CapCut MCP server Let your AI agent export and share your CapCut drafts.

Connect CapCut to Claude, ChatGPT, n8n or a script. Your agent exports drafts, adds auto captions, sends review links and manages team spaces in your own CapCut account. Cotlet hosts it, so there is no developer setup and no server to run.

  • Free 7-day trial, no card
  • Not affiliated with CapCut
CapCut logo CapCut Cloud Browser

13 tools Read and write

Drafts to review

What can your AI agent do in CapCut? Everything around the edit.

  • Export drafts at a set size and format

  • Add auto captions to a draft

  • Share a draft for review

  • Invite an editor to a team space

  • Check who can edit your spaces

  • Search the template gallery

ChatGPT plugin only

Does CapCut have an MCP server or an API? A ChatGPT plugin, but no public API.

CapCut has no public API for drafts, exports or sharing and publishes no MCP address for Claude or Cursor (checked 6 Nov 2026). Its official AI route is the CapCut plugin for the ChatGPT desktop app on PC, which builds and edits drafts inside a ChatGPT task. Cotlet runs 13 CapCut tools in your own account, hosted, over MCP and REST.

  • The plugin generates media, builds an editable timeline and adds captions, effects and templates in chat. CapCut says it is made for the ChatGPT desktop app on PC, available outside the United States, with the U.S. coming soon.
  • CapCut links no developer portal, API key or webhooks documentation. Zapier and n8n have no CapCut app page.
  • Community servers on GitHub mostly write draft files on your own computer. You open them in CapCut and run the export there.
CapCut's ChatGPT plugin, a community GitHub server and Cotlet compared
What you need CapCut plugin for ChatGPTCommunity MCP serverCotlet
Export at a chosen size and format Finish in the editor Draft file, export in CapCut Yes
Review links, spaces and members Not listed by CapCut No Yes, links after your OK
Works in Claude, n8n or a script ChatGPT desktop only Local MCP clients Yes
Runs on a schedule, 24/7 Inside a ChatGPT task While your computer is on Hosted
No install, no key, no code Install from a prompt Clone and run it Sign in once

Checked 6 Nov 2026. Sources: CapCut: CapCut × ChatGPT plugin · CapCut newsroom: CapCut World Los Angeles · GitHub: VectCutAPI · CapCut: Collaborate on CapCut online

Set up once

How does Cotlet connect to CapCut? One account, two ways to connect.

  1. 1Sign in to CapCut

    Use your own account in its Cotlet Cloud Browser.

  2. 2Choose MCP or REST

    Connect your agent or create a Cotlet API key.

  3. 3Run your workflow

    Ask your agent or send an HTTP request.

We never keep your CapCut password, and by default no review link or invite goes out until you approve it. Who can see your session

Any MCP client

Connect CapCut to your agent or workflow

Use MCP with your AI agent, or HTTP requests in n8n, Make, Zapier and scripts. Follow the MCP setup below or jump to the REST guide.

  1. 1

    Enable CapCut for agents. Sign up, log in to CapCut in its Cloud Browser, then press Enable for agents.

  2. 2

    Add the Cotlet address. Add https://cotlet.dev/mcp/v1 as an MCP server or connector in your agent.

  3. 3

    Approve the connection. Chat apps ask you to sign in to Cotlet. Editors, n8n and scripts use an API key from the console.

One shared address, https://cotlet.dev/mcp/v1, also carries CapCut next to your other apps. If you enable CapCut after connecting, refresh the connector so the new tools show up.

Claude
Settings > Connectors > Add custom connector
URL: https://cotlet.dev/mcp/v1/connect

Claude Code:
claude mcp add --transport http cotlet-capcut \
  https://cotlet.dev/mcp/v1 \
  --header "Authorization: Bearer $COTLET_API_KEY"
ChatGPT
Settings > Apps & Connectors > Create
MCP server URL: https://cotlet.dev/mcp/v1/connect
Authentication: OAuth
Cursor
// ~/.cursor/mcp.json
{
  "mcpServers": {
    "cotlet-capcut": {
      "url": "https://cotlet.dev/mcp/v1",
      "headers": { "Authorization": "Bearer ${env:COTLET_API_KEY}" }
    }
  }
}
Codex
# ~/.codex/config.toml
[mcp_servers.cotlet-capcut]
url = "https://cotlet.dev/mcp/v1"
bearer_token_env_var = "COTLET_API_KEY"
n8n
MCP Client Tool (inside an AI Agent)
Transport: HTTP Streamable
URL: https://cotlet.dev/mcp/v1
Auth: Bearer, <your key>
Tool: capcut_read
Make, Zapier
Make: MCP Client > Call a tool
Zapier: MCP Client by Zapier > Run Tool
Server URL: https://cotlet.dev/mcp/v1
Token: <your key>
Tool: capcut_write
Scripts and HTTP

How to use the CapCut REST API

Create your Cotlet API key

Sign in to your CapCut account in its Cotlet Cloud Browser and enable the app for agents. Managing members and roles needs owner or admin rights in the space.

Create a Cotlet API key with access to CapCut and its read operations. Store it as COTLET_API_KEY in your environment or automation platform's credential store.

Make your first CapCut API request

cURL: list_drafts

curl https://cotlet.dev/api/v1/capcut/drafts \
  -H "Authorization: Bearer $COTLET_API_KEY"

Read drafts and continue the list

A successful REST call puts the tool output in result. This illustrative response excerpt omits call IDs, messages and credit details.

Illustrative response excerpt

{
  "status": "success",
  "app": "capcut",
  "tool": "list_drafts",
  "result": {
    "drafts": [
      {
        "draft_id": "dr_5c7e10",
        "name": "Launch teaser",
        "editor": "Maya Brooks",
        "updated_at": "2026-11-04T16:20:00Z"
      }
    ],
    "next_cursor": null
  }
}

Read result.drafts and pass result.next_cursor unchanged as cursor until it is null. Without space_id the call reads your Default space; pass a space_id from list_spaces for the others.

Keep draft IDs in your workflow so later runs match the same drafts. Only one member edits a draft at a time, so editor tells you who holds it.

CapCut workflows for agents and automations

CapCut workflows you configure
ToolConnect throughExample workflow
n8nHTTP RequestRead list_drafts for a space every Monday and post the draft names and editors to your team channel.
Python or Node.jsREST APICall list_space_members for each space from list_spaces and write a roles report to a sheet.
MakeHTTP > Make a requestCall list_share_history with direction set to shared_by_you and keep a list of the review links that are out.

Send Authorization: Bearer <your Cotlet API key> in request headers. You configure the schedule, destination and record comparisons.

Cotlet reads CapCut; your workflow steps write to your chosen destination. These HTTP workflows do not require a native Cotlet connector or a prebuilt template.

The API and MCP reference lists operations and inputs. The REST API guide explains authentication, errors and approvals.

6 read, 7 write

CapCut API endpoints and MCP tools

Team spaces and members6

CapCut allows 5 spaces per user, Default space included, and 30 members per space (CapCut help, Aug 2026).

  • list_spaces Your CapCut spaces with your role and member count. read

    Lists the spaces in your Workspace, the Default space first. Each space shows your role (owner, admin or collaborator) and how many members it has. CapCut allows up to 5 spaces per user, counting the Default space, and up to 30 members in a space. Use space_id in the other tools.

    MCP callcapcut_read → list_spaces

    REST endpointGET https://cotlet.dev/api/v1/capcut/spaces

    Parameters

    No parameters.

    Example response

    {
      "spaces": [
        {
          "space_id": "sp_8f21c4",
          "name": "Default space",
          "role": "owner",
          "members": 1
        },
        {
          "space_id": "sp_31ab9d",
          "name": "Client reviews",
          "role": "owner",
          "members": 4
        }
      ]
    }
  • list_space_members Members of a space with their role. read

    Lists the members of one space with name, email and role: owner, admin or collaborator. Admins can edit and manage every file in the space; collaborators manage only the files they posted. You need to be a member of the space to read it.

    MCP callcapcut_read → list_space_members

    REST endpointGET https://cotlet.dev/api/v1/capcut/space-members

    Parameters

    Parameters: list_space_members
    NameTypeDescription
    space_id string required string A space_id from list_spaces.

    Example input

    {
      "space_id": "space_8c41d2"
    }

    Example response

    {
      "members": [
        {
          "name": "Maya Brooks",
          "email": "maya@example.com",
          "role": "owner"
        },
        {
          "name": "Tom Becker",
          "email": "tom@example.com",
          "role": "collaborator"
        }
      ]
    }
  • create_space Creates a new team space in your Workspace. writeasks first

    Creates a space with the name you give. CapCut allows up to 5 spaces per user, counting the Default space, and says deleting a space is not supported, so every call is permanent. Returns the new space_id. By default you confirm each call; you can switch that off for this tool.

    MCP callcapcut_write → create_space

    REST endpointPOST https://cotlet.dev/api/v1/capcut/spaces

    Parameters

    Parameters: create_space
    NameTypeDescription
    name string required string Name of the new space.

    Example input

    {
      "name": "Jane Doe"
    }

    Example response

    {
      "space_id": "sp_77de02",
      "name": "Q4 campaigns",
      "role": "owner",
      "members": 1
    }
  • invite_members Sends space invitations by email through Invite members. writeasks first

    Enters each address in Invite members and presses Send. A space holds up to 30 members. New members arrive without admin rights; change their role with set_member_role after they join. By default you confirm each call; you can switch that off for this tool.

    MCP callcapcut_write → invite_members

    REST endpointPOST https://cotlet.dev/api/v1/capcut/spaces/{space_id}/members/invite

    Parameters

    Parameters: invite_members
    NameTypeDescription
    space_id string required string A space_id from list_spaces.
    emails array required array Email addresses to invite.

    Example input

    {
      "space_id": "space_8c41d2",
      "emails": "jane@example.com"
    }

    Example response

    {
      "space_id": "sp_31ab9d",
      "invited": [
        "tom@example.com"
      ],
      "status": "sent"
    }
  • set_member_role Sets a member's access in a space to admin or collaborator. writeasks first

    Changes the role in the space's member settings. An admin can edit and manage every video file in the space; a collaborator manages only the files they posted. You need to be an owner or admin of the space. By default you confirm each call; you can switch that off for this tool.

    MCP callcapcut_write → set_member_role

    REST endpointPUT https://cotlet.dev/api/v1/capcut/spaces/{space_id}/member-role

    Parameters

    Parameters: set_member_role
    NameTypeDescription
    space_id string required string A space_id from list_spaces.
    email string required string Email of an existing member.
    role enum required enum admin or collaborator.

    Example input

    {
      "space_id": "space_8c41d2",
      "email": "jane@example.com",
      "role": "admin"
    }

    Example response

    {
      "space_id": "sp_31ab9d",
      "email": "tom@example.com",
      "role": "collaborator",
      "status": "updated"
    }

Drafts, captions and export4

Export goes to the Cloud Browser's downloads and reaches no one. 2K and 4K depend on your device and app version.

  • list_drafts Drafts in a space with who holds editing permission and the last edit. read

    Lists the projects in the Drafts list of one space, in the order CapCut shows them. Each draft has an id, its name, the member who currently holds editing permission and the time of the last edit. Only one member edits a draft at a time, the others get view only. Without space_id it reads your Default space.

    MCP callcapcut_read → list_drafts

    REST endpointGET https://cotlet.dev/api/v1/capcut/drafts

    Parameters

    Parameters: list_drafts
    NameTypeDescription
    space_id string string A space_id from list_spaces. Default: your Default space.
    cursor string string next_cursor from the previous page.

    Example response

    {
      "drafts": [
        {
          "draft_id": "dr_5c7e10",
          "name": "Launch teaser",
          "editor": "Maya Brooks",
          "updated_at": "2026-11-04T16:20:00Z"
        },
        {
          "draft_id": "dr_9a02f3",
          "name": "Customer story",
          "editor": "Tom Becker",
          "updated_at": "2026-11-03T09:05:00Z"
        }
      ],
      "next_cursor": null
    }
  • generate_captions Runs auto captions on a draft and adds the lines to its timeline. write

    Opens the draft, runs Auto captions and returns how many caption lines the app added. It edits the draft in place and reaches no one, so it needs no confirmation. Run it on a draft you are fine changing. If the app asks for a plan upgrade for the language, the call fails with that message and nothing is bought. You need the editing permission on the draft.

    MCP callcapcut_write → generate_captions

    REST endpointPOST https://cotlet.dev/api/v1/capcut/drafts/{draft_id}/captions/generate

    Parameters

    Parameters: generate_captions
    NameTypeDescription
    draft_id string required string A draft_id from list_drafts.
    language string string The language as named in the app's auto captions menu. Default: the app's own choice.

    Example input

    {
      "draft_id": "draft_8c41d2"
    }

    Example response

    {
      "draft_id": "dr_5c7e10",
      "status": "captions_added",
      "language": "English",
      "caption_lines": 42
    }
  • export_draft Exports a draft with the file name, resolution, quality, frame rate and format you set. write

    Opens the draft, applies your settings in Export and Advanced Settings, and returns the settings the app used and the export status. Whether 2K or 4K is offered depends on your device and the app, and the call reports an option the app refuses instead of choosing another one. The export goes to the Cloud Browser's downloads and reaches no one, so it needs no confirmation. Use share_for_review to send a draft to other people.

    MCP callcapcut_write → export_draft

    REST endpointPOST https://cotlet.dev/api/v1/capcut/drafts/{draft_id}/export

    Parameters

    Parameters: export_draft
    NameTypeDescription
    draft_id string required string A draft_id from list_drafts.
    file_name string string Name of the exported file. Default: the draft name.
    resolution string string Resolution as named in the app's Resolution menu, e.g. 1080p. 2K and 4K only where the app offers them.
    quality string string Quality as named in Advanced Settings.
    frame_rate string string Frame rate as named in Advanced Settings.
    format string string File format as named in Advanced Settings, e.g. mp4.

    Example input

    {
      "draft_id": "draft_8c41d2"
    }

    Example response

    {
      "draft_id": "dr_5c7e10",
      "file_name": "Launch teaser",
      "resolution": "1080p",
      "format": "mp4",
      "status": "exported"
    }
  • search_templates Templates from the CapCut gallery that match a search. read

    Searches the template gallery on the web and returns the title and link of each match. It only reads: it does not apply a template to a draft. Results come in the order the gallery shows them.

    MCP callcapcut_read → search_templates

    REST endpointGET https://cotlet.dev/api/v1/capcut/templates/search

    Parameters

    Parameters: search_templates
    NameTypeDescription
    query string required string Search words, e.g. product launch.
    cursor string string next_cursor from the previous page.

    Example input

    {
      "query": "query"
    }

    Example response

    {
      "templates": [
        {
          "title": "Product launch intro",
          "url": "https://www.capcut.com/template-detail/example-product-launch"
        },
        {
          "title": "Clean caption pack",
          "url": "https://www.capcut.com/template-detail/example-clean-captions"
        }
      ],
      "next_cursor": null
    }

Review links and editing permission3

Only one member edits a draft at a time, so a transfer turns the previous editor to view only.

  • list_share_history Drafts shared with you or by you, with the review link. read

    Reads Share history in one direction: shared_with_you or shared_by_you. Each row has the draft name, who shared it and the link. Use it to check what an outside reviewer can still open.

    MCP callcapcut_read → list_share_history

    REST endpointGET https://cotlet.dev/api/v1/capcut/share-histories

    Parameters

    Parameters: list_share_history
    NameTypeDescription
    direction enum required enum shared_with_you or shared_by_you.

    Example input

    {
      "direction": "shared_with_you"
    }

    Example response

    {
      "shares": [
        {
          "draft_name": "Launch teaser",
          "shared_by": "Maya Brooks",
          "visibility": "space",
          "url": "https://www.capcut.com/share/example-review-link"
        }
      ]
    }
  • share_for_review Shares a draft through Export > Share for review so others can comment. writeasks first

    Runs Export > Share for review on the draft and returns the review link. visibility everyone lets anyone with the link open it; space limits it to members of the space. Emails get the link too. A private video cannot be shared outside the team. By default you confirm each call; you can switch that off for this tool.

    MCP callcapcut_write → share_for_review

    REST endpointPOST https://cotlet.dev/api/v1/capcut/drafts/{draft_id}/review/share

    Parameters

    Parameters: share_for_review
    NameTypeDescription
    draft_id string required string A draft_id from list_drafts.
    visibility enum required enum everyone or space.
    emails array array Email addresses that receive the review link.

    Example input

    {
      "draft_id": "dr_5c7e10",
      "visibility": "space",
      "emails": [
        "anna@example.com"
      ]
    }

    Example response

    {
      "draft_id": "dr_5c7e10",
      "visibility": "space",
      "shared_with": [
        "anna@example.com"
      ],
      "url": "https://www.capcut.com/share/example-review-link"
    }
  • transfer_editing_permission Hands editing permission on a draft to another team member. writeasks first

    Opens the draft, chooses Transfer editing permission, picks the member and confirms. Only one member edits a draft at a time, so the previous editor drops to view only. The permission can be taken back the same way. By default you confirm each call; you can switch that off for this tool.

    MCP callcapcut_write → transfer_editing_permission

    REST endpointPOST https://cotlet.dev/api/v1/capcut/drafts/{draft_id}/editing-permission/transfer

    Parameters

    Parameters: transfer_editing_permission
    NameTypeDescription
    draft_id string required string A draft_id from list_drafts.
    email string required string Email of a member of the draft's space.

    Example input

    {
      "draft_id": "draft_8c41d2",
      "email": "jane@example.com"
    }

    Example response

    {
      "draft_id": "dr_5c7e10",
      "editor": "Tom Becker",
      "status": "transferred"
    }
Encrypted, revocable

Who can see my CapCut session, and how do I revoke it?

  • What we store

    Your logged-in CapCut profile, encrypted with AES-256-GCM, in Finland. Not the password.

  • What your agent gets

    The 13 CapCut tools. Never the cookie.

  • What the session sees

    Your drafts, spaces, members and share history.

  • What no tool touches

    Billing, plan, password, two-factor and deleting drafts.

  • If CapCut signs you out

    Your agent gets a link to sign in again. You do it, we never do.

  • How to cut access

    Disable for agents or reset the browser in the Cotlet console.

Our site scores A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory (live results). There is no SOC 2 report or third-party pentest yet.

Tested every 12 h

What happens when CapCut changes? We repair the tool; your prompts stay the same.

between tests of the CapCut tools
12 h
for a call to a CapCut tool paused for repair
$0

When CapCut moves a button or renames a menu, the fix happens on our side and your prompts keep working. status.cotlet.dev watches the site, console and API every 3 minutes.

5 tools ask first

Approvals, undo and mistakes No one outside hears from CapCut until you say so.

  1. 01 Finds the draft Looks it up by name in the space you name.
  2. 02 Sets the visibility Everyone with the link, or the space only.
  3. 03 Waits for your OK The share shows up in your Cotlet console first.
  4. 04 Reports the link Review link, visibility and who got an email.
Which CapCut actions can be undone
ActionUndo
Export a draftDelete the file; the draft is unchanged
Add auto captionsDelete the caption lines in the editor
Share a draft for reviewNo revoke tool here; list_share_history shows which links are out
Invite membersThe email is out; no tool removes a member
Set a member roleSet the old role again
Transfer editing permissionTake it back the same way
Create a spaceNo, CapCut does not support deleting a space

5 of 13 tools ask first: the ones that email or invite someone, change access or create a space. Exports and captions reach no one, so they run at once. Switch the wait off per tool for a scheduled run.

Create a space is permanent. You get 5 spaces, Default included.

MCP call
{
  "name": "share_for_review",
  "arguments": {
    "draft_id": "dr_5c7e10",
    "visibility": "space",
    "emails": [
      "anna@example.com"
    ]
  }
}
REST
curl -X POST https://cotlet.dev/api/v1/capcut/drafts/dr_5c7e10/review/share \
  -H "Authorization: Bearer $COTLET_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"visibility":"space","emails":["anna@example.com"]}'
Tool output
{
  "draft_id": "dr_5c7e10",
  "visibility": "space",
  "shared_with": [
    "anna@example.com"
  ],
  "url": "https://www.capcut.com/share/example-review-link"
}

Scripts and cron jobs reach the same tools over REST at /api/v1/capcut, with the same key and price. A setting CapCut refuses, such as 4K on a device without it, fails with CapCut's message and buys nothing. A failed call costs nothing. The tools table lists the REST path of each tool.

Pay per call

How much does the CapCut MCP server cost?

About $12 a monthfor a small video team exporting 12 drafts a month, 2,120 credits. Your CapCut plan is billed by CapCut as before.

A month of CapCut jobs for one small team, in credits
JobCallsCredits
Auto captions, then export a draft3 × 8240
Export a draft as it is2 × 480
Share a draft for review2 × 6120
Weekly look at spaces and members3 × 4120
Invite an editor and set the role3 × 260
Cloud Browser, 30 days1,500
Total2,120
  • Free 7-day trial, no card
  • 10 credits per successful call, MCP or REST
  • 50 credits a day for the Cloud Browser
  • CapCut lists Free, Pro, Ultra and Teams plans, billed by CapCut

The month is our example: one client-review space of about 4 members, 12 drafts exported, 6 review shares, 2 new editors. No public figure for a typical CapCut team exists. Dollars at the $29 pack rate.

Cotlet credit packs: price, credits and calls at 10 credits each
Credits Price, one time Calls at 10 credits Per 1,000 credits
5,000 $29 500 $5.80
15,000 $79 1,500 $5.27
32,000 $149 3,200 $4.66
60,000 $249 6,000 $4.15

Only successful calls use credits; failed calls and timeouts cost nothing. At a balance of 0 calls pause, never a surprise charge. Authenticate with the Authorization: Bearer header.

Other options

CapCut MCP server on GitHub, the ChatGPT plugin or hosted: which to use Different jobs, so they combine.

Other CapCut tools on GitHub and from CapCut, checked 6 Nov 2026
OptionWhat it doesWhere it stops
CapCut × ChatGPT pluginOfficial. Builds a draft from a prompt or upload, edits the timeline, captions and effects in chat.ChatGPT desktop app on PC. CapCut lists export, sharing and space management in the editor, not in the plugin.
sun-guannan/VectCutAPIHTTP API and MCP mode that write CapCut and Jianying draft files. 2,362 stars, last commit 24 Oct 2026.Runs on your computer with Python and FFmpeg. Its feature list has no spaces, sharing or members.
Hommy-master/capcut-mateFastAPI draft service that works with Coze and n8n. 2,108 stars, last commit 1 Nov 2026.Chinese first. You host it, and it covers drafts, not your team spaces.
mrbuslov/capcut-ai-editorMCP server that cuts silences and repeated takes using CapCut's auto captions. 123 stars, last commit 27 Oct 2026.One editing job on a local project.
Atx-Guy/capcut-mcp-serverMCP wrapper for the VectCutAPI backend. 90 stars, last commit 13 Jan 2026.Needs that backend running on your computer.

Use CapCut's plugin when you shape the cut in ChatGPT. Use a draft writer when you build timelines from code on your own machine. Use Cotlet when the chores around the edit are the job: exports, captions, review links and who can edit, from Claude, ChatGPT or a schedule, with nothing to host.

EU company, since 2019

Who runs Cotlet A company you can look up.

Take Group sp. z o.o. runs Cotlet. It is a software company registered in Poland, EU (VAT PL6342984273), working since 2019, founded by Bart Krawczyk (Co-founder, CTO) and Jake Slugocki (Co-founder, SEO, sales and marketing). Write to contact@cotlet.dev with questions about the CapCut tools.

CapCut MCP and API: questions

How do I connect CapCut to ChatGPT or Claude?

Sign up at cotlet.dev, log in to CapCut once in its Cloud Browser and add Cotlet to ChatGPT or Claude, following the steps in your console. No API key is needed. ChatGPT and Claude then work in your CapCut account through Cotlet, in their phone apps too.

What can ChatGPT do in CapCut?

With Cotlet, ChatGPT, Claude and other AI agents handle jobs like these in CapCut: export drafts at a set size and format; add auto captions to a new draft; send a draft for client review. You ask in plain words, and anything that reaches other people waits for your OK first.

Can I use the CapCut API without an AI agent?

Yes. Call Cotlet's REST API from a script or an HTTP step in n8n, Make or Zapier with your Cotlet key. MCP is the alternative for AI agents; you do not need to connect an agent to use REST.

How do I get access?

Create a free account at https://cotlet.dev, open CapCut under Integrations in the console and log in to CapCut in its Cloud Browser. The trial starts with your first app, no card asked.

Can my agent edit the timeline, cut clips or add effects?

No. The tools cover what sits around the edit: drafts, auto captions, export, review links, team spaces and template search. Cutting, effects and transitions stay in the editor, where you or your team do them by hand.

Do I need CapCut Pro for exports?

Not for the call itself. CapCut's help says 2K and 4K depend on your device, the app version and the platform, and the project resolution must be set before editing. When the app refuses a setting or asks for a plan, export_draft reports it and changes nothing else.

Does CapCut have webhooks?

CapCut documents none (checked 6 Nov 2026). Nothing tells an agent that a draft changed. Run your agent on a schedule instead, for example a weekly list_drafts and list_share_history pass.

Is the MCP server different from the REST API?

Only the door is different. Both expose the same 13 tools, inputs and answers, with one API key and one price. Agents use MCP; scripts and HTTP steps use REST.

Is Cotlet affiliated with CapCut?

No. Cotlet is independent and not affiliated with CapCut or ByteDance.

Give your agent access to CapCut.

Free 7-day trial with 2,000 credits, no card needed.