io.github.doc2videoPublished by GitHub account doc2videov0.2.3Updated Oct 29, 2026
Turn documents and photos into narrated AI videos from Claude, ChatGPT, Codex or any MCP client.
Turns documents and photos into narrated AI videos on doc2video.io, letting an assistant build, review and steer storyboards and produce final videos.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/io.github.doc2video%2Fd2v/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.
{
"mcpServers": {
"doc2video": {
"type": "http",
"url": "https://doc2video.io/mcp"
}
}
}[npm] [License: MIT] [Add to Cursor] [Install in VS Code]
Point d2v at a folder of documents and photos and it makes a narrated, AI-produced video on
doc2video.io. Drive it yourself, or let Claude or ChatGPT (Codex) drive it
for you — either through the CLI or as an MCP server.
Requires Node.js 18.18+.
Or run it without installing: npx doc2video <command>.
Your browser opens doc2video. Sign in (or sign up), check the code matches your terminal, click
Approve — done. The key is saved to ~/.doc2video/config.json and shows up on the dashboard's
API page, where you can revoke it. No browser on this machine? d2v login --no-browser prints the
link to open anywhere.
Agents use two steps so they can show you the link: d2v login --start --json (returns the link
and code), then d2v login --wait after you approve. Over MCP, the d2v_connect_account tool does
the same.
You can also paste a key created on the API page (d2v login --key d2v_…) or set
DOC2VIDEO_API_KEY. To target another server (e.g. local dev) use --url http://localhost:3000
or DOC2VIDEO_URL.
Folders are scanned recursively (hidden files skipped). Legacy .doc/.ppt/Keynote/Pages files
are skipped with a hint to convert them. A photos-only folder works too — the story is built from
the photos and your creative direction. With no files at all, use --draft "description".
Photos are used as-is by default — cropped to the video's shape, and free as still or Ken
Burns scenes (you only pay for AI work, e.g. an AI video clip made from the photo). Use
--photos restyle to have AI polish them into cinematic keyframes while keeping the real subject,
or set it per scene with d2v scene <p> <n> --photo-treatment restyle.
Each day you get 2 free storyboards and 20 scene redos on unpaid projects. After that, a
storyboard costs $0.50 from prepaid credits — pass --use-credits to create --build, build
or run to confirm (without it the command stops and tells you the price). Credits also unlock
finished videos: d2v buy <p> --credits.
Projects can be named by id, 8-character id prefix, or exact name. d2v help <command> shows
every option; d2v guide prints the full workflow guide.
Settings (on create and set): --duration auto|30s|1m|2m|5m|10m, --aspect 9:16|16:9,
--direction, --voice (see d2v voices), --stability, --photos original|restyle,
--consistency/--no-consistency, --client, --email, --phone, --website.
Everything runs on doc2video's servers; a storyboard takes several minutes and final production
longer. --wait blocks with progress on stderr, and Ctrl+C only stops the waiting — the work
continues. Pick it back up with d2v wait <project>. Steps can be chained on the server, so a
build keeps going even if your terminal closes.
Add --json to any command for machine-readable output on stdout (progress stays on stderr).
Exit codes: 0 ok, 1 error, 2 usage error, 3 payment required, 4 --wait timed out,
5 rate limit or daily free limit reached.
doc2video also runs the MCP server for you at https://doc2video.io/mcp. Add it as a custom
connector and sign in with your doc2video account when asked (OAuth — no keys to copy):
https://doc2video.io/mcp.claude mcp add --transport http doc2video https://doc2video.io/mcp, then run
/mcp to sign in.https://doc2video.io/mcp (developer mode) and
OAuth sign-in.{ "doc2video": { "url": "https://doc2video.io/mcp" } } (VS Code: "type": "http").The hosted server has the same tools, but it can't see your computer's files: give it text, public
links (PDFs, Word and PowerPoint files, photos, web pages), or add files on the project page it
links to. To work from local folders, use the CLI or d2v mcp below. Connected apps are listed,
and can be disconnected, on your dashboard's API page.
Both can simply run d2v. Open a terminal agent in the folder with your files and ask, e.g.
"Make a 60-second vertical video from this folder with doc2video, show me the storyboard, and
punch up the opening." For better results, install the agent instructions:
agents/SKILL.md to ~/.claude/skills/doc2video-cli/SKILL.mdagents/AGENTS.md to ~/.codex/AGENTS.md (or the folder's AGENTS.md)Both files ship with the package — find them under $(npm root -g)/doc2video/agents/.
d2v mcp runs an MCP server over stdio with tools for the whole workflow — including
d2v_view_storyboard, which returns the keyframe images so the model can actually see the
storyboard and give visual feedback. It's listed in the official
MCP Registry as io.github.doc2video/d2v.
The API key below is optional: without one, the d2v_connect_account tool gives you a link to
sign in (or sign up) in your browser, and remembers the key.
Cursor / VS Code — use the buttons at the top of this page.
Claude Code
Claude Desktop — claude_desktop_config.json:
Codex CLI — ~/.codex/config.toml:
With a global install you can use "command": "d2v", "args": ["mcp"] instead of npx.
ChatGPT (web/desktop): ChatGPT connects only to remote MCP servers, so use the hosted server above. Use Codex CLI for local folders.
The CLI is a thin client over the doc2video REST API — see API.md to call it directly.
Releases are published from GitHub Actions when a v* tag is pushed: to npm (with provenance)
and to the MCP Registry. Issues and pull requests are welcome at
github.com/doc2video/cli.
The CLI and MCP server are MIT licensed. They're a client for the hosted doc2video service at doc2video.io, which has its own terms.
Source: README.md at commit 40f7cc5
Connect doc2video account
Connect this server to the user's doc2video account. Call it first when other tools say the user is not logged in. It returns a link: ask the user to open it, sign in or sign up, and click Approve, then call this tool again to finish.
wait_secondsList projects
List the user's doc2video projects (id, name, status, format).
Takes no parameters.
Get project
Full project detail: settings, sources, every scene (narration, visual mode, photo, keyframe URL), jobs, preview/final video, cost estimate and suggested next steps.
projectrequiredList narrator voices
Narrator voices available for projects.
Takes no parameters.
Create project
Create a video project from local files and folders (uploaded from this machine), public links, written text, or an AI draft prompt. Photos (jpg/png/webp/heic) are featured in scenes; documents (pdf/docx/pptx/md/txt/csv/json) supply the story. Set build: true to start generating the storyboard right away (then poll d2v_wait).
namerequiredtextbuildvoicesourcesclient_nameconsistencyuse_creditsaspect_ratiodraft_promptcontact_emailcontact_phone+5 moreAdd sources
Upload more local files/folders, add public links, or add written content to a project. Rebuild the storyboard afterwards for them to take effect.
textprojectrequiredsourcesRemove source
Delete a source document or photo from a project, by document id or filename.
projectrequireddocumentrequiredUpdate project settings
Change project settings. They apply to steps run afterwards (e.g. run narration again after a voice change).
namevoiceprojectrequiredclient_nameconsistencyaspect_ratiocontact_emailcontact_phonecontact_websitephoto_treatmentvoice_stabilityduration_seconds+1 moreAI-draft source content
Have AI write the video's source content from a short description (saved as the project's AI content brief by default).
savepromptrequiredprojectrequiredSuggest creative direction
Suggest a creative direction from the project's sources and optional preferences; save: true stores it on the project.
saveprojectrequiredpreferencesBuild storyboard
Queue the storyboard chain on the server: script → keyframes → narration → preview. `from` starts later in the chain. Starting from the script replaces existing scenes, so it needs force: true when scenes exist. Poll d2v_wait afterwards.
fromforceprojectrequireduse_creditsRun pipeline step
Queue one pipeline step (script, keyframes, narration, preview, clips, assemble), optionally chaining more with `then`. clips and assemble require purchase. Poll d2v_wait afterwards.
steprequiredthenprojectrequireduse_creditsmax_credits_centsWait for jobs
Block until the project's queued/running jobs finish or timeout_seconds passes (default 50), then return status. If done is false, call again. Storyboards take several minutes.
projectrequiredtimeout_secondsView storyboard
See scene keyframe images with their titles and narration. Pass `scenes` to view specific scene numbers (default: all).
scenesprojectrequiredUpdate scene
Edit one scene: title, narration text (re-voice with d2v_update_narration), visual engine, approval, or photo. photo accepts a project photo's filename, a document id, an absolute local file path (uploaded), a public link to a photo, or "none" for an AI visual. A photo change regenerates the keyframe unless regenerate_keyframe is false.
photoscenerequiredtitleprojectrequiredapprovedvisual_modenarration_textphoto_treatmentregenerate_keyframeRegenerate keyframe
Regenerate one scene's image. With a direction and mode iterate (default when a keyframe exists) the current image is edited; mode fresh creates a new image from the scene description (plus direction). Run the preview step afterwards to update the video.
modescenerequiredprojectrequireddirectionUpdate narration
Change a scene's narration and regenerate its voice-over: pass exact `text`, or a `prompt` for an AI rewrite, or neither to just re-voice. regenerate_audio: false saves text only.
textscenerequiredpromptprojectrequiredregenerate_audioRetry AI clip
Retry a scene's failed AI video clip, optionally on another engine (still/kenburns drop the clip). AI clips require purchase; retrying a failed clip is free, while a pricier engine or a new take of a working clip may cost credits.
scenerequiredengineprojectrequireduse_creditsmax_credits_centsSave storyboard locally
Download every keyframe PNG plus a storyboard.md (titles, narration, prompts) to a local folder.
projectrequiredoutput_dirEstimate cost
Price to unlock AI clips, final assembly and download, broken down by each scene's visual engine. Only AI work is charged: photos used as-is are free except for AI video clips.
projectrequiredCreate checkout link
Create a Stripe checkout URL for the user to open and pay in their browser. Only call when the user asks to purchase.
projectrequiredGet credits
The user's prepaid credit balance, free storyboards left today, and recent credit activity.
Takes no parameters.
Add credits link
Create a Stripe checkout link for the user to add $5, $10 or $25 of credits in their browser. Only when the user asks.
amount_dollarsrequiredUnlock with credits
Unlock a project (AI clips, final assembly, download) by paying its price from the user's credits. Only when the user asks; show d2v_estimate_cost first.
projectrequiredmax_credits_centsrequiredRedeem promo code
Unlock a project with a promo code the user provided (one code per account).
coderequiredprojectrequiredProduce final video
Generate AI clips for veo3/runway scenes (if needed) then assemble the final video. Requires purchase; only call when the user asks. Clips beyond what the purchase covers (engines changed to pricier ones after buying) need the user's OK to pay from credits. Poll d2v_wait afterwards.
projectrequireduse_creditsmax_credits_centsDownload final video
Save the final MP4 to this machine (requires purchase).
projectrequiredoutput_path100% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
d2v create "Spring Open House" ./open-house --duration 1m --aspect 9:16 \ --direction "Warm and inviting, finish on the garden" --build --waitnpm install -g doc2video # installs the `d2v` (and `doc2video`) commandd2v logind2v create "Name" ./folder [settings] --build --wait # storyboard: script → keyframes → narration → previewd2v show <project> # scenes, narration, preview URL, next stepsd2v pull <project> # keyframes + storyboard.md to a local folder
# steer, scene by scened2v keyframe <p> 3 "warmer light, show the sign" # edit the imaged2v keyframe <p> 3 --fresh # brand-new imaged2v narration <p> 3 --prompt "shorter and punchier" # AI rewrite + new voice-overd2v narration <p> 3 --text "Exact words." # exact text + new voice-overd2v scene <p> 3 --engine veo3 # still | kenburns | runway | veo3d2v scene <p> 3 --photo IMG_2041.jpg # feature a photo (or --photo none)d2v run <p> preview --wait # refresh the preview video
# finish (costs money — you pay in the browser)d2v estimate <p>d2v buy <p> --open # or: d2v buy <p> --credits, or: d2v redeem <p> CODEd2v produce <p> --wait # AI clips → final assemblyd2v download <p>d2v credits # balance, free storyboards left today, recent activityd2v credits add 10 --open # top up $5, $10 or $25 in the browserclaude mcp add doc2video -- npx -y doc2video mcp# or with a key from doc2video.io/dashboard/api-keys:claude mcp add doc2video -e DOC2VIDEO_API_KEY=d2v_xxx -- npx -y doc2video mcp{ "mcpServers": { "doc2video": { "command": "npx", "args": ["-y", "doc2video", "mcp"], "env": { "DOC2VIDEO_API_KEY": "d2v_xxx" } } }}[mcp_servers.doc2video]command = "npx"args = ["-y", "doc2video", "mcp"]env = { DOC2VIDEO_API_KEY = "d2v_xxx" }npm installnpm run build # compile to dist/npm test # build + end-to-end tests against a mock API (no network)npm link # use your local build as `d2v`