS reference images:
{"modelId":"wan30-reference-to-video","prompt":"Move the camera slowly toward the scene","imageUrls":["https://example.org/reference.jpg"]}
Every mode takes 2–30 seconds and 480p, 720p or 1080p. The default is 5
seconds at 480p. wan30 model <modelId> prints every option as a JSON Schema.
create prints a request ID on stderr. Re-running it with
--request-id <id> after a network error returns the same task and is never
charged twice. A wait timeout only stops waiting; the task keeps running.
Credentials are stored in the macOS Keychain, or with
--credential-store file in a private file (directory 0700, file 0600).
WAN30_CONFIG_DIR changes that directory. WAN30_ACCESS_TOKEN accepts a
pre-issued access token for automation. Logging out revokes this connection;
changing your website password revokes every connection.
Connect an assistant (local MCP)
Sign in once with wan30 auth login, then register the stdio server:
codex mcp add wan30 -- wan30 mcp
claude mcp add wan30 -- wan30 mcp
Tools: account_status, list_models, get_model, estimate_generation,
generate_video, list_tasks, get_task.
Clients that accept JSON configuration can launch the same stdio server with npx:
{
"mcpServers": {
"wan30": {
"command": "npx",
"args": ["-y", "@wan30/cli", "mcp"]
}
}
}
The server starts and lists its tools before you sign in. A tool call made
without a sign-in tells the assistant to run wan30 auth login; no restart is
needed afterwards.
Read the account status and estimate the cost before generating. Video generation spends your website credits.
Documentation and support
- Wan30 website
- MCP setup and client instructions
- CLI installation
- MCP and CLI usage guide
- Credit packs
- Issue tracker
License
MIT. The hosted generation service is operated at wan30.video.
Wan30 MCP questions
How do I add Wan30 MCP to Claude Code?
Run claude mcp add wan30-mcp -- npx -y @wan30/cli in your terminal. Add --scope user to make it available in every project.
How do I add Wan30 MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
How do I pay for video generation?
You must purchase credits on the Wan30 website; sign-up, check-in, and gift credits do not qualify for generation.
Can I estimate the cost before generating a video?
Yes, you can use the estimate tool to check the cost before starting a generation task.
What happens if a network error occurs during a request?
You can re-run the command with the specific request ID to return to the same task without being charged twice.
Where are my credentials stored?
Credentials are saved in the macOS Keychain or in a private file if you specify a credential store.