OpusClip MCP connector for AI agents

Tools your video clipping agent reaches for on OpusClip, scoped per user.

CALL ANY TOOL

30 tools for video clipping: submit videos, list and preview ranked clips, read transcripts, edit and export clips, manage collections, and request social posts.

opusclipmcp_opusclip_add_clip_to_collection

Opusclip add clip to collection

Adds a clip (projectId + clipId) to a collection. Calling twice for the same clip+collection returns an error per the underlying service.

Parameters

Name

Type

Required

Description

clipId

string

Required

The clip ID within the project.

collectionId

string

Required

Target collection ID.

projectId

string

Required

The clip project ID.

opusclipmcp_opusclip_analyze_video

Opusclip analyze video

opusclipmcp_opusclip_apply_editing_script

Opusclip apply editing script

opusclipmcp_opusclip_create_censor_job

Opusclip create censor job

opusclipmcp_opusclip_create_collection

Opusclip create collection

opusclipmcp_opusclip_create_post_task

Opusclip create post task

opusclipmcp_opusclip_create_social_copy_job

Opusclip create social copy job

opusclipmcp_opusclip_create_upload_link

Opusclip create upload link

opusclipmcp_opusclip_describe_clip

Opusclip describe clip

opusclipmcp_opusclip_duplicate_clip

Opusclip duplicate clip

opusclipmcp_opusclip_edit_clip

Opusclip edit clip

opusclipmcp_opusclip_export_clip

Opusclip export clip

opusclipmcp_opusclip_export_collection

Opusclip export collection

opusclipmcp_opusclip_get_editing_script

Opusclip get editing script

opusclipmcp_opusclip_get_social_copy_job

Opusclip get social copy job

opusclipmcp_opusclip_get_transcript

Opusclip get transcript

opusclipmcp_opusclip_get_usage

Opusclip get usage

opusclipmcp_opusclip_list_brand_templates

Opusclip list brand templates

opusclipmcp_opusclip_list_clips

Opusclip list clips

opusclipmcp_opusclip_list_clips_in_collection

Opusclip list clips in collection

opusclipmcp_opusclip_list_collections

Opusclip list collections

opusclipmcp_opusclip_list_projects

Opusclip list projects

opusclipmcp_opusclip_list_scheduled_posts

Opusclip list scheduled posts

opusclipmcp_opusclip_list_social_accounts

Opusclip list social accounts

opusclipmcp_opusclip_preview_clips

Opusclip preview clips

opusclipmcp_opusclip_schedule_publish

Publish opusclip schedule

opusclipmcp_opusclip_share_project

Opusclip share project

opusclipmcp_opusclip_submit_project

Opusclip submit project

Submits a long-form video URL to OpusClip. Three submit modes, chosen by which params are set: (1) AI clipping (default, no skip flags) -- cuts the source into short, curated, ranked clips. (2) no-clip / full-video reframe -- set skipSlicing:true to keep the FULL video as ONE output (reframe + captions, no cutting into clips); use this for asks like "don't cut it into clips", "reframe the whole video", or "convert horizontal to vertical without clipping" (see skipSlicing). (3) no-curation passthrough -- set skipCurate:true to skip curation entirely; this also returns ONE full-length output rather than multiple clips, and it is NOT ranked or scored, so do not choose it when the user wants several clips (see skipCurate). Returns a project ID the agent can poll via list_clips until processing finishes. Mirrors the CLI's `submit` command. Charges against the org's API/MCP quota.

Parameters

Name

Type

Required

Description

videoUrl

string

Required

Public URL of the long-form video. Supported sources: YouTube, Google Drive, Vimeo, Zoom, Rumble, Twitch, Facebook, LinkedIn, X, Dropbox, Riverside, Loom, Frame.io, StreamYard, or any public S3 mp4 (up to 10GB).

aspectRatio

string

Optional

Optional output aspect ratio: 'portrait' (9:16), 'square' (1:1), 'landscape' (16:9), or 'four_five' (4:5). Defaults to portrait. One of: `portrait`, `square`, `landscape`, `four_five`. Default: `portrait`.

brandTemplateId

string

Optional

Optional brand template ID (from list_brand_templates).

clipDurationsSec

array

Optional

Optional clip duration buckets in seconds, e.g. [[0,30],[30,60]]. Each inner pair is [minSec, maxSec]. Omit to let OpusClip choose.

customPrompt

string

Optional

Optional free-text prompt steering curation, mirroring the CLI submit --prompt.

enableAutoHook

boolean

Optional

Optional flag to add an AI-generated hook to the start of each clip. Applies only to a clipping run -- not compatible with skipSlicing or skipCurate. Omit to inherit the brand template / org default.

enableCaption

boolean

Optional

Optional flag to turn captions on or off. Omit to inherit the brand template default.

genre

string

Optional

Optional curation genre/topic hint, mirroring the CLI submit --genre. Omit to let OpusClip choose.

model

string

Optional

Optional AI clipping model, mirroring the CLI submit --model. Omit to let OpusClip choose.

rangeEnd

number

Optional

Optional end of the source-video range to use, in seconds. Must be >= rangeStart. Pair with rangeStart to limit processing to a slice of the video instead of the whole thing. Applies to the default clipping mode, where it bounds which part of the source clips are drawn from. NOT honored in no-clip mode: combined with skipSlicing the render currently ignores the range and outputs the full source, so do not use the pair to ask for one segment of a no-clip render. Omit to use the whole video.

rangeStart

number

Optional

Optional start of the source-video range to use, in seconds. Pair with rangeEnd to limit processing to a slice of the video instead of the whole thing. Applies to the default clipping mode, where it bounds which part of the source clips are drawn from. NOT honored in no-clip mode: combined with skipSlicing the render currently ignores the range and outputs the full source, so do not use the pair to ask for one segment of a no-clip render. Omit to use the whole video.

removeFiller

boolean

Optional

Optional flag to remove filler words from the rendered clips, mirroring the CLI submit --remove-filler.

skipCurate

boolean

Optional

Optional flag to skip all curation steps, mirroring the CLI submit --skip-curate. Bypasses curation entirely, which also means the submission returns ONE full-length output (the whole video, or the selected range) rather than multiple clips, with no ranking or scores -- do not choose it when the user wants several clips. Clip-only options (clipDurationsSec, enableAutoHook) do not apply and are rejected when set together. Distinct from skipSlicing, which also returns one full-length output but still runs curation over it.

skipSlicing

boolean

Optional

THIS IS THE NO-CLIP MODE: set true to keep the FULL video as a single output instead of cutting it into clips -- import / reframe / caption the whole video, with nothing trimmed away. Use for asks like "don't cut it into clips", "reframe the whole video", or "convert horizontal to vertical without clipping". Still available together with this: enableCaption (captions on/off) and aspectRatio (output orientation). Do NOT pair with rangeStart/rangeEnd expecting only that segment -- the range is currently ignored in this mode and the full source is rendered. Conflicts with clip-only options enableAutoHook and clipDurationsSec -- rejected when set together with this. Distinct from skipCurate: this suppresses only the CUTTING and still runs the curation pipeline over the whole video (so the single output can carry curation scores), whereas skipCurate bypasses curation entirely. To skip curation itself, use skipCurate.

sourceLang

string

Optional

Optional source language code (e.g. 'en', 'es'). Omit for auto-detect.

targetLang

string

Optional

Optional target language code (e.g. 'es', 'fr') to translate the rendered clips into -- translated text and captions, not synthesized voice. Omit to keep the source language.

title

string

Optional

Optional title for the uploaded video, mirroring the CLI submit --title.

topicKeywords

array

Optional

Optional topic keywords - only relevant when model='ClipAnything'.

webhookUrl

string

Optional

Optional webhook URL called when the project concludes, mirroring the CLI submit --webhook.

opusclipmcp_opusclip_unschedule_publish

Publish opusclip unschedule

opusclipmcp_opusclip_whoami

Opusclip whoami

Build your Agent

Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.

import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// OpusClip MCP tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["opusclipmcp"], toolNames: [
    "opusclipmcp_opusclip_submit_project",
    "opusclipmcp_opusclip_list_clips",
    "opusclipmcp_opusclip_export_clip"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Clip this webinar recording and list the top clips" }] });

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["opusclipmcp"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Clip this webinar recording and list the top clips" }],
  tools,
});

// Execute the tool call with the user's vaulted OpusClip token
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["opusclipmcp"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Clip this webinar recording and list the top clips" }],
  tools,
});

// Tool call runs with the user's vaulted OpusClip token
await sk.tools.executeTool(msg.content, "user_123");

import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["opusclipmcp"] }, pageSize: 100,
});

const agent = new Agent({
  name: "video_agent",
  model: "gemini-2.5-pro",
  instruction: "OpusClip MCP tools scoped to this user",
  tools,
});

await agent.run("Clip this webinar recording and list the top clips");

Try these prompts

Copy any prompt into your agent. Each maps directly to a OpusClip MCP tool. Click to copy, paste into your agent, done.

Clip projects

Copy the prompt

Copied

Submit this webinar video URL to OpusClip and cut it into short clips.

Copy the prompt

Copied

List my clip projects from this week.

Copy the prompt

Copied

Show the top 6 clips from my latest project with scores and hashtags.

Edit and export

Copy the prompt

Copied

Turn on captions and keyword highlights for this clip.

Copy the prompt

Copied

Run the profanity censor on this clip's captions.

Copy the prompt

Copied

Export this clip in HD and give me the download link.

Collections and social

Copy the prompt

Copied

Create a collection called Q3 launch and add these clips to it.

Copy the prompt

Copied

Generate social copy for this clip for my TikTok account.

Copy the prompt

Copied

Schedule this clip to publish on YouTube next Tuesday at 14:00 UTC.

SEE HOW AUTH WORKS

Each user signs in to OpusClip once; Scalekit stores and refreshes their tokens. Tokens stay vaulted, every call is scope checked, and every action is logged.

Authorize

Your user connects

OpusClip MCP

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

Store

Their

OpusClip MCP

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

Resolve

When your agent calls a

OpusClip MCP

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

Audit

Every

OpusClip MCP

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

See the same per-user auth pattern across other media and video connectors.

GTM and RevOps Teams

Competitive intelligence briefing agent

Scans Gong calls for competitor mentions, matches each one to its Notion battlecard, and DMs every affected rep a single Slack digest per cycle. Every call runs as the PMM who owns the briefing, never a shared bot.

GTM and RevOps Teams

Outbound prospecting agent

Searches Apollo for prospects matching your ICP, scores and ranks them, drafts personalized outreach in Gmail, and logs every send to Google Sheets. Mail goes out as the rep, not from a shared inbox.

Engineering Teams

Slack triage

Polls Slack for new messages, classifies bugs and support requests with a LangGraph router, files GitHub issues or Zendesk tickets, and confirms in the thread.

Support and Ops Teams

Meeting prep

Pulls agenda, participant context, and open action items before every meeting.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared OpusClip token looks fine in a demo. In production every clip project and post request looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

OpusClip today. Ten connectors tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access OpusClip as the user or as a shared key?

As the user. Each user signs in to OpusClip once, and Scalekit stores and refreshes their tokens. Audit logs attribute every clip edit and post request to that user, not a shared service account.

Where is the OpusClip OAuth token stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.

Can I limit what the agent does in OpusClip?

Yes. Filter by tool name in listScopedTools to expose only what you want. Scalekit also enforces scope checks before every API call.

What happens when a user revokes OpusClip access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Does the agent post to social accounts without review?

No. The post, schedule, unschedule, and share tools return an approval_url, and the action only happens after the user confirms it in the OpusClip app. The agent prepares the request; the user approves it.

On this page

Tool and actions Framework Compatibility Starter Prompt Auth Lifecycle Try Other Agents Why Scalekit