1. Conduid
  2. Content
  3. Autovio
MCP server · Content

Autovio

· github.com/Auto-Vio/autovio-mcp

Open-source AI video pipeline. Text prompt → scenario → images → video clips → editor → MP4. Self-hosted, multi-provider, MCP-ready.

Unclaimed aiai-videoclaudedall-effmpeggeminigenerative-aillmmcpopen-sourceopenairunwayself-hostedtext-to-videotypescriptveovideo-automationvideo-editorvideo-generationvideo-pipeline
InstallView source
39Low

Scored 6 days ago · breakdown

About Autovio

Autovio is an MCP server in the Content category: open-source AI video pipeline. Text prompt → scenario → images → video clips → editor → MP4. Self-hosted, multi-provider, MCP-ready.

The repository has 32 stars and 0 forks.

Install

Claude Code
claude mcp add autovio -- npx -y autovio-mcp
npx
npx -y autovio-mcp

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Tools (27)

autovio_ai_analyze_videoAnalyze reference video for style/tone

Parameters not published.

autovio_ai_generate_imageGenerate image from prompt

Parameters not published.

autovio_ai_generate_scenarioGenerate scene-by-scene scenario

Parameters not published.

autovio_ai_generate_scenario_for_workGenerate scenario attached to a work

Parameters not published.

autovio_ai_generate_sceneGenerate image + video for one scene

Parameters not published.

autovio_ai_generate_videoAnimate image into video clip

Parameters not published.

autovio_auth_loginLogin (email + password)

Parameters not published.

autovio_auth_meCurrent user info

Parameters not published.

autovio_auth_registerRegister new user

Parameters not published.

autovio_healthAPI health check

Parameters not published.

Show all 27 tools
autovio_projects_createCreate project

Parameters not published.

autovio_projects_deleteDelete project

Parameters not published.

autovio_projects_getGet project details

Parameters not published.

autovio_projects_listList projects

Parameters not published.

autovio_projects_updateUpdate project

Parameters not published.

autovio_providers_listList available AI providers

Parameters not published.

autovio_templates_createCreate template

Parameters not published.

autovio_templates_deleteDelete template

Parameters not published.

autovio_templates_getGet template details

Parameters not published.

autovio_templates_listList templates

Parameters not published.

autovio_templates_updateUpdate template

Parameters not published.

autovio_works_apply_templateApply template to work

Parameters not published.

autovio_works_createCreate work

Parameters not published.

autovio_works_deleteDelete work

Parameters not published.

autovio_works_getGet work details

Parameters not published.

autovio_works_listList works

Parameters not published.

autovio_works_updateUpdate work

Parameters not published.

Ask AI

✦

Ask AI about Autovio

Powered by Claude · Grounded in docs

I know everything about Autovio. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

  • ✓README presentThe repository ships documentation.

5 checks have not been run yet.

README

AutoVio MCP Server

npm version

MCP server for the AutoVio AI video generation pipeline. Connects Claude Code, Claude Desktop, Cursor, and any MCP-compatible client to the AutoVio API — no clone or build required.

Installation

No installation needed. Use npx to run the server directly:

npx autovio-mcp --autovio-base-url http://localhost:3001 --autovio-api-token YOUR_TOKEN

Or install globally:

npm install -g autovio-mcp
autovio-mcp --autovio-base-url http://localhost:3001 --autovio-api-token YOUR_TOKEN

Quick Start

Claude Code

claude mcp add autovio-mcp -- npx -y autovio-mcp \
  --autovio-base-url http://localhost:3001 \
  --autovio-api-token YOUR_TOKEN \
  --llm-model gemini-2.5-flash \
  --llm-api-key YOUR_KEY \
  --image-model gemini-2.5-flash-image \
  --image-api-key YOUR_KEY \
  --video-model veo-3.0-generate-001 \
  --video-api-key YOUR_KEY

Claude Desktop / Cursor

Add to your claude_desktop_config.json (or equivalent MCP config):

{
  "mcpServers": {
    "autovio": {
      "command": "npx",
      "args": [
        "-y", "autovio-mcp",
        "--autovio-base-url", "http://localhost:3001",
        "--autovio-api-token", "YOUR_TOKEN",
        "--llm-model", "gemini-2.5-flash",
        "--llm-api-key", "YOUR_KEY",
        "--image-model", "gemini-2.5-flash-image",
        "--image-api-key", "YOUR_KEY",
        "--video-model", "veo-3.0-generate-001",
        "--video-api-key", "YOUR_KEY"
      ]
    }
  }
}

Configuration

Config is loaded from four sources in priority order: CLI flags > environment variables > config file > defaults.

CLI flags

Flag Description
--autovio-base-url AutoVio API base URL (default: http://localhost:3001)
--autovio-api-token AutoVio API token
--config Path to a JSON config file
--vision-model Vision model (e.g. gemini-2.0-flash-exp)
--vision-api-key Vision API key
--llm-model LLM model (e.g. gemini-2.5-flash)
--llm-api-key LLM API key
--image-model Image model (e.g. gemini-2.5-flash-image)
--image-api-key Image API key
--video-model Video model (e.g. veo-3.0-generate-001)
--video-api-key Video API key
--log-level debug | info | warn | error
--enable-resources true | false
--enable-prompts true | false

CamelCase variants (e.g. --autovioBaseUrl) are also accepted.

Environment variables

AUTOVIO_BASE_URL        AUTOVIO_API_TOKEN
AUTOVIO_VISION_MODEL    AUTOVIO_VISION_API_KEY
AUTOVIO_LLM_MODEL       AUTOVIO_LLM_API_KEY
AUTOVIO_IMAGE_MODEL     AUTOVIO_IMAGE_API_KEY
AUTOVIO_VIDEO_MODEL     AUTOVIO_VIDEO_API_KEY
AUTOVIO_LOG_LEVEL       AUTOVIO_MCP_CONFIG

Config file

Pass a JSON file with --config path/to/config.json. See examples/config.example.json for the full structure.

Available Tools

Tool Description
autovio_health API health check
autovio_auth_login Login (email + password)
autovio_auth_register Register new user
autovio_auth_me Current user info
autovio_projects_list List projects
autovio_projects_create Create project
autovio_projects_get Get project details
autovio_projects_update Update project
autovio_projects_delete Delete project
autovio_works_list List works
autovio_works_create Create work
autovio_works_get Get work details
autovio_works_update Update work
autovio_works_delete Delete work
autovio_works_apply_template Apply template to work
autovio_ai_analyze_video Analyze reference video for style/tone
autovio_ai_generate_scenario Generate scene-by-scene scenario
autovio_ai_generate_scenario_for_work Generate scenario attached to a work
autovio_ai_generate_image Generate image from prompt
autovio_ai_generate_video Animate image into video clip
autovio_ai_generate_scene Generate image + video for one scene
autovio_providers_list List available AI providers
autovio_templates_list List templates
autovio_templates_get Get template details
autovio_templates_create Create template
autovio_templates_update Update template
autovio_templates_delete Delete template

Requirements

  • Node.js >= 18
  • A running AutoVio backend
  • An AutoVio API token (or use autovio_auth_login to get one)
  • API keys for the AI providers you want to use

Links

License

MIT

README copy captured when this server was indexed; it may lag the repository. The original is authoritative.

Questions

About Autovio

How do I install Autovio?

Run claude mcp add autovio -- npx -y autovio-mcp, then add the server to your MCP client's configuration.

Is Autovio safe to use with an AI agent?

Its trust score is 39 out of 100 (low). It passes 1 of the 1 static security checks run so far. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Autovio still maintained?

Conduid hasn't recorded a commit date for this repository yet. Check the repository directly for recent activity.