Spiritme MCP. Automate multilingual video generation with avatars.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Spiritme MCP Server lets your AI client generate high-fidelity, multilingual videos using digital human avatars. You can programmatically list avatar portfolios, trigger video generation jobs for specific scripts and voices, and monitor job status in real time—all through simple natural language commands.
What your AI agents can do
Check spiritme status
Verifies the current API connectivity status with Spiritme.
Delete video
Removes a specific video asset from your account.
Generate audio
Creates an audio file based on provided text input.
List all available digital avatars in your portfolio, retrieving technical metadata and SKU IDs for programmatic use.
Submit jobs to create full videos or just audio tracks using specified scripts, templates, and voice selections.
Fetch specific details about avatars (get_avatar), available video templates (get_template), or voices (get_voice) before starting a job.
Check the real-time status of any submitted video generation job, getting instant confirmation when assets are ready.
Access your full directory of hosted video assets to see what's already created and where it lives.
Ask AI about this MCP
Supported MCP Clients
OAuth 2.0 Compatible Gemini Waiting for input…
Spiritme MCP Server: 12 Tools for Media Production
These tools let your AI client interact directly with Spiritme's core services to manage avatars, generate media, and monitor video jobs.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using Spiritme on Vinkius019dd164check spiritme status
Verifies the current API connectivity status with Spiritme.
019dd164delete video
Removes a specific video asset from your account.
019dd164generate audio
Creates an audio file based on provided text input.
019dd164generate video
Triggers the creation of a full video asset using specified inputs.
019dd164get avatar
Retrieves detailed information for a single digital avatar by its ID.
019dd164get job status
Checks the real-time status and results of a submitted video generation job.
019dd164get template
Retrieves metadata for available video templates.
019dd164get voice
Fetches details about available synthetic voices, including language and accent information.
019dd164list avatars
Retrieves a full list of all digital avatars you own or can access.
019dd164list templates
Returns a catalog listing all available video templates.
019dd164list videos
Generates a list of your previously created and hosted video assets.
019dd164list voices
Retrieves a complete catalogue of available voices for selection.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Spiritme, then connect any of our 5,000+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,000+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Spiritme. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 12 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Tracking video assets shouldn't take 10 clicks across different dashboards.
Today, tracking a single campaign’s video output means jumping between the dashboard to see asset counts, then checking job status in one tab, and finally pulling metadata for every avatar used into a spreadsheet. It's slow, it breaks focus, and you lose time copying IDs.
With this MCP server, your agent handles the whole stack. You ask about assets, and it runs `list_videos` or `get_job_status`. The result is a single, immediate data response that lets you move on. No clicks needed.
Spiritme MCP Server: Programmatically create multilingual video content.
Before this, generating personalized videos for five global branches required a dedicated team member to manually submit and monitor five separate jobs—a multi-hour process of API calls and status checks. You were bottlenecked by the UI itself.
Now, you simply instruct your agent: 'Create a localized video set.' It executes `generate_video` across multiple language/avatar combinations in sequence, giving you coordinated service scaling without human intervention.
What you can do with this MCP connector
You've got a bunch of video assets to manage, and you don't wanna deal with a web dashboard or manual status checks. This server lets your AI client handle the entire lifecycle of high-fidelity digital video content through simple commands.
First off, before you run anything else, you can use check_spiritme_status to verify that the API connection is up and running right now. If everything's green, you're good to go.
To get started on a project, your AI client first needs to know what avatars it's dealing with. You can run list_avatars to pull a complete inventory of every digital person you own or have access to. Need more detail on one specific face? Use get_avatar and pass in the ID; that pulls all the technical metadata, including the SKU IDs you need for generation.
If you're building out a script from scratch, your agent needs supporting media first. You can run list_voices to see every synthetic voice available, checking things like language and accent details using get_voice. If you also gotta pick a visual style, running list_templates gives you the whole catalog of video layouts, and then get_template pulls all the metadata for a specific template.
For your content library, you can use list_videos to see a full list of every video asset you've created and where it lives. If you need to clean things up or remove an old file, delete_video takes out that specific video from your account.
Now for the generation part—the fun stuff. You can programmatically create just audio tracks using generate_audio, simply feeding in text, and the server handles the rest. If you're ready to make a whole video, you trigger it with generate_video. That job requires specific inputs: you gotta specify your script, which template you want to use, and which voice selection you’ve chosen.
When you submit a job using generate_video, the AI client doesn't just forget about it. You can track everything by running get_job_status. This checks the real-time status of that video generation job, giving you instant confirmation when all your assets are ready and available for download.
It’s a full loop: Your agent first pulls configuration details—listing avatars with list_avatars, checking templates with list_templates, and getting detailed voice info with list_voices. Then it uses that data to call generate_video or generate_audio. Finally, it monitors the process using get_job_status until everything's done. You can even check your existing work anytime by calling list_videos.
019dd165-1926-7139-905f-6d4a9f84ea9a 
How Spiritme MCP Works
- 1 First, subscribe to the Spiritme server. Then, grab your API Key from the dashboard (Settings > API).
- 2 Next, tell your AI client exactly what you need—for example, 'Generate a video with avatar av_123 using this script.'
- 3 The agent runs the necessary tools (
generate_video,list_avatars) and returns job IDs or asset URLs. You then useget_job_statusto track completion.
The bottom line is, your AI client manages video creation and status checks without you ever opening a web browser.
Who Is Spiritme MCP For?
This server targets content teams that are constantly producing localized or personalized media. It's for the Content Marketer who needs to scale videos across different regions, the Training Coordinator who must update employee assets frequently, and any Developer building automated pipelines that rely on high-fidelity video outputs.
Needs to trigger personalized video messages for campaigns instantly and monitor job status without leaving their primary workflow.
Must verify individual avatar metadata and track the generation of training videos across multiple team members' profiles.
Integrates Spiritme data into custom pipelines, using simple AI queries to handle video asset creation or audio extraction.
What Changes When You Connect
- You get instant job status updates. Instead of checking a dashboard, running
get_job_statusgives you the current progress and final URL as soon as it's ready. - Manage your entire portfolio from chat. Use
list_avatarsto see every avatar SKU ID without logging into the web portal, making data retrieval fast. - Build structured content pipelines. By using
get_templateandget_voice, you ensure that any generated video follows brand guidelines before submission. - Scale multilingual production easily. You can run
generate_videofor different language scripts and voices in a single prompt, drastically cutting down manual work. - Keep track of everything. After running
list_videos, your agent shows you exactly how many assets are active, giving an immediate resource count.
Real-World Use Cases
Need to localize a message for 5 countries
A marketing manager needs five versions of the same product announcement. Instead of manually creating five separate video jobs, they prompt their agent: 'Generate videos using avatar av_123 with scripts in Spanish, French, German, Italian, and Japanese.' The agent runs generate_video multiple times, handling all the necessary multilingual calls.
A training team needs to audit avatars
The L&D specialist wants to know which avatar IDs are available for a new department video. They prompt: 'List all avatars.' The agent runs list_avatars, returning the full technical portfolio list, allowing them to verify metadata before writing scripts.
A developer needs an asset ID check
The automation developer's script fails because it can't find a template. They ask their agent: 'Check available templates.' The agent runs list_templates, providing the required structured data so the script can proceed with generate_video.
Need to verify video job completion
A user submitted a complex, long-running video generation request and needs an update. They ask: 'What's the status of job XYZ789?' The agent immediately runs get_job_status, confirming if it succeeded or providing details on why it stalled.
The Tradeoffs
Treating video generation as a single call
Trying to prompt the agent with 'Make me a cool video.' without specifying an avatar ID, voice, or template. The job will fail because it lacks necessary parameters.
→
Always start by listing options. Use list_avatars first to get the correct ID, then use get_voice to select the right language/accent, and finally run generate_video with all three pieces of data.
Manually checking asset status
Constantly opening the Spiritme web dashboard to see if a job finished. This wastes time and is non-scalable.
→
Rely entirely on get_job_status. Your agent monitors this tool, giving you an immediate notification when 'DONE' status hits, so you don't have to poll the UI.
Overlooking resource availability
Attempting to generate a video using a template or voice that doesn't exist in your account.
→
Before generating, run list_templates and list_voices. This confirms the necessary resources are available before you submit the costly generate_video request.
When It Fits, When It Doesn't
Use this server if your core workflow involves programmatic video asset creation using digital avatars. You need to manage multilingual content, track complex job statuses, or programmatically interact with metadata like avatar IDs and template names. If you only need simple editing (e.g., trimming a clip) or generating basic graphics without human presenters, this server is overkill—look for general media editing APIs instead. Don't use it if your primary goal is simply storing files; use list_videos to confirm existence, but the tool isn't designed for file storage management itself.
Common Questions About Spiritme MCP
How do I find out what avatars are available using list_avatars? +
You run list_avatars. This returns a complete portfolio listing. The metadata you get back includes the necessary SKU IDs and technical details required to use them in other tools.
Does generate_video handle multiple languages at once? +
Yes, it can. You pass the script/language options directly into the generate_video tool call. This allows you to orchestrate multilingual content creation efficiently in one sequence.
What if my video job fails? How do I check that with get_job_status? +
The get_job_status tool will return the current status, including error codes or messages. This helps you pinpoint exactly which step failed, saving debugging time.
Can list_voices help me pick the right accent for my message? +
Absolutely. Running list_voices gives you details on available voices. You can check if a specific language and required regional accent (like British English vs. American) is supported.
How do I verify my API credentials are working before generating content using check_spiritme_status? +
It immediately checks your connectivity status. Running this tool verifies that your API key is active and connected to the Spiritme platform, confirming you're ready for high-fidelity video jobs.
If I need to remove old or unused files, how do I use the delete_video tool? +
The tool deletes specific videos from your hosted assets. You pass the ID of the asset you want gone; it handles the removal request directly through the API.
What details does list_videos provide when I need to audit my entire content library? +
It retrieves a comprehensive directory listing of all your existing video assets. This lets you see metadata, SKU IDs, and status for every piece of media in your portfolio.
If I need technical specs on an avatar, how do I use the get_avatar tool? +
It pulls detailed technical metadata about a specific digital human. This includes critical information like SKU IDs and physical parameters, which is essential for automated pipeline integration.
How do I find my Spiritme API Key? +
Log in to your account, navigate to Settings > API, and copy your unique access token from the credentials section.
Can I check the status of a video job via AI? +
Yes! The get_spiritme_job_status tool allows your agent to poll the high-fidelity real-time status of any generation request.
How do I list my available avatars? +
Use the list_spiritme_avatars tool to retrieve your complete high-fidelity directory along with the unique identifiers for all managed digital actors.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.