Skip to main content
Connect any MCP-compatible AI agent to VMEG by manually adding the remote MCP endpoint and your API Key. Your agent can list materials, create translation tasks, edit drafts, and poll job status — using the same account credits as the website.
Marketplace / app-store connectors are not supported yet. Use manual setup with an API Key for now.

​
Remote MCP endpoint

Point your MCP client at: 
{mcpUrl}
The server uses Streamable HTTP (Spring AI MCP Server, sync tools).

​
Authentication

Recommended today: if your client supports a Bearer token, send your API Key on every MCP request (same key as the Open API): 
Authorization: Bearer YOUR_API_KEY
Create and rotate keys on API Configuration.
ModeStatusNotes
API Key (Bearer)SupportedManual MCP config in Cursor or any compatible client. Key from API Configuration.
OAuth 2.1 (PKCE)Available on serverFor future connector flows; not needed for manual setup.
You do not pass projId in MCP tool arguments. The authenticated project comes from your API Key (or OAuth token when using connectors later).

​
What you can do

Once connected, your agent can call tools for:
  • Materials — list, upload (POST /api/mcp/material/upload), delete
  • Tasks — create video/audio/subtitle translation, list and poll status, delete
  • Voices — list system and cloned voices for manual voice selection
  • Editor workflows — query scripts/subtitles/ASR/speakers/tracks, save draft edits, re-translate, trigger TTS, compose final render
See the full MCP tools reference for every tool name and description.

​
Typical flow

1

Connect manually

Add {mcpUrl} to your MCP client and set Authorization: Bearer plus your API Key. See Setup.
2

Provide media

Upload a file (POST /api/mcp/material/upload), pick from vmeg_list_materials, or pass a YouTube URL.
3

Create a task

Call vmeg_create_video_translation_task or vmeg_create_subtitle_translation_task with targetLanguage and a media source.
4

Poll and edit

Use vmeg_list_tasks and editor tools to query content, save draft changes, re-dub, or compose the final output.
Tasks are asynchronous. Creating a job returns a taskId and editorUrl; poll until the task finishes.

​
Remote MCP vs Open API

Remote MCPOpen API
SetupManual MCP URL + API KeyAPI Key only
Hostwww.vmeg.ai (/api/mcp)api.vmeg.ai (/openapi/v1/**)
Best forAI agents (conversational workflows)Your backend (REST integration)
BillingAccount credits (same plan)Account credits (same plan)
Both access the same VMEG project, materials, and tasks.

​
FAQ

Do I need a separate MCP API Key?
No. Reuse the same API Key as the Open API — send it as the Bearer token. Can I install VMEG from the Cursor marketplace or ChatGPT app store?
Not yet. Use manual setup until marketplace connectors are published. Does MCP cost extra?
No. Tool calls consume the same credits as tasks created on vmeg.ai. See Pricing. Can I use MCP and the Open API together?
Yes. They operate on the same project scope; choose MCP for agents and REST for programmatic backends. Why does the agent ask me to confirm before delete or compose?
Delete tools (vmeg_delete_material, vmeg_delete_task) and destructive editor actions require explicit user confirmation by design.