TikTok MCP
틱톡 MCP
TikTok MCP는 TikNeuron을 통해 TikTok 액세스를 Claude AI 및 기타 앱에 통합합니다. 이 TikTok MCP를 사용하면
TikTok 비디오를 분석하여 바이러스성 요인을 파악합니다.
TikTok 비디오에서 콘텐츠를 가져오세요
TikTok 영상으로 채팅하기
사용 가능한 도구
틱톡_사용가능한_자막
설명:
사용 가능한 자막, 즉 TikTok 동영상 콘텐츠를 조회합니다. 이 기능은 TikTok 동영상에 사용 가능한 콘텐츠(자막)가 있는지 확인하는 데 사용됩니다. 동영상에 사용 가능한 자막을 반환합니다. 자막은 자동 음성 인식, 기계 번역, 크리에이터 캡션 등 다양한 언어와 형식으로 제공됩니다.
입력 매개변수:
tiktok_url(필수): TikTok 비디오 URL, 예: https://www.tiktok.com/@username/video/1234567890 또는 https://vm.tiktok.com/1234567890
틱톡_자막_받기
설명:
TikTok 동영상 URL의 자막(콘텐츠)을 가져옵니다. 이 기능은 TikTok 동영상의 자막, 콘텐츠 또는 맥락을 가져오는 데 사용됩니다. 언어 코드가 제공되지 않으면 도구는 자동 음성 인식 기능을 통해 자막을 반환합니다.
입력 매개변수:
tiktok_url(필수): TikTok 비디오 URL, 예: https://www.tiktok.com/@username/video/1234567890 또는 https://vm.tiktok.com/1234567890language_code(선택 사항): 자막의 언어 코드입니다. 예를 들어 영어는 en, 스페인어는 es, 프랑스어는 fr 등입니다.
틱톡_게시물_세부정보_받기
설명:
TikTok 게시물의 세부 정보를 가져옵니다. 다음과 같은 비디오 세부 정보를 반환합니다.
설명
작성자 사용자 이름
해시태그
좋아요, 공유, 댓글, 조회수 및 북마크 수
생성 날짜
영상의 길이
입력 매개변수:
tiktok_url(필수): TikTok 비디오 URL, 예: https://www.tiktok.com/@username/video/1234567890 또는 https://vm.tiktok.com/1234567890
Related MCP server: tiktok-mcp
요구 사항
이 TikTok MCP를 사용하려면 다음이 필요합니다.
NodeJS v18 이상( https://nodejs.org/ )
Git( https://git-scm.com/ )
TikNeuron 계정 및 MCP API 키( https://tikneuron.com/tools/tiktok-mcp )
설정
저장소를 복제합니다
지엑스피1
종속성 설치
npm install프로젝트 빌드
npm run build이렇게 하면 build\index.js 파일이 생성됩니다.
Claude AI에서 사용
mcpServers 에 다음 항목을 추가합니다.
"tiktok-mcp": {
"command": "node",
"args": [
"path\\build\\index.js"
],
"env": {
"TIKNEURON_MCP_API_KEY": "XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX"
}
}그리고 경로를 TikTok MCP path 로 바꾸고 XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX TIkNeuron API 키로 바꾸세요.
그러면 mcpServers 다음과 같이 보일 것입니다.
{
"mcpServers": {
"tiktok-mcp": {
"command": "node",
"args": [
"path\\build\\index.js"
],
"env": {
"TIKNEURON_MCP_API_KEY": "XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX"
}
}
}
}Available Tools
3 toolstiktok_get_post_detailsB
Get the details of a TikTok post.This is used for getting the details of a TikTok post.Supports TikTok video url (or video ID) as input.Returns the details of the video like - Description - Video ID - Creator username - Hashtags - Number of likes, shares, comments, views and bookmarks - Date of creation - Duration of the video - Available subtitles with language and source information
| Name | Required | Description | Default |
|---|---|---|---|
| tiktok_url | Yes | TikTok video URL, e.g., https://www.tiktok.com/@username/video/1234567890 or https://vm.tiktok.com/1234567890, or just the video ID like 7409731702890827041 |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It lists many return fields (likes, shares, comments, etc.), which is helpful, but does not disclose authentication, rate limits, or potential errors.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is moderately concise but has redundancy (first two sentences say similar things). It lists return fields in a bullet-like manner, which aids readability.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has one parameter and no output schema, the description adequately covers input and output fields. However, it lacks context on error handling, authentication, or pagination if applicable.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already describes the parameter in detail, including URL formats and video ID example. The description adds minimal extra value; it mentions 'supports TikTok video url (or video ID)' which matches the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it gets post details and lists specific returned fields, distinguishing it from sibling tools like tiktok_get_subtitle and tiktok_search. However, the first two sentences are redundant.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It implies use when post details are needed and specifies input formats (URL or video ID), but does not provide explicit when-to-use or when-not-to-use guidance compared to alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
tiktok_get_subtitleA
Get the subtitle (content) for a TikTok video url.This is used for getting the subtitle, content or context for a TikTok video.Supports TikTok video url (or video ID) as input and optionally language code from the tool post detailsReturns the subtitle for the video in the requested language and format.If no language code is provided, the tool will return the subtitle of automatic speech recognition.
| Name | Required | Description | Default |
|---|---|---|---|
| tiktok_url | Yes | TikTok video URL, e.g., https://www.tiktok.com/@username/video/1234567890 or https://vm.tiktok.com/1234567890, or just the video ID like 7409731702890827041 | |
| language_code | No | Language code for the subtitle, e.g., en for English, es for Spanish, fr for French, etc. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden; it mentions automatic speech recognition fallback but omits other behaviors like rate limits, authorization, or error handling for missing subtitles.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description has some redundancy (e.g., 'Get the subtitle...' and 'This is used for getting...'). Could be more concise without losing clarity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Adequate for a simple tool with two parameters, but lacks details on return format, error handling, and authentication requirements. Not thoroughly complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so parameters are already described. The description adds little beyond the schema, only mentioning the automatic speech recognition fallback for missing language code.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool gets subtitles for TikTok videos using a URL or ID. This distinguishes it from siblings like tiktok_get_post_details and tiktok_search.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains the tool is for getting subtitles and mentions optional language code. However, it does not explicitly state when not to use it or compare with alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
tiktok_searchA
Search for TikTok videos based on a query.This is used for searching TikTok videos by keywords, hashtags, or other search terms.Supports search query as input and optional cursor and search_uid for pagination.Returns a list of videos matching the search criteria with their details including - Description, video ID, creator, hashtags, engagement metrics, date of creation, duration of the video and available subtitles with language and source information - Pagination metadata for continuing the search
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Search query for TikTok videos, e.g., 'funny cats', 'dance', 'cooking tutorial' | |
| cursor | No | Pagination cursor for getting more results (optional) | |
| search_uid | No | Search session identifier for pagination (optional) |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description must fully convey behavioral traits. Only states that it searches and returns results, but omits necessary details like read-only nature, authentication, rate limits, or side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences but includes a lengthy list of return fields, making it slightly verbose. Purpose is front-loaded, but structure could be tighter.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema, yet description thoroughly lists returned fields and pagination metadata. Adequate for a search tool, though structure of return could be clarified.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and schema descriptions are adequate. Description reiterates parameter usage without adding significant new meaning beyond stating pagination.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the verb 'Search' and resource 'TikTok videos', and differentiates from siblings (get_post_details, get_subtitle) by being a general search tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Describes when to use (search by keywords, hashtags) and mentions pagination with cursor and search_uid, but does not explicitly compare to alternatives or state when not to use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
3 tool updates
- First observed
tiktok_get_post_details - First observed
tiktok_get_subtitle - First observed
tiktok_search
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose: get post details, get subtitles, and search. No overlap, descriptions are clear and specific.
All tools follow a consistent 'tiktok_verb_noun' pattern (get_post_details, get_subtitle, search). Naming is uniform and predictable.
3 tools is appropriate for a focused TikTok MCP that provides core reading operations. Could be slightly expanded, but not under-scoped.
Covers search, post details, and subtitles, but missing user profiles, trending, or interaction features. Notable gaps for a comprehensive TikTok tool set.
Maintenance
Related MCP Connectors
An MCP server that provides tools to discover and retrieve podcast episodes transcripts.
MCP server for ByteDance Seedance AI video generation
MCP server for meme generation, template search, caption rendering, and AI meme creation.
MCP server for Kling AI video generation
Related MCP Servers
- AlicenseAqualityCmaintenanceA Bilibili MCP Server that can retrieve subtitles, danmaku (bullet comments), and comments information from videos using the video URL.320MIT
- 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-
- FlicenseAqualityDmaintenanceAn MCP server that extracts and analyzes subtitles from YouTube and Bilibili videos, supporting time-stamped keyword search and video information retrieval.4-
- AlicenseAqualityBmaintenanceMCP server for TikTok that publishes videos to your own TikTok account and retrieves video performance metrics through TikTok's official Content Posting and Display APIs.636 PyPIMIT