TikTok Intelligence MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| APIFY_API_TOKEN | Yes | Your Apify Personal API Token, passed as the Bearer token in the Authorization header when connecting to the hosted Streamable-HTTP MCP endpoint. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Streamable-HTTP & stdio MCP server for TikTok video search, spoken viral hook & transcript extraction, creator email discovery, buyer-intent comment mining, and sponsor spying. Remote Streamable-HTTP endpoint: https://church-of-loujess--tiktok-intelligence-mcp.apify.actor/mcp | Store: https://apify.com/church_of_loujess/tiktok-intelligence-mcp
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_tiktok_videosB | Search TikTok videos by keyword or hashtag ( |
| extract_viral_hooks_and_scriptsA | Extract timestamped first-3-second spoken hooks, body scripts, closing CTAs, speaking pace (WPM), hook archetype, and outlier virality multiplier from TikTok videos matching |
| find_tiktok_creator_emailsA | Discover TikTok micro-influencers, UGC creators, and Shop affiliates in any niche ( |
| mine_buyer_intent_commentsA | Scan TikTok video comments ( |
| spy_tiktok_brand_sponsorsA | Detect active DTC & SaaS brands sponsoring TikTok creators in any niche ( |
| scan_breakout_tiktok_soundsA | Discover trending and breakout TikTok audio/music tracks in any niche ( |
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
Each tool targets a distinct intelligence action: video search, hook extraction, creator email discovery, comment intent mining, sponsor detection, and sound trend scanning. Boundaries are clear even though search, hook extraction, and comment mining all accept keyword/videoUrl inputs, since their outputs and purposes differ sharply.
All six names use snake_case and follow a verb_object pattern (search_, extract_, find_, mine_, spy_, scan_). Minor inconsistency: some names embed 'tiktok' (search_tiktok_videos, find_tiktok_creator_emails, spy_tiktok_brand_sponsors) while others omit it (extract_viral_hooks_and_scripts, mine_buyer_intent_comments), which slightly weakens predictability.
Six tools is well-scoped for a focused TikTok intelligence server. Each tool corresponds to a distinct marketing research workflow, and none feels redundant or like padding.
The surface covers core TikTok intelligence workflows: discovery, content analysis, creator contact discovery, buyer intent, sponsorship spying, and sound trends. Minor gaps exist around tracking individual creators over time or aggregating multi-tool reports, but agents can compose existing tools to work around these.