TikTok MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| FFMPEG_PATH | No | Path to an ffmpeg binary. Default: ffmpeg on PATH, else the bundled one. | ffmpeg |
| TRANSCRIBE_MODEL | No | Model name. Default whisper-large-v3. Use whisper-1 for OpenAI. | whisper-large-v3 |
| TIKTOK_MCP_CHANNEL | No | Force chrome, msedge, or chromium. Auto prefers an installed Chrome/Edge over bundled Chromium. Default auto. | auto |
| TRANSCRIBE_API_KEY | No | API key for the speech-to-text endpoint. Required for transcription unless using a keyless local server. | |
| TRANSCRIBE_API_URL | No | Full speech-to-text endpoint, used verbatim. Required for transcription. Examples: https://api.groq.com/openai/v1/audio/transcriptions, https://api.openai.com/v1/audio/transcriptions, http://localhost:8000/v1/audio/transcriptions | |
| TIKTOK_MCP_HEADLESS | No | Set to false to show the browser while debugging. Default true. | true |
| TIKTOK_MCP_WINDOW_S | No | Length of the request window in seconds. Default 300. | 300 |
| TIKTOK_MCP_LOG_LEVEL | No | DEBUG, INFO (default), WARNING, ERROR. | INFO |
| TIKTOK_MCP_SETTLE_MS | No | How long a page is given to finish rendering in milliseconds. Default 2500. | 2500 |
| TIKTOK_MCP_COOLDOWN_S | No | First cooldown after a block in seconds; doubles on each further block. Default 90. | 90 |
| TIKTOK_MCP_CACHE_TTL_S | No | How long a read is reused instead of re-requested in seconds. Set 0 to disable. Default 300. | 300 |
| TIKTOK_MCP_PROFILE_DIR | No | Where the browser profile lives. Default: OS cache dir (%LOCALAPPDATA%\tiktok-mcp\browser-profile on Windows). | OS cache dir |
| TIKTOK_MCP_COOLDOWN_MAX_S | No | Ceiling for cooldown doubling in seconds. Default 900. | 900 |
| TIKTOK_MCP_MIN_INTERVAL_S | No | Minimum seconds between TikTok requests. Default 4. | 4 |
| TIKTOK_MCP_BLOCK_TELEMETRY | No | Drop TikTok's ad and telemetry calls. Default true. | true |
| TIKTOK_MCP_PERSIST_PROFILE | No | Reuse one browser profile so TikTok cookies survive restarts. Default true. | true |
| TIKTOK_MCP_REQUESTS_PER_WINDOW | No | Requests allowed per window. Default 24. | 24 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_profileA | Get a TikTok user's public profile: nickname, bio, verified status, follower, following, like, and video counts, and avatar URL. |
| get_videosA | List a TikTok user's most recent public videos with id, caption, URL, and view count. Returns an empty list with a note if the account is private or TikTok blocks the request. |
| get_commentsA | Get top-level comments on a TikTok video (author, text, likes). An empty list comes with a note when TikTok hides comments from logged-out browsers. |
| search_videosB | Search TikTok videos by keyword or hashtag. Returns id, caption, URL, creator, and view count. |
| discover_creatorsA | Find TikTok creators posting about a topic. Searches the topic as a hashtag and returns unique creators with their profile URL and the video that surfaced them. |
| transcribe_videoA | Transcribe a TikTok video's speech with the server's speech-to-text API. Returns the full text, language, duration, and word-level timestamps when the API supports them. Takes 10-60 seconds. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
Most tools target distinct resources and actions: profile, videos, comments, search, creators, and transcription. The only mild overlap is between search_videos and discover_creators, since both search by topic/hashtag, but their output focus is clearly different (videos vs. creators).
All tool names follow a consistent verb_noun snake_case pattern: get_profile, get_videos, get_comments, search_videos, discover_creators, transcribe_video. The convention is predictable and readable throughout.
Six tools is well-scoped for a read-only TikTok data server, covering core retrieval and analysis needs without redundant operations. Each tool earns its place and the set is easy to navigate.
The surface covers profiles, user videos, comments, keyword search, creator discovery, and transcription, which handles most public TikTok research workflows. Minor gaps remain, such as no single-video lookup by ID or reply-level comments, but agents can work around these.