MCP Server

Vidocu provides a Model Context Protocol (MCP) server that lets AI assistants like Claude interact with the Vidocu API through natural conversation.

Available on every plan

The MCP integration works on any Vidocu plan, whether you connect with OAuth or with an API key. Operations draw from your plan's monthly allowance.

Authentication

The MCP server supports two authentication methods:

Option 1: OAuth (recommended)

MCP clients that support OAuth (like Claude Desktop) can authenticate automatically. The user authorizes Vidocu through a browser-based consent flow — no manual key management needed.

The MCP server advertises Vidocu's OAuth authorization server via RFC 9728 Protected Resource Metadata at /.well-known/oauth-protected-resource.

{
  "mcpServers": {
    "vidocu": {
      "url": "https://mcp.vidocu.ai/"
    }
  }
}

The MCP client handles the OAuth flow automatically — redirects the user to Vidocu's consent screen, obtains tokens, and sends them as Authorization: Bearer on each request.

Option 2: API Key

For MCP clients that don't support OAuth, or for quick testing, pass your API key as a Bearer token:

{
  "mcpServers": {
    "vidocu": {
      "url": "https://mcp.vidocu.ai/",
      "headers": {
        "Authorization": "Bearer vdo_live_your_key_here"
      }
    }
  }
}

Get your API key from the Vidocu Dashboard.

Server details

URL	https://mcp.vidocu.ai/
Transport	Streamable HTTP
Authentication	Authorization: Bearer (API key or OAuth token)
OAuth metadata	https://mcp.vidocu.ai/.well-known/oauth-protected-resource

Available tools

The MCP server exposes 145 tools, covering the same platform as the REST API: videos and projects, processing, the AI Recorder, the Knowledge Center, courses and training, Studio, Remix, voices and avatars, the brand kit, approvals, and webhooks.

Features keep their plan rules over MCP. The AI Recorder needs a paid plan, the Knowledge Center tools need the Knowledge Center add-on, and every operation draws the same credits it would in the app. Call get_credit_costs to price a job before starting it.

Videos and projects

Tool	What it does
get_upload_url	Get an upload URL for a local video file.
upload_video	Upload a video to Vidocu from a public URL.
list_videos	List videos in the workspace with optional filtering and pagination.
get_video	Get details of a specific video including status, duration, URLs, and export info.
update_video	Rename a video, move it to a different project folder, or adjust the context used when generating content.
delete_video	Permanently delete a video and its stored files, including any exports.
create_project	Create a project folder to organize videos in the workspace.
list_projects	List project folders in the workspace with pagination, search, and sort.
get_project	Get details of a specific project folder.
update_project	Update a project folder's name, description, thumbnail, or access.
delete_project	Delete a project folder.

Processing

Tool	What it does
analyze_video	Start video analysis to generate subtitles and a narration script.
export_video	Start a video export with burned-in subtitles.
translate_video	Translate video subtitles to another language.
generate_voiceover	Generate an AI voiceover for a video. Use list_voices for valid voice IDs.
get_subtitles	Get subtitles for an analyzed video in JSON or SRT format.
generate_article	Generate a step-by-step help article from a video.
get_article	Fetch the help article already generated for a video, without regenerating it.
process_video	One-shot pipeline: process a video through multiple operations (analyze, voiceover, article, export, translate) in a single request.
get_script	Get a video's timed script lines.
update_script	Replace a video's script lines.
get_download_url	Get the URL of a stored file for a video: the exported video, the original source, the voiceover audio, the SRT, or the thumbnail.

AI Recorder

Tool	What it does
start_recording	Describe a flow in plain words and the AI Recorder drives a browser to produce a screen recording of it. Pass sessionId to pick a saved login.
list_recordings	AI Recorder jobs for the workspace, newest first.
get_recording	Status of one recording.
get_recording_download	A time-limited URL for a completed recording's video file.
answer_recording_prompt	Supply a value the agent paused to ask for.
delete_recording	Remove a recording job from the workspace's list.
list_recorder_sessions	Logins the recorder has saved, so a recording behind a login doesn't have to sign in again. A site can have several; one per site is the default.
update_recorder_session	Rename a saved login, make it its site's default, or change its setup instructions or how long it is kept.
delete_recorder_session	Forget one saved login, by its id.

Knowledge Center

Tool	What it does
get_knowledge_base	The workspace's knowledge base: its public URL, locales and visibility.
create_knowledge_base	Create the workspace's knowledge base.
update_knowledge_base	Change the knowledge base's name, slug, locales, visibility (public, or gated behind sign-in), sign-in access or tags.
delete_knowledge_base	Take the knowledge base offline.
list_kb_sections	The knowledge base's sections, in display order.
create_kb_section	Add a section.
update_kb_section	Rename a section, change its slug, description, thumbnail, visibility, parent or outside readers (sharedWith), or set its name in the knowledge base's other languages (translations).
delete_kb_section	Delete an empty section.
reorder_kb_sections	Set the display order of sections.
list_kb_articles	List articles, newest-edited first.
create_kb_article	Write a new article.
get_kb_article	One article, including its full Markdown content.
update_kb_article	Edit an article, publish it by setting state to 'published', or attach/detach its video with linkedVideoId.
delete_kb_article	Delete an article.
kb_article_from_video	Publish a video's help article into the knowledge base, linked back to the video.
translate_kb_article	Translate an article into other locales.
ask_knowledge_base	Ask a natural-language question and get an answer grounded in the workspace's published articles, with citations.
reindex_knowledge_base	Rebuild the search embeddings for every published article.
list_kb_redirects	Redirects configured on the public help site.
create_kb_redirect	Point an old path at a new one, so links that were published before a slug change keep working.
delete_kb_redirect	Remove a redirect.
kb_analytics	How the help site is doing: article counts by state, most-viewed articles, top searches, and searches that returned nothing.
export_knowledge_base	Build a static, offline copy of the help center as a ZIP: branding, sections, articles, images, exported videos and client-side search.
list_kb_exports	Offline bundles built for this knowledge base, newest first.
get_kb_export	One offline bundle: progress while it builds, then the download link, counts and any videos that were skipped.

Courses

Tool	What it does
list_courses	List courses.
create_course	Turn a document (PDF, DOCX, PPTX, Keynote, TXT) or an existing video into a course.
get_course	Get a course with its modules.
update_course	Rename a course, change the planner instructions, file it under a project folder, or set who may take it and what counts as finishing a module.
course_progress	Who is getting through a course.
delete_course	Delete a course plan.
get_course_storyboard	Get every module's scenes, plus omissions (source content the storyboard deliberately left out) and warnings (review hints).
build_course_storyboard	Build the storyboard for one module.
generate_course_module	Build one module into a video made of editable slides (one per storyboard scene, each with its own voiceover).

Training

Tool	What it does
list_modules	Training modules in the workspace, most recently updated first.
generate_module	Write a quiz from a video or a knowledge-base article.
get_module	One module with its questions.
update_module	Edit a module's title, description, questions, settings or state.
delete_module	Delete a module.
lock_module	Freeze a module permanently.
translate_module	Translate a module's questions into other locales.
list_module_translations	A module's translations.
submit_module_attempt	Submit someone's answers and record the graded result.
get_module_results	Attempts on a module with the pass rate and average score.
training_planner	Every training against every person, most urgent first.
set_training_deadline	Set the date by which one person must complete one training, or pass dueAt: null to clear it.
withdraw_qualification	Take a training qualification away from one or more people, with a reason.
list_training_people	The roster of people this workspace trains, plus anyone who has training records but is not on the roster yet.
add_training_person	Add somebody to the training roster before they have taken anything, so they appear against every training as not started.
list_module_passers	Distinct people who have passed a module, with when they last passed.
list_module_qualifications	Who a trainer has signed off on a module.
qualify_person	Record that a trainer has signed this person off on a module.
module_analytics	Workspace-wide training rollups.

Studio

Tool	What it does
list_studio_projects	Multi-track editor projects, most recently updated first.
create_studio_project	Create an empty Studio project with the editor's default canvas and one track.
get_studio_project	One Studio project including its full timeline.
update_studio_project	Rename a Studio project, move it to a folder, or change its canvas settings.
delete_studio_project	Delete a Studio project and its timeline.
set_studio_timeline	Replace a project's whole timeline.
duplicate_studio_project	Copy a Studio project, timeline and all.
export_studio_project	Render a Studio project's timeline to a video.
share_studio_project	Get or create a public share link for a Studio project.
list_studio_templates	Templates available to the workspace: its own, plus Vidocu's global gallery (marked global: true).
use_studio_template	Start a new Studio project from a template.

Remix

Tool	What it does
list_remixes	Remixes in the workspace, most recently updated first.
create_remix	Set up a remix from a workspace video (videoId) or an external URL (videoUrl plus durationSec).
get_remix	One remix, including the full analysis once its status is 'ready'.
update_remix	Rename a remix or move it to a project folder.
delete_remix	Delete a remix and its analysis.
analyze_remix	Find the shorts worth cutting and draft the blog and social copy.
export_remix	Produce one output from an analyzed remix.
regenerate_remix_text	Rewrite the blog post, LinkedIn posts or X thread from the analyzed transcript.
list_remix_exports	Exports produced from a remix, with their status and download URLs.

Voices, avatars and languages

Tool	What it does
list_languages	List every language Vidocu can transcribe, translate and narrate, with the exact code each operation expects.
list_voices	List voices that can be used as voiceId when generating a voiceover.
delete_voice	Delete one of the workspace's cloned voices.
list_avatars	List AI avatars usable with the avatar generation tool.
get_avatar	Get one avatar by ID.
create_avatar	Create a photo avatar for the workspace from an image URL.

Brand kit

Tool	What it does
get_brand_kit	Get the workspace's Brand Kit.
update_brand_kit	Change Brand Kit defaults.
get_pronunciations	Get the workspace's pronunciation overrides.
set_pronunciations	Replace the workspace's pronunciation overrides.
list_brand_skills	List the workspace's brand skills.
create_brand_skill	Create a brand skill: markdown instructions describing writing style, terminology, pacing or structure.
update_brand_skill	Change a brand skill's name, domain or content.
delete_brand_skill	Delete a brand skill.
get_glossary	Get the workspace's glossary.
set_glossary	Replace the workspace's glossary.
import_glossary	Import glossary terms from CSV text.
list_brand_assets	The reusable files a workspace renders with: opening and closing scenes, watermarks, music, backgrounds.
create_brand_asset	Record an already-uploaded file as a brand asset.
delete_brand_asset	Remove a brand asset record.

Approvals, locks and comments

Tool	What it does
lock_video	Freeze a video's content so it stays stable through an approval cycle.
unlock_video	Unfreeze a locked video so it can be edited again.
request_approval	Send a video for approval.
list_approvals	List approval requests for the workspace, newest first.
get_video_approvals	Every approval round for one video, newest first.
decide_approval	Approve or reject an approval request.
withdraw_approval	Withdraw a pending approval round.
list_comments	List review comments on a video, oldest first.
add_comment	Add a review comment to a video, optionally pinned to a timestamp in seconds.
delete_comment	Delete a review comment from a video.

Micro-tools

Tool	What it does
list_tools	List all available Vidocu video processing tools.
get_tool	Get details and parameter schema for a specific tool.
execute_tool	Execute a video processing tool.

Jobs, usage and webhooks

Tool	What it does
get_job_status	Check the status of an async job (analysis, export, translation, voiceover, tool execution, or process pipeline).
list_jobs	List recent jobs for the workspace, newest first.
get_usage	Get the current API plan, usage counters, and limits for the authenticated workspace.
get_credit_costs	What each API operation costs, alongside the current balance.
list_webhooks	List webhook subscriptions for the workspace.
create_webhook	Subscribe an HTTPS endpoint to Vidocu events.
update_webhook	Change a webhook's URL, event subscriptions, or enabled state.
delete_webhook	Delete a webhook subscription.

OAuth scopes

With OAuth, the consent screen lists the scopes the client asks for, grouped by area, before you approve. Each tool needs one scope, for example videos:read for list_videos or recordings:write for start_recording. The connection acts as the user who approved it, so their workspace role still decides what each tool may do.

See OAuth Scopes for every scope and what it grants.

Async operations

Some operations (analyze, export, translate, voiceover, process, execute tool) run asynchronously. These tools return a jobId immediately. Use get_job_status to check progress:

You: "Analyze this video: https://example.com/demo.mp4"

Claude: I'll upload and analyze the video.
→ calls upload_video
→ calls analyze_video → returns { jobId: "analysis_..." }

Claude: The analysis is running. Let me check the status.
→ calls get_job_status → returns { status: "completed", result: { ... } }

Claude: Analysis complete! The video has 24 subtitles generated.

Example conversations

Generate subtitles:

"Upload this video and generate English subtitles: https://example.com/demo.mp4"

Export with subtitles:

"Export my latest video with subtitles burned in"

Translate:

"Translate the subtitles for video vid_abc123 to Spanish and French"

Full pipeline:

"Process this video end-to-end — analyze it, generate a help article, and export: https://example.com/tutorial.mp4"