Local stdio bridge for the hosted SocialDataX Douyin MCP service. Provides social media research support for Douyin/TikTok including hot search lists, work search, work details, comments, creator profiles, creator works, and short drama series.
13 tools with complete schemas and consistent naming (verb_noun pattern). Descriptions are present and adequate (avg ~100 chars), exceeding the 20-char minimum. All parameters are typed with descriptions. However, output schemas are not documented in the source code, LLMs cannot see what fields to expect from responses. Pagination is well-designed (opaque page_token with clear guidance). No error handling guidance visible. No tool annotations (readOnlyHint, destructiveHint, idempotentHint) despite all tools being READ_ONLY. Missing output documentation is a significant gap for agent composition.
Fetch the current Douyin main hot search list.
Resolve a Douyin profile link, short link, or share text into creator profile data.
Fetch creator profile data when the caller already has a sec_user_id.
Fetch a paginated list of works published by a creator from a profile link, short link, or share text.
Fetch a paginated list of works published by a creator when the caller already has a sec_user_id.
Fetch a paginated list of short-drama series published by a creator from a profile link, short link, or share text.
Output schemas not documented. LLMs cannot see what fields responses contain, breaking tool composition and forcing agents to guess field names for downstream calls.
No tool annotations despite all tools being READ_ONLY. Missing readOnlyHint prevents agents from understanding safety properties and optimizing retry logic.
No error handling guidance in tool descriptions. When API calls fail, LLMs receive raw errors with no recovery path (e.g., 'User not found. Try search_users() first.').
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | C | 61 | 2026-07-28+ | v2 |
Fetch a paginated list of short-drama series published by a creator when the caller already has a sec_user_id.
Fetch paginated replies under a first-level Douyin comment; pass both aweme ID and comment ID, and use page_token to continue pagination.
Fetch paginated first-level comments when the caller already has an aweme ID.
Fetch paginated first-level comments from a Douyin content page URL, short link, or share text.
Fetch structured work details when the caller already has an aweme ID.
Resolve a Douyin content page link, short link, or share text into structured work details.
Search Douyin works by keyword with optional sort, publish-time, duration, and content-type filters.
Pagination token description is verbose (200+ chars) and repetitive across 6 tools. Consider centralizing or shortening to reduce token waste.
Tool names use double underscore prefix (douyin-insights__) which is non-standard. Prefer simple verb_noun naming (e.g., get_hot_search_list) for clarity.