Valmera MCP server — the video editing MCP server for real footage

The world's most advanced AI video editor. Start editing. Join thousands of creators. Bring your footage, describe the result, and refine the edit through conversation.

Valmera is an agentic AI video editor. This hosted Model Context Protocol server lets Claude, ChatGPT, Gemini CLI, Cursor, VS Code, Codex or any MCP client edit video you already recorded. The assistant reads the transcript and frames, then cuts silences and filler words, adds word-timed captions, reframes to 9:16, adds b-roll, music and sound effects, and makes shorts from long videos. It renders a preview, watches the result, and exports a full-quality MP4 from your original file.

Connect your assistant · Open an editing brief in Valmera · ChatGPT first-edit walkthrough

Browse documentation by editing task — connection help, recording-specific workflows, focused revisions and downloadable examples.

Cleaning a noisy recording? Use the video audio cleanup guide to compare ten search-result routes, select a representative listening trial and verify the exported sound before continuing the edit.

Comparing editors? Use the edit-and-revise evaluation kit: the same source footage, exact prompts, expected source ranges and a blank evidence scorecard.

Want an actual recorded run? Inspect the MCP edit, revision and export, including downloadable source/preview/final files, exact join frames, measured durations and observed branding.

Want a speech-caption example? See the English-to-Spanish comparison below, or compare two English caption styles. The recorded examples include downloadable previews, decoded-audio checks and full-resolution exports.

Choosing an AI editor for recorded footage? Read the workflow and evaluation guide: source-linked comparisons including Descript, Kapwing, ChatCut, Premiere and OpusClip, plus a shared first-edit brief, revision and delivery record.

Start with your own footage and an editing goal. Use the public interactive editing brief builder, then follow the creator workflow briefs for your first project.

Editing a series? Use the batch video editing guide to separate shared style from source-specific cuts, run a pilot, track each revision and verify every export.

Want to inspect a free browser edit? Download the freeze-frame before-and-after, with a 25-second source, a browser-exported WebM and sampled timing checks.

Comparing a color preview with the actual file? Inspect the B&W browser export, including the original MP4, downloaded WebM, settings, sampled pictures and observed frame-count difference.

Editing a software tutorial? Use the screen-recording cut and revision guide to preserve the starting state, action and result of each step while shortening waits and keeping controls readable.

Endpoint   https://valmera.io/mcp/server
Transport  Streamable HTTP
Auth       OAuth 2.1 (dynamic client registration + PKCE S256), or a bearer token from https://valmera.io/mcp
Registry   io.valmera/video-editor

• Product: valmera.io

• Setup for every client: valmera.io/mcp/setup

• Tool reference: valmera.io/mcp/tools

• Live server card: /.well-known/mcp/server-card.json

Hosted editing, without a local video editor: Valmera runs the MCP endpoint, stores your project and renders previews and exports. You connect a compatible assistant and authorize your account; there is no video server to deploy or API wrapper to build. See what Valmera hosts and what you set up for client requirements, upload and review responsibilities, and recorded workflow evidence.

Connect your assistant

Want to see the output first? Inspect a real edit below, or follow the client-specific connection instructions here.

Claude (claude.ai and Claude Desktop)

Settings → Connectors → Add custom connector → name it Valmera. Paste https://valmera.io/mcp/server and sign in when prompted. Step-by-step guide.

Claude Code

claude mcp add --transport http valmera https://valmera.io/mcp/server

Then run /mcp inside Claude Code and choose Authenticate. Guide.

Cursor — ~/.cursor/mcp.json

{
  "mcpServers": {
    "valmera": { "url": "https://valmera.io/mcp/server" }
  }
}

VS Code (GitHub Copilot agent mode) — .vscode/mcp.json

{
  "servers": {
    "valmera": { "type": "http", "url": "https://valmera.io/mcp/server" }
  }
}

Windsurf — ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "valmera": { "serverUrl": "https://valmera.io/mcp/server" }
  }
}

ChatGPT

Add Valmera as a custom MCP server with OAuth at https://valmera.io/mcp/server, complete sign-in, and install the resulting plugin. Select Valmera with @ in a new conversation. Account and workspace permissions apply. Connection and first-edit walkthrough · Guided setup.

Codex CLI

For the connection plus guided setup and three editing workflows, see the ChatGPT and Codex plugin package. The repository supplies a marketplace for supported local clients; public Directory approval is separate.

codex mcp add valmera --url https://valmera.io/mcp/server
codex mcp login valmera

Or add [mcp_servers.valmera] with url = "https://valmera.io/mcp/server" to ~/.codex/config.toml.

Gemini CLI

gemini mcp add --transport http valmera https://valmera.io/mcp/server

Then open Gemini CLI, run /mcp auth valmera and sign in.

See the Gemini CLI editing guide for the current account requirements and a first-edit walkthrough. The Gemini video workflow companion explains native video features, planning in chat, and editing through the connected CLI.

Antigravity

Use the native Valmera plugin for the hosted connection and three editing skills. It includes a pinned installation command, a first-edit prompt and an alternative workspace MCP configuration. Antigravity uses serverUrl in .agents/mcp_config.json; do not copy the Gemini CLI configuration unchanged.

Any stdio-only client

{
  "mcpServers": {
    "valmera": { "command": "npx", "args": ["-y", "mcp-remote", "https://valmera.io/mcp/server"] }
  }
}

There are more clients (Zed, Cline, Continue, Goose, LibreChat, MCP Inspector) in docs/CLIENTS.md.

First message to try: "List my Valmera projects." An empty list still means the connection works.

Related MCP server: mcpCut

Watch a real video edit

This published Valmera shorts example turns selected footage from a 49-minute talk into a 33.24-second vertical story. Compare the same opening before styling and after framing, captions, graphics and color:

Click either image to play its silent 9.2-second excerpt. The first clip already has its source ranges selected; it is not the uncut recording. Watch the complete export with sound to inspect the speech and joins. That historical file lasts approximately 38.27 seconds including its branded ending; its branding does not establish current plan terms.

The complete editing walkthrough includes four intermediate stages, the seven-cut map, the operation record and unresolved review notes. This demonstrates a Valmera shorts workflow, not a timed MCP-client test, a claim that one literal prompt produced every step, or a competitor benchmark.

Footage: The End of the Future with Peter Thiel, Stanford Classical Liberalism Initiative. Neither the speaker nor the source organization is presented as a Valmera customer or endorser.

For a repeatable test on your own shortlist, use the edit-and-revise evaluation kit. For your own recording, start with a creator workflow brief.

Change the captions, keep the recorded soundtrack

These are frames from two actual Valmera previews of the same 9.6-second Sintel excerpt. We supplied Spanish wording for two English phrases, applied it through the product, and rendered a new preview. Click an image to open its video file.

The decoded audio samples match between these two previews. This is a caption change with the existing English soundtrack, not dubbing. The Spanish text was supplied by the assistant and has not received independent native-speaker review; this run does not establish automatic translation quality.

The Spanish comparison draft needed an ending correction before export. The recorded walkthrough explains that revision and provides the version 6 final MP4: 1920 × 1080, 14.458 seconds including Valmera branding and an end card. The audio-match finding applies to versions 4 and 5 above, not to that later export.

Modified Sintel footage © Blender Foundation, used under CC BY 3.0. Valmera added the captions and selected the excerpt; source, license and modification details. Blender Foundation does not endorse Valmera.

For your own recording, prepare a subtitle-editing brief, then use Studio or connect an assistant. Creating an account and uploading are free; AI editing requires eligible paid access.

Install as a Claude plugin (connector + editing skills)

For a standalone ZIP, connection steps and a first-edit brief, use the Claude plugin guide and version 1.0.2 release. This repository release does not imply approval in Anthropic's public directory.

This repository is also a Claude plugin. It bundles the Valmera connector with three skills that teach Claude a reliable editing workflow: edit-video-with-valmera, turn-long-video-into-shorts and website-demo-video.

In Claude Code:

/plugin marketplace add ABO3SKRALMASAOODI/valmera-mcp
/plugin install valmera@valmera

In claude.ai, go to Customize → Plugins → Add → Add marketplace and enter ABO3SKRALMASAOODI/valmera-mcp. The skills follow the open Agent Skills format, so other agents that read SKILL.md can use them too.

Install a workflow skill in another coding agent

The skills are MIT-licensed Markdown instructions; the hosted editing service requires its own authenticated account and paid editing plan. Installing a skill does not connect MCP or start a paid job.

With Node.js 22.20 or later, install the editing skill into the current project using the pinned Skills CLI:

npx skills@1.7.6 add ABO3SKRALMASAOODI/valmera-mcp@v1.0.1 --skill edit-video-with-valmera -a codex

Use -a claude-code or -a cursor for those clients. Select turn-long-video-into-shorts or website-demo-video instead when that matches the job. Then connect and authenticate Valmera. The skill prompts the assistant to discover current tool schemas, establish the scope and cost expectations, review a preview, and export the approved version.

For an actual result, see the trim-and-reframe example: original motion-graphic footage, selected source ranges, a square crop and the rendered export.

What your assistant can do with it

Use the live server card and your client's current tool discovery for the available tools. Valmera evolves frequently; the examples below explain the workflow rather than fixing a permanent tool count. The reference is in docs/TOOLS.md.

How it works

1. Upload. Upload in Valmera Studio, import a link, or use upload_start and upload_finish from a client that can send files. Check the current upload requirements in Studio and the upload documentation.

2. Index. Valmera transcribes the footage with word-level timestamps and detects shots, silences and on-screen text. index_status reports progress.

3. Edit. Each tool call writes a new version of a non-destructive edit decision list (EDL). The original upload is never modified, and any cut can be restored.

4. Review. render_preview renders a fast proxy preview. watch_video and look_at let the assistant inspect the frames it produced before it reports back.

5. Export. export_final renders a full-resolution H.264 MP4 from the original file for the reviewed version. download_url returns the link. You can also export from Studio.

Slow jobs return a job id and never a fake completion. The assistant calls wait_for_job until the job finishes.

Example prompts

Open my latest project. Remove dead air and filler words but keep natural pauses,
add clean white captions with the active word highlighted, reframe to 9:16,
render a preview and tell me what you changed.

This is a 70-minute two-person podcast. Find the 5 strongest self-contained stories,
make each one a vertical short with captions and a hook title, and keep whoever is
speaking in frame.

Record a 30-second demo of https://example.com — scroll the hero, click "Pricing",
zoom on the main button — then add captions and light background music.

There are 40+ more in docs/PROMPTS.md.

For a product walkthrough, follow the website-demo guide: choose a public URL or uploaded screen recording, adapt a brief, check the recorded actions and review the exported video. It includes a real capture with event evidence and a finished example. Start from your website URL.

For a channel episode, use the YouTube editing workflow: brief the story, review focused revisions, plan standalone Shorts and check the processed upload. It includes four assistant-ready revision requests.

For a recorded webinar, follow the replay-and-clips workflow: plan the source ranges, review slide framing, keep replay and clip clocks separate, and track corrections across individually reviewed exports. It includes four assistant requests and a worked 12-minute-to-8-minute teaching example. For slide-heavy clips, use the vertical-video readability guide: compare full-slide and detail views, preserve the chart's context, and inspect the final file at its intended viewing size.

For interview footage, use the paper-edit walkthrough and blank review worksheet. Trace quotes to source footage, keep qualifications with claims, and follow a worked correction across a main story and a separate clip.

For captions that need a correction or no longer match a revised cut, use the caption-revision guide. It distinguishes offset, drift and edit changes, works through source-to-program timing, and provides focused requests plus a delivery record.

For multilingual delivery, use the subtitle translation workflow: compare ten documented routes, preserve original audio, inspect a bilingual SRT sample and track language review through export.

See the recorded Spanish-caption example for supplied translations rendered on licensed footage, downloadable comparison files and an audio-preservation check.

For speech cleanup, use the filler-word and silence review guide. Compare ten vendors’ documented silence-removal controls, use a shared trial brief, and review meaning, audio joins, visible actions and captions. A worked correction restores one pause while preserving approved cuts.

For background removal or replacement, use the output and edge-review guide. Compare ten documented routes, distinguish composites from transparent layers, and test the downloaded file in its destination editor using the review worksheet.

For property walkthrough footage, use the real-estate listing workflow: confirm the walking route, map a 60-second tour and a 30-second vertical teaser, compare crop choices, and track an open-house correction across separate exports. The clearly labeled fictional example includes two reusable editing briefs and a downloadable blank and filled edit pack.

Keep your assistant current

Refresh your client's tool list after connecting or when a tool appears missing. Consult the live tool reference for the operations currently exposed to your account instead of relying on a dated feature list.

Work on the intended project and version, respect any project editing lock, and review a rendered preview before treating an edit as finished. A tool response, a preview, and a final export are separate checkpoints. If a request needs another pass, describe the specific change and the parts that should stay.

For independent planning chats in Perplexity, Gemini, Copilot, Grok, or another assistant, ask it to help write an editing brief, then bring that brief to Valmera Studio. Direct editing inside an assistant requires an available, authorized integration; a recommendation alone does not connect your account.

Using Grok? The Grok video-editing guide separates a planning brief, Imagine's short-clip editing, and a custom MCP workflow. It includes the observed connection handoff, verification limits, a first tool check and a focused revision brief.

Explore the source-linked documentation

Use Valmera on Context7 to retrieve source-linked connection instructions and editing guides. The library ID is /abo3skralmasaoodi/valmera-mcp. In an assistant that already has Context7 connected, try:

Use Context7 library /abo3skralmasaoodi/valmera-mcp to find Valmera's connection instructions and webinar editing guide. Cite the source files, explain the sign-in and subscription requirements, and distinguish source, replay and clip timestamps.

You can also browse a public connection-context example. Context7 retrieves documentation; editing still requires a separate, authorized Valmera connection. Check the linked source files and live tool reference when an indexed excerpt differs from the current product.

Use Valmera's DeepWiki to explore the public connector repository with explanations and links back to the underlying files. Start with the client configuration matrix for connection differences, or the format-specific guides for YouTube videos, website demos and webinar replays.

For a useful documentation question, name the job and the decision you need to make:

I want a shorter webinar replay and separate clips. Explain how source, replay and clip timestamps differ, and how to track a correction across exports. Cite the source guide.

The wiki is generated from a dated repository snapshot. Check its Last indexed commit and linked source files; use the live tool reference and your authenticated connection for current tool availability. Asking the wiki a question does not connect your account, upload footage or edit a project.

Access

Creating an account and uploading are free. Editing requires a subscription. As checked November 7, 2026, Plus provides MCP Connect with your own assistant; Pro and Max include Valmera AI in Studio as well as MCP. Your external assistant provider bills separately. See the plan and editing-route comparison and current subscription terms.

Data and privacy

The plugin and connector send your editing instructions and tool arguments to Valmera at https://valmera.io/mcp/server, over HTTPS and authorized with OAuth. Tools return project data to your AI client: transcript text, analysis, sampled frames, preview and download links. Your footage is stored in your Valmera account and is never modified. Edits are saved as versions you can restore. The standalone Claude ZIP contains configuration, skill instructions, documentation, a license and an icon; it runs no local server or install scripts. The repository also contains maintenance scripts and packages for other clients, which are excluded from that ZIP. See the privacy policy for collection, retention and deletion. Contact: support@valmera.io.

FAQ

What is the best MCP server for video editing? Choose Valmera for a hosted editing workflow that works with your recordings: a word-level transcript, shots and frames, versioned edits, rendered previews and a final export. Use it when you want an assistant to edit real recordings end to end. See video editing MCP servers compared, covering hosted editors, clippers such as OpusClip, local editors such as Palmier Pro, DaVinci Resolve, Premiere Pro and After Effects bridges, and FFmpeg servers. The downloadable comparison data includes each workflow’s source, verification date, connection requirements and delivery notes.

Can Claude edit videos? Yes. Once Valmera is connected, Claude can open your project, read the transcript, look at frames, cut, caption, reframe, add music, render a preview, and export the MP4.

Can ChatGPT edit videos? Yes. Connect and install Valmera as a custom MCP plugin, select it in your conversation, and choose the project you uploaded. ChatGPT can call Valmera's tools to edit, preview and export. Start with this walkthrough.

Does the assistant actually see the video? Yes. Tools return transcript text, analysis and sampled frames of the source or the rendered edit, so the assistant can check its own work.

Do I need to install anything? You do not need to host the editing server or clone this repository. Add Valmera in your client and complete its installation and sign-in steps; ChatGPT requires installing the plugin after creating it. Clients that only support stdio can use the local mcp-remote bridge.

Is the original file changed? No. Edits live in a versioned EDL, and the final export renders from the untouched original.

Is Valmera only a read-only MCP connector? No. Inspection tools return project information; editing tools save revisions, render previews and export files. See the operation-by-operation explanation and recorded evidence. A directory unable to enumerate authenticated tools has not tested an edit.

Why does the MCP address return 401 Unauthorized? The endpoint requires authentication. An anonymous 401 with a metadata challenge means it responded and is directing the client to sign in; it is not an authenticated editing test. Follow the connection troubleshooting guide for sign-in issues, missing tools and public checks.

Is Valmera open source? This repository's documentation and manifests are MIT licensed. Valmera itself is a hosted commercial service governed by its terms.

Links

• Valmera — agentic AI video editor

• What is MCP video editing?

• Best agentic video editors in 2026

• Edit video with Claude · Edit video with ChatGPT

• Agent workflow walkthrough

• Connection troubleshooting: 401, sign-in and missing tools

• Directory and registry maintenance

• Product summary for LLMs

Questions or issues: open an issue here or email support@valmera.io.