TikTok MCP
Enables analysis of TikTok videos including retrieving subtitles in multiple languages, obtaining post details (likes, shares, comments, views, creator info, hashtags), and determining virality factors.
Click on "Install 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 MCPget subtitles for https://www.tiktok.com/@chef/video/1234567890"
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 MCP
The TikTok MCP integrates TikTok access into Claude AI and other apps via TikNeuron. This TikTok MCP allows you to
analyze TikTok videos to determine virality factors
get content from TikTok videos
chat with TikTok videos
Available Tools
tiktok_available_subtitles
Description:
Looks up the available subtitle, i.e., content for a TikTok video. This is used for looking up if there is any content (subtitle) available to a TikTok video. Returns the available subtitle for the video which can be in different languages and different formats like Automatic Speech Recognition, Machine Translation or Creator Captions and different languages.
Input Parameters:
tiktok_url(required): TikTok video URL, e.g., https://www.tiktok.com/@username/video/1234567890 or https://vm.tiktok.com/1234567890
tiktok_get_subtitle
Description:
Get the subtitle (content) for a TikTok video url. This is used for getting the subtitle, content or context for a TikTok video. If no language code is provided, the tool will return the subtitle of automatic speech recognition.
Input Parameters:
tiktok_url(required): TikTok video URL, e.g., https://www.tiktok.com/@username/video/1234567890 or https://vm.tiktok.com/1234567890language_code(optional): Language code for the subtitle, e.g., en for English, es for Spanish, fr for French, etc.
tiktok_get_post_details
Description:
Get the details of a TikTok post. Returns the details of the video like:
Description
Creator username
Hashtags
Number of likes, shares, comments, views and bookmarks
Date of creation
Duration of the video
Input Parameters:
tiktok_url(required): TikTok video URL, e.g., https://www.tiktok.com/@username/video/1234567890 or https://vm.tiktok.com/1234567890
Related MCP server: mcp-youtube-transcript
Requirements
For this TikTok MCP, you need
NodeJS v18 or higher (https://nodejs.org/)
Git (https://git-scm.com/)
TikNeuron Account and MCP API Key (https://tikneuron.com/tools/tiktok-mcp)
Setup
Clone the repository
git clone https://github.com/Seym0n/tiktok-mcp.gitInstall dependencies
npm installBuild project
npm run buildThis creates the file build\index.js
Using in Claude AI
Add the following entry to mcpServers:
"tiktok-mcp": {
"command": "node",
"args": [
"path\\build\\index.js"
],
"env": {
"TIKNEURON_MCP_API_KEY": "XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX"
}
}and replace path with the path to TikTok MCP and XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX with TIkNeuron API Key
so that mcpServers will look like this:
{
"mcpServers": {
"tiktok-mcp": {
"command": "node",
"args": [
"path\\build\\index.js"
],
"env": {
"TIKNEURON_MCP_API_KEY": "XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX"
}
}
}
}Available Tools
3 toolstiktok_available_subtitlesC
Looks up the available subtitle, i.e., content for a TikTok video.This is used for looking up if there is any content (subtitle) available to a TikTok video.Supports TikTok video url as input in objectReturns the available subtitle for the video which can be in different languages and differentformats like Automatic Speech Recognition, Machine Translation or Creator Captionsand different languages.
| 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 |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. The description fails to clarify whether the operation is read-only, requires authentication, or any rate limits. It implies returning subtitle data but doesn't disclose the full behavior.
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 verbose and repetitive, restating the same idea multiple times. It could be condensed into a single clear sentence.
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?
Without an output schema, the description should clearly explain the return value structure. It only mentions 'different languages and formats' but lacks specificity, leaving ambiguity about the response.
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% with a clear description for 'tiktok_url'. The tool description adds no additional semantic value beyond what the schema already provides.
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 states it 'Looks up the available subtitle' but also says 'Returns the available subtitle', creating ambiguity about whether it checks availability or retrieves content. With sibling 'tiktok_get_subtitle', the exact purpose is unclear.
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 mentions 'looking up if there is any content available' but does not explicitly contrast with siblings or specify when to use this tool instead of alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
tiktok_get_post_detailsA
Get the details of a TikTok post.This is used for getting the details of a TikTok post.Supports TikTok video url as input.Returns the details of the video like - Description - Creator username - Hashtags - Number of likes, shares, comments, views and bookmarks - Date of creation - Duration of the video
| 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 |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It correctly implies a read operation and lists outputs, but does not disclose potential side effects, authentication requirements, rate limits, or error handling (e.g., for private videos). The transparency is adequate but could be improved.
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 somewhat redundant: 'Get the details of a TikTok post.This is used for getting the details of a TikTok post.' It could be more concise by removing the repetition. The list of return fields is clear but unstructured. Overall, it is not excessively long but 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?
For a simple tool with one parameter and no output schema, the description covers the core purpose, input format, and key output fields. It lacks information about accessibility restrictions (public only) and error scenarios, but these are minor gaps. The description is largely sufficient.
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 input schema already describes the 'tiktok_url' parameter with examples, and the tool description merely repeats 'Supports TikTok video url as input' without adding new constraints or formatting details. With 100% schema coverage, the description does not significantly enhance parameter understanding.
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's function: 'Get the details of a TikTok post.' It specifies the input (TikTok video URL) and lists the specific return fields (description, creator username, hashtags, counts, dates, duration). This differentiates it from sibling tools like tiktok_available_subtitles, which deal with subtitles.
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 only says 'Supports TikTok video url as input' but does not explicitly compare with sibling tools or state when to use this tool versus alternatives. While the sibling tools have different purposes (subtitles), the lack of explicit guidance reduces the score.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
tiktok_get_subtitleB
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 as input and optionally language code from tool 'AVAILABLE_SUBTITLES'Returns 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 | |
| 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 provided, the description carries the full burden. It discloses the default behavior (returns automatic speech recognition subtitle when no language code is provided) but does not mention error handling, response format details, or performance characteristics.
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 somewhat repetitive ('Get the subtitle ... This is used for getting the subtitle, content or context') and contains a typo ('AVAILABLE_SUBTITLES'). It could be more concise and better formatted with proper spacing.
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?
For a simple tool with 2 parameters and no output schema or annotations, the description covers basic behavior and default. However, it omits details about the output format and any limitations, leaving some uncertainty about the return structure.
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 baseline is 3. The description adds value by specifying that the language code should come from the 'AVAILABLE_SUBTITLES' tool and explains the default when omitted. This gives meaningful context beyond 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 that the tool gets the subtitle for a TikTok video URL, mentioning input and optional language code. It references the sibling tool 'AVAILABLE_SUBTITLES' (likely tiktok_available_subtitles) for obtaining language codes, which helps differentiate from siblings like tiktok_get_post_details. However, it could be more explicit about the exact output format.
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 implies a workflow by mentioning the language code from 'AVAILABLE_SUBTITLES', but does not explicitly state when to use this tool vs alternatives. It lacks clear guidance on prerequisites or exclusion conditions.
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. Dates show when Glama detected each change.
3 tool updates
v1.0.0- First observed
tiktok_available_subtitles - First observed
tiktok_get_post_details - First observed
tiktok_get_subtitle
TDQS
Each tool has a clearly distinct purpose: one checks for available subtitles, one retrieves post details, and one fetches a specific subtitle. There is no overlap in functionality, making it easy for an agent to select the correct tool based on the need.
All tools follow a consistent 'tiktok_verb_noun' pattern (tiktok_available_subtitles, tiktok_get_post_details, tiktok_get_subtitle). This predictability enhances usability and reduces confusion.
With only 3 tools, the server feels thin for a TikTok integration, as it lacks common operations like searching for videos, uploading content, or managing user interactions. However, the tools cover specific use cases adequately.
The toolset is severely incomplete for a TikTok server, missing essential CRUD operations such as creating posts, liking videos, or searching content. It only handles retrieval of subtitles and post details, leaving significant gaps in functionality.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
AI YouTube analyst in Claude for creators: audit, fix, decide what to make next, grow subs.
AI speech-to-text for public TikTok videos: SRT, VTT, word timings, speaker labels, 90+ languages.
Ask Claude about your ads: Meta, Google, TikTok, LinkedIn, GA4 & Shopify. No AI credits.
Connect Claude to Fathom meeting recordings, transcripts, and summaries
Related MCP Servers
- AlicenseBqualityCmaintenanceAnalyze YouTube, TikTok, and Instagram videos from URL. Extracts transcripts, generates AI insights, and pulls tutorial steps from any video link.183MIT
- FlicenseBqualityDmaintenanceExtracts YouTube transcripts and performs AI-powered video analysis for Claude Desktop, enabling transcript retrieval, quality analysis, and smart resource management.8-
- AlicenseNot gradedqualityCmaintenanceEnables Claude AI to extract transcripts from YouTube videos with zero local setup, supporting multi-language and all URL formats.MIT
- AlicenseNot gradedqualityCmaintenanceEnables Claude to read and watch online videos (YouTube, TikTok, Douyin, Facebook, Instagram) by pasting a link, providing summaries, transcripts, frame analysis, and metadata.MIT
Appeared in Searches
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/davibauer/tiktok-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server