Skip to main content
Glama
Sign In
Crawlora-org

Crawlora MCP

Official
by Crawlora-org
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

rednote_explore

Fetch one page of the anonymous Rednote explore feed as normalized note cards, with an optional channel ID for category feeds. Use it to inspect public recommendations without login.

Instructions

Anonymous Rednote explore/channel feed. Returns one page of the anonymous Rednote (international Xiaohongshu) explore feed as normalized note cards: note id, a public note_url of the form https://www.rednote.com/discovery/item/, the card's short-lived xsec_token, media type, title, cover image, like count, and a public author card. Omit channel_id for the default recommendation feed; use channel_id with an id from the channels list returned by this endpoint for a category feed. The upstream serves one server-rendered page per channel (typically 20-35 cards) and has no credential-free cursor, so there is no pagination. Note detail, user profiles, comments, and search are not available on this anonymous surface: note detail and profiles require the page's guest session, and search requires login, so note_url is a link for a human browser rather than a follow-up API call.

Input Schema

NameRequiredDescriptionDefault
channel_idNoOptional explore channel id from the channels list in a previous response. Unknown values are rejected; omit for the default feed.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.17.18

TDQS

A4.6/5.0
Behavior4/5

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

No annotations are provided, so the description carries the full burden, and it mostly does: it discloses the anonymous/no-credential surface, that the upstream serves one server-rendered page of 20-35 cards, that there is no credential-free cursor hence no pagination, and that xsec_token is short-lived. What it does not cover is failure behavior (what an unknown or expired channel_id returns) and rate/retry expectations, which keeps it off a 5.

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 what the tool returns before the channel_id rule, and every clause is informational rather than filler. It is dense but long — the field enumeration and the limitation paragraph could be tightened slightly without losing meaning.

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?

With no output schema, the description compensates by enumerating the normalized card fields (id, note_url shape, xsec_token, media type, title, cover, like count, author card). Pagination limits, the anonymous constraint, and the human-browser caveat for note_url are all present, so an agent can call this correctly with no follow-up guesses.

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 coverage is already 100%, so the baseline is 3; the description goes beyond it by explaining the parameter's provenance (an id from the channels list in a prior response) and the default-feed behavior when omitted. The one gap is that it never says where that channels list appears in the response, given there is no output schema to point to.

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 ('Returns one page of the anonymous Rednote explore feed as normalized note cards') and enumerates the returned fields. It also distinguishes itself from sibling surfaces by declaring that note detail, profiles, comments, and search are unavailable here, so an agent can rule out rednote_note and the xiaohongshu_* siblings without opening them.

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?

Gives explicit branching: 'Omit channel_id for the default recommendation feed; use channel_id with an id from the channels list returned by this endpoint for a category feed.' It also names the excluded use cases and why (note detail/profiles need the guest session, search needs login), which is exactly the when-not guidance an agent needs.

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

Deploy Server

Other Tools