tiktok-studio-mcp
Allows publishing videos to your own TikTok account and reading back performance metrics through TikTok's official Content Posting and Display APIs.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@tiktok-studio-mcp upload the latest video as a draft"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
tiktok-studio-mcp
MCP server for TikTok. Publishes videos to your own TikTok account and reads back how they performed, through TikTok's official Content Posting and Display APIs.
Built as the TikTok counterpart to
yt-studio-mcp.
What it can and cannot do
TikTok's creator APIs are narrower than YouTube's. Rather than advertise tools that cannot work, this server exposes only what the platform actually supports:
capability | supported |
Upload video (drafts or direct post) | yes |
View / like / comment / share counts | yes |
List your videos | yes |
List or moderate comments | no — TikTok offers this only through the Research API, which is gated to academic institutions |
Playlists, captions, thumbnails | no — no API surface |
Related MCP server: TikTok MCP Server
Posting modes
TikTok gates direct publishing behind an app audit, so there are two modes,
selected with TIKTOK_MCP_MODE:
upload(default) — the video lands in your TikTok inbox/drafts and you finish posting it in the app. Works without an audit.publish— posts directly. Requires thevideo.publishscope, which needs TikTok's full app audit (2–4 weeks, demo video, privacy policy, domain verification).
Until the app is audited, TikTok forces everything an unaudited client posts
to private, whatever privacy_level you ask for. post_video says so in its
result rather than letting you assume something published.
Install
claude mcp add tiktok -s user -- uvx tiktok-studio-mcpAuthenticate
Register an app at developers.tiktok.com with
Login Kit, Content Posting API and Display API, requesting the scopes
user.info.basic, video.upload, video.list, video.publish. Set the
Desktop redirect URI to http://localhost:8902/.
export TIKTOK_MCP_CLIENT_KEY=...
export TIKTOK_MCP_CLIENT_SECRET=...
tiktok-studio-mcp authPrefer the environment over --client-key / --client-secret: command-line
arguments are visible to any user on the box via ps and land in shell history.
The flags still work as a fallback.
The flow is headless-friendly: it binds a fixed port and prints the consent URL rather than launching a browser. On a machine with a browser:
ssh -N -L 8902:localhost:8902 user@your-hostthen open the printed URL.
Tools
tool | purpose |
| credentials refresh, account reachable, granted scopes, active mode |
| nickname, allowed privacy levels, duration cap, interaction toggles |
| upload a file; returns |
| poll a |
| your videos, with statistics |
| counts for specific video ids |
post_video calls creator_info first and validates privacy_level against
what the account actually allows, because TikTok rejects mismatches with an
unhelpful error.
Secrets
TIKTOK_MCP_SECRETS selects the backend: file (default,
~/.config/tiktok-studio-mcp/credentials.json, mode 600), env, or vaultproxy.
TikTok rotates refresh tokens — every refresh returns a new one and invalidates the old. This server writes the new token back on every refresh; if it did not, authentication would work for 24 hours and then fail with no obvious cause.
Limits
Enforced by TikTok, surfaced by this server:
6 requests per minute per access token on the init endpoints
5 pending shares per 24 hours
chunked upload: files under 5 MB go whole; otherwise chunks are 5–64 MB, the final chunk may reach 128 MB, 1–1000 chunks, 4 GB maximum
Development
pip install -e '.[dev]'
ruff check src tests
pytestTests use an injected transport and need no TikTok credentials.
License
MIT
Available Tools
6 toolscreator_infoA
Nickname, allowed privacy levels, duration cap, interaction toggles.
Direct-Post-only. TikTok gates this endpoint on video.publish, so it is unavailable — and unnecessary — in upload mode, where the creator picks privacy in the TikTok app. Consulted automatically before a direct post, because TikTok rejects one whose privacy_level the account does not offer.
Inputs: no named parameters.
health_checkA
Credentials refresh, account reachable, and which posting mode is active.
Deliberately backed by /v2/user/info/ (user.info.basic) rather than creator_info: creator_info is a Direct Post endpoint gated on video.publish, so using it here made health_check fail on exactly the upload-only setup this server is built for.
Inputs: no named parameters.
list_videosC
The account's videos, with their statistics.
Inputs: limit, cursor.
post_statusA
Poll a publish_id returned by post_video.
Inputs: publish_id (required).
post_videoA
Upload a video to the authorized account. Returns a publish_id to poll.
In upload mode the video lands in the account's inbox/drafts. In publish mode it posts directly, which requires an audited app — until the audit passes TikTok forces all content from the client to private.
Inputs: file_path (required), caption, dry_run, disable_duet, +3 more.
video_statsB
View, like, comment and share counts for specific video ids.
Inputs: video_ids (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each tool has a clear role: health_check and creator_info cover account status/capabilities, post_video and post_status handle posting, list_videos and video_stats handle video data. The only mild overlap is list_videos already includes statistics, which could make video_stats seem redundant, but it's useful for targeted lookups.
All names are lowercase snake_case and readable, but the pattern varies: verb_noun (post_video, post_status, list_videos), noun_noun (creator_info, video_stats), and noun_verb (health_check). This is a minor deviation from a uniform convention.
Six tools is well-scoped for a TikTok studio MCP, covering account health, creator capabilities, video posting, status polling, and video analytics. No tool feels extraneous.
The core lifecycle (post, poll, list, stats) is complete. Missing update/delete video operations, but the server appears designed for posting and analytics, so these are not critical gaps. Account info and post-mode checks are included.
Maintenance
Related MCP Connectors
MCP server for QPost — lets AI agents publish video and image posts to YouTube, TikTok, Instagram.
TikTok Ads MCP server: run TikTok campaigns, ad groups, ads and reports from AI.
Real-time TikTok videos, profiles, comments, trends & Creative Center ads MCP. OAuth or API key.
Build, run, schedule, and publish AI video pipelines to YouTube and TikTok from any MCP client.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceMCP server for analyzing TikTok data for insight extraction6MIT
- AlicenseBqualityNot gradedmaintenanceA comprehensive MCP server that enables AI assistants to search, download, and analyze TikTok content while also performing active tasks like publishing videos and interacting with posts. It provides full automation capabilities for TikTok through browser session management and anti-detection features.122MIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server that enables LLMs to automatically upload videos to the Douyin (TikTok China) creator platform with features like automated login, smart upload, SMS verification, and flexible publishing.1MIT
- FlicenseBqualityDmaintenanceMCP server for TikTok that enables searching videos, users, hashtags, and fetching trending content, user profiles, and video details via official API or public scraping.8-