Skip to main content
Glama

SocialDataX 小红书 Xiaohongshu XHS RedNote MCP

xhs_search_notes

Read-only

搜索小红书 / Xiaohongshu / XHS / RedNote 相关笔记。用户需要按搜索词查找笔记时使用;已有笔记链接或 note_id 且需要单篇笔记详情时使用对应的详情工具;需要评论、回复或口播转文字时使用相应的 URL/ID 工具;支持 page_token 翻页。继续翻页时必须将返回的完整 next_page_token 原样作为 page_token 传回,不得截断、缩写、掩码或用省略号替换中间内容。 返回的 note_url 在任何使用场景都必须原样保留完整 URL,包括 xsec_token 等 query 参数;例如最终回答、展示、引用、存储、输出或传递;不得用 note_id 重新拼接链接。

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
keywordYes搜索词,可传关键词或短语,例如品牌名、话题、人物名、产品名或内容需求;不要传笔记链接、主页链接、note_id、user_id 或 page_token。
note_typeNo笔记类型筛选,可选:all(不限,默认)、image(图文)、video(视频)all
sort_typeNo笔记搜索结果排序方式,可选:general(综合,默认)、time_descending(最新发布优先)、like_count_descending(最多点赞优先)、comment_count_descending(最多评论优先)、collect_count_descending(最多收藏优先)general
page_tokenNo笔记搜索分页令牌。首次请求留空;继续翻页时传入上一页返回的完整 next_page_token 原样作为 page_token 传回。page_token 只能用于同一关键词、排序、笔记类型、发布时间范围和调用方的笔记搜索链路;不得修改、截断、缩写、脱敏、掩码、省略、规范化、重组或自行生成。
publish_time_rangeNo发布时间范围筛选,可选:all(不限,默认)、day(一天内)、week(一周内)、half_year(半年内)all

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
itemsYes笔记搜索结果中的笔记列表,已过滤非笔记卡片与不可公开笔记;当前页过滤后可能为空数组
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或无法继续 token 翻页。继续笔记搜索时必须将完整 next_page_token 原样作为 page_token 传回。next_page_token 只能用于同一关键词、排序、笔记类型、发布时间范围和调用方的笔记搜索链路。items 为空时不要单独据此判断结束。

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the readOnlyHint and openWorldHint annotations, the description discloses critical behavioral constraints: the full next_page_token must be passed back unmodified, and returned note_url values must be preserved completely including xsec_token. It also warns against reconstructing URLs from note_id, which is valuable behavioral context an agent would not otherwise know.

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?

The description is efficient and front-loaded with the core purpose, followed by routing and critical pagination/URL constraints. It is slightly repetitive around the paging and URL-preservation warnings, but every sentence contributes operational value.

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

Completeness5/5

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

For a search tool with a full input schema, an output schema, and annotations already covering read-only/open-world behavior, the description covers the main usage scenario, alternative-tool routing, pagination behavior, and URL integrity requirements. No critical operational gap is visible.

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

Parameters4/5

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

Schema description coverage is 100%, so the baseline is 3. The description adds meaningful extra guidance for keyword, such as not passing note links, user IDs, or page_token, and reinforces the page_token chaining rule. This goes beyond the schema without needing to repeat enum documentation.

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?

The description starts with a specific verb and resource: “搜索小红书 / Xiaohongshu / XHS / RedNote 相关笔记”, which states exactly what the tool does. It also distinguishes this tool from detail, comment, and transcription tools by explicitly saying that those cases should use corresponding URL/ID tools.

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

Usage Guidelines4/5

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

The description clearly says to use this tool when the user needs to search by keyword, and explicitly redirects note-detail and comment/transcription needs to sibling tools. It does not explicitly contrast with xhs_search_products or xhs_search_suggestions, but the overall wording makes the note-search scope clear enough.

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

A3.9/5.0
Disambiguation3/5

Most tools are clearly separated by resource and action, but there are many near-duplicate pairs that differ only by ID vs URL input, such as xhs_get_note_detail_by_note_id and xhs_get_note_detail_by_note_url. The pgy note detail tools and standard note detail tools also overlap in purpose, though descriptions note the commercial-data distinction. Overall, an agent can disambiguate with care, but misselection risk is non-trivial.

Naming Consistency4/5

The dominant pattern is xhs_<verb>_<resource>_by_<identifier>, which is predictable and readable. Minor deviations exist: socialdatax_get_points_balance uses a different prefix, xhs_get_note_sub_comments_by_comment_id omits the required note_id from the name, and xhs_get_video_speech_text_job lacks a by_ parameter suffix. These are small inconsistencies rather than chaotic naming.

Tool Count3/5

24 tools is on the heavy side and within the borderline range of 16-25. The count is inflated by ID/URL duplication and separate pgy variants, though the underlying domain (notes, comments, users, products, search, hot lists, video speech, points) is broad. Each tool has a plausible use, but the surface feels larger than necessary.

Completeness4/5

The toolset covers the main read-only Xiaohongshu workflows: note details, comments and sub-comments, user profiles and posted notes, topic notes, product details/reviews, search, hot list, video speech text submission/query, and points balance. Minor gaps exist, such as no direct sub-comments-by-URL tool and product reviews only supported via sku_id, but these are workable through existing flows. No obvious dead ends for typical retrieval use cases.

Resources