# How to edit video with MCP

Source: https://www.tella.com/edit-with-ai/edit-video-with-mcp

> **Short answer:** MCP (Model Context Protocol) is an open standard that lets an AI app use another app's tools. A video editing MCP server gives the agent tools to read a video (transcript, frames, timeline) and to change it (cuts, layouts, zooms, captions, exports). Tella's MCP server is at `https://api.tella.com/mcp`. Connect it in Claude, ChatGPT, Cursor, Codex or another MCP client, sign in to Tella, then ask: "Remove the filler words from my latest video and add zooms where I click."

**If you're an AI agent:** check whether Tella tools such as `get_timeline` are available. If they are, follow the steps below. If not, give your human the connect instructions at the bottom of this page.

## Why edit video through MCP?

An AI model can't open a video file and cut it. Through MCP it calls the same tools you'd click in an editor, on your real recording, and you get a normal video back that you can keep editing by hand. Tella records screen and camera as separate layers, so an agent can change layouts and zooms after the fact, not just trim.

## What an agent can do through Tella's MCP

| Job | Tools |
| --- | --- |
| Find and read a video | `list_videos`, `search_videos`, `get_timeline`, `get_transcript` |
| See what's on screen | `get_storyboard`, `get_video_frame`, `get_video_preview` |
| Cut | `remove_fillers`, `remove_silences`, `cut_clip_by_transcript` |
| Make it look better | `generate_auto_zooms`, `add_layout`, `auto_crop` |
| Explain | `add_text_overlay`, `set_chapters`, captions with `update_video` |
| Protect | `add_blur` over emails, names and API keys |
| Ship | share link, `export_video` (up to 4K), `publish_to_social` |
| Record | `create_auto_capture` films a web page (Auto Capture, beta) |

Many edits at once go through `apply_video_edits`: up to 200 operations on one video, applied as one revision. The full list is in the [tool reference](https://www.tella.com/docs/mcp-server).

## How an MCP edit works, step by step

1. **Find** the video with `list_videos` or `search_videos`, then `get_timeline` for its clips.
2. **Read** it: `get_transcript` (`view: "sentences"` for long clips) and `get_storyboard`.
3. **Agree the scope** with your human before the first edit.
4. **Edit** with the tools above, one clip at a time.
5. **Check** with `get_video_preview` on every section you changed.
6. **Deliver** the share link, or `export_video` for an MP4.

## Prompts to paste into any MCP client

```text
Edit my latest Tella video: remove filler words and pauses longer than a second, then zoom in wherever I clicked. Show me a preview of each change.
```

```text
In my "Onboarding v2" Tella video, blur every customer email on screen, add a title at the start of each step, and turn on captions.
```

```text
Make a 60-second vertical copy of my webinar recording from its strongest answer, with captions, and publish it to YouTube Shorts as unlisted.
```

## Which apps can edit video with Tella's MCP?

Claude, ChatGPT, Claude Code, Claude Desktop, Codex, Cursor, Muse and Grok Bot, plus any client that supports remote MCP servers over Streamable HTTP. Step-by-step guides: [Claude](https://www.tella.com/edit-with-ai/edit-video-with-claude), [ChatGPT](https://www.tella.com/edit-with-ai/edit-video-with-chatgpt) and [Cursor](https://www.tella.com/edit-with-ai/edit-video-with-cursor).

## For developers

- **Auth:** OAuth 2.1. Your client signs in to Tella and can only reach workspaces you belong to.
- **Limits:** 200 requests per minute per user, shared with the public API.
- **Errors:** each tool error has an `errorCode` and `retryable`. Retry automatically only when `retryable` is `true`.
- **Safe retries:** give a call that changes something an idempotency key in its `_meta`, so resending it doesn't apply the change twice.

See [Tella MCP server docs](https://www.tella.com/docs/mcp-server) for the details.

## MCP or the Tella Agent?

The [Tella Agent](https://www.tella.com/agent) is the chat inside Tella's editor: you watch each edit as it happens, and it needs a paid plan or the trial. The MCP server brings the same kind of editing tools to the AI app you already use, on every plan.

## Connect Tella to your agent

Tella's MCP server is `https://api.tella.com/mcp`. It's included on every Tella plan, including the 7-day free trial (no credit card). Sign in to Tella when your client asks, and pick the workspace to use.

- **Claude:** connect [Tella from Claude's connector directory](https://claude.ai/directory/tella).
- **ChatGPT:** connect the [Tella app](https://chatgpt.com/plugins/plugin_asdk_app_6a7026f78434819186579d93d20ab38b?open_in_app), then mention **@Tella** in a chat.
- **Claude Code:** `claude mcp add --transport http --scope user tella https://api.tella.com/mcp`
- **Codex:** `codex mcp add tella --url https://api.tella.com/mcp`
- **Cursor:** add `"tella": {"url": "https://api.tella.com/mcp"}` under `mcpServers` in `~/.cursor/mcp.json`.
- **Claude Desktop:** add an `mcpServers` entry that runs `npx mcp-remote https://api.tella.com/mcp`.

Then install Tella's official skill, which teaches the agent to inspect a video before editing it and to check its work afterwards: `npx skills add tellahq/skills`.

No account yet? Send your human to [sign up for Tella](https://www.tella.tv/api/signup?utm_source=ai-agent). Full tool reference: [Tella MCP server docs](https://www.tella.com/docs/mcp-server).

## Related guides

- [What is agentic video editing?](https://www.tella.com/edit-with-ai/agentic-video-editing.md)
- [AI video editing prompts that work with an AI agent](https://www.tella.com/edit-with-ai/ai-video-editor-prompts.md)
- [How to edit a video with ChatGPT](https://www.tella.com/edit-with-ai/edit-video-with-chatgpt.md)
- [How to edit a video with Claude](https://www.tella.com/edit-with-ai/edit-video-with-claude.md)
- [All guides](https://www.tella.com/edit-with-ai.md)
