Skip to main content
Glama

SocialDataX 知乎 Zhihu MCP

zhihu_search_content

Read-only

按搜索词搜索知乎公开内容。用户需要按搜索词查找内容时使用;已有回答页、专栏文章页或独立视频页链接且需要详情或评论时使用对应 URL 工具;已有用户主页链接时使用用户资料或文章列表工具;支持类型、排序、发布时间筛选与 page_token 翻页。

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
keywordYes知乎内容搜索词,可传关键词或短语,例如问题、话题、人物、机构或内容需求;不要传问题链接、回答链接、专栏文章链接、视频链接、用户主页链接或 page_token。
sort_typeNo排序方式:general=综合排序,upvote_count_descending=最多赞同,time_descending=最新发布。如无明确排序需求,保持 general。general
page_tokenNo知乎搜索分页令牌。首次请求留空。继续翻页时必须将上一页返回的完整 next_page_token 原样作为 page_token 传回;page_token 是不透明分页令牌;不得修改、截断、缩写、脱敏、掩码、省略、规范化、重组或自行生成,不得用省略号替换中间内容。只能用于同一关键词、同一类型筛选、同一排序和同一发布时间筛选链路。更换关键词、类型、排序或发布时间筛选时,请清空 page_token 后从第一页重新搜索。
content_typeNo内容类型筛选:all=不限类型,answer=只看回答,article=只看文章,video=只看视频内容(可能返回独立视频 video 或带视频的回答 videoanswer;videoanswer 不是独立视频,也不是筛选取值)。all
publish_time_rangeNo发布时间筛选:all=不限时间,day=一天内,week=一周内,month=一月内,three_months=三月内,half_year=半年内,year=一年内。如无明确筛选需求,保持 all。all

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
itemsYes当前页知乎内容列表;当前页可能为空,是否可继续翻页以 next_page_token 是否为空为准。
pointsYes本次成功调用的积分消耗与调用完成时的账户积分余额。
next_page_tokenYes下一页不透明分页令牌;为空表示没有更多结果。继续翻页时必须将返回的完整 next_page_token 原样作为 page_token 传回;只用于当前搜索续页;不得修改、截断、缩写、脱敏、掩码、省略、规范化、重组或自行生成。

TDQS

A4.1/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered. The description adds scoping context (公开内容/public content only) and notes page_token pagination support, which are useful behavioral traits. However, it does not go deeper (e.g., token expiry, rate limits, or that a videoanswer result is returned under video filter — though that detail is in the schema). Modest value beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core purpose, then usage routing, then capability summary; every clause earns its place and there is zero filler. Slightly dense as one continuous sentence block, but efficient overall.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 5-parameter tool with 3 enums, an output schema, and 11 siblings, the description covers purpose, when to use, when-not-to-use with named alternatives, and available filters/pagination. The output schema covers return values, so no need to restate them. Complete enough for selection and correct invocation, though the dense single-sentence structure is the only minor weakness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% with detailed descriptions for all 5 parameters, including the opaque-token contract for page_token and enum meanings for sort_type/content_type/publish_time_range. The description only summarizes these at a high level, so baseline 3 applies; it adds no semantics beyond the schemas

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('按搜索词搜索知乎公开内容') and names the alternatives it is not: URL-based detail/comment tools for existing page links, and user profile/article-list tools for profile links. An agent can clearly distinguish it from the 10+ sibling tools without opening schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use ('用户需要按搜索词查找内容时') and when-not: when the user already has answer/article/video page links, or a profile link, it routes to the corresponding sibling tools. This is explicit when/when-not with alternatives named.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.1/5.0
Disambiguation4/5

Each tool maps to a distinct resource and action: search, hot list, content detail, comments, comment replies, user info, user articles, video speech submission/status, and points balance. The only close pair is the two video-submission tools, but their input difference (video URL vs zvideo ID) is clearly stated. Descriptions actively route agents to the right tool based on available identifiers, which reduces ambiguity.

Naming Consistency4/5

Most tools follow the consistent zhihu_<verb>_<object>_by_<identifier> pattern, making the set predictable and readable. The points-balance tool breaks the pattern with the socialdatax_ prefix, and the video speech tools have a longer nested object name but still fit the overall convention. This is a minor deviation rather than a systematic inconsistency.

Tool Count5/5

11 tools is a well-scoped count for a Zhihu content-access MCP, covering search, hot list, content details, comments, user profiles, user articles, video transcription, and account points. Each tool has a concrete purpose, and the set does not feel bloated or overly thin. The dual video-submit tools are mildly redundant but justified by different input identifier types.

Completeness4/5

The core read surface is well covered: hot list, search, content details, comments and replies, user info, user articles, and video speech transcription. One notable gap is that user-posted answers and videos are explicitly excluded from the user articles tool, so that part of a user's Zhihu activity is not accessible. Overall the surface is solid with only minor missing operations.

Resources