@instavar/mcp-server
This server lets you manage the full Instavar Studio video workflow — from creation to publishing and analytics — via MCP.
Video Job Management
List recent video jobs, optionally filtered by status
Retrieve detailed job status including runs, artifacts, verifications, and media URLs
Access the materialized composition state (scenes, duration, aspect ratio, etc.) for a job
Video Creation & Editing
Create new video jobs from a structured brief (title, script, caption, scenes, objective, aspect ratio, publish target), triggering the render pipeline
Edit existing job briefs (script, caption, title, scenes, objective, aspect ratio); most changes trigger a re-render automatically
Modify a job's publish target without triggering a re-render
Approval & Publishing
Approve a rendered job to make it publishable and revoke review links
Publish an approved job to a connected social destination (LinkedIn, X, TikTok, YouTube, Instagram, Threads, Facebook, RedNote, Lemon8), with platform-specific options (e.g., TikTok post mode, YouTube privacy status) and QA/AI disclosure overrides
Metrics & Costs
Get engagement metric snapshots for published jobs
Query production infrastructure costs with filtering by date and grouping by provider, job, or day
Social Account Integration
Initiate a headless OAuth pairing flow for social accounts (YouTube, X, TikTok, LinkedIn, Facebook, Instagram, Threads), providing a URL and code for user approval
Poll for the status of a pending social account connection
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., "@@instavar/mcp-servercreate a video brief for my new product launch"
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.
@instavar/mcp-server
Drive the full Instavar Studio video workflow — create → render → approve → publish → metrics — from Claude Code or Codex, without leaving your terminal.
The server is a thin HTTP client: it authenticates with a per-user API key and talks to the hosted Instavar API. It holds no database connection and stores no data of its own.
Setup
Create an API key at https://instavar.com/studio/settings (shown once — copy it).
Add the server to your MCP client config:
{
"mcpServers": {
"instavar": {
"command": "npx",
"args": ["-y", "@instavar/mcp-server"],
"env": { "INSTAVAR_API_KEY": "ik_live_..." }
}
}
}Restart the client. The
instavartools appear.
Environment
Var | Required | Default | Purpose |
| yes | — | Your key from |
| no |
| Override the API host. |
Related MCP server: Clean-Cut-MCP
Tools
Tool | What it does |
| List recent jobs (newest first). |
| Runs, artifacts, verifications, current video + thumbnail URLs. |
| Materialized composition state for a job. |
| Platform engagement snapshots for a published job. |
| Infra cost summary (Lambda / RunPod / R2 / WaveSpeed / PoYo). |
| Create a job from a structured brief and start rendering. |
| Patch a brief (incl. objective / publishTarget); re-renders unless only publishTarget changed. |
| Approve a rendered job so it can be published. |
| Publish an approved job to its connected social destination. |
| Start connecting a social account (headless OAuth pairing). |
| Poll a pending account connection until it is connected. |
Writes require a key with the write scope; publish_job requires publish.
Connecting a social account from the terminal
connect_account returns an approve URL and a short confirm code. Open
the URL in a browser where you are signed in to Instavar, check the code matches
the one in your terminal, and approve — you go through the platform's normal
sign-in, then return to Instavar. Poll connect_account_status with the returned
pairingId until it reports connected. Pairings expire after 10 minutes and
can only be approved by an owner/admin of the workspace.
CLI
npx @instavar/mcp-server --version
npx @instavar/mcp-server --helpLicense
MIT
Maintenance
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/instavar/mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server