Skip to main content
Glama
Sign In

Crawlora MCP

by net.crawlora
OverviewDiscussionsAdmin

xiaohongshu_note

Read-only

Fetch one public Xiaohongshu note's normalized detail from the note_url returned by xiaohongshu_explore. Returns note_id, type, title, description text, topic tags, image URLs, an optional video URL with duration, publish time, a public author card, and like/collect/comment/share counters. Pass url with the explore-issued xsec_token, or pass note_id plus xsec_token from an explore card; a note id alone is not accessible anonymously, a stale token returns not-found, and comments are not included in the anonymous page state.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "URL": "<URL>",
      "NoteID": "<NoteID>",
      "XsecToken": "<XsecToken>"
    },
    "name": "xiaohongshu_note"
  }
}

Input Schema

NameRequiredDescriptionDefault
URLYesNote URL carrying xsec_token, normally the note_url returned by /xiaohongshu/explore. Pass url, or both note_id and xsec_token.
NoteIDYes24-character hex note id from an explore card (requires xsec_token)
XsecTokenYesShort-lived feed-issued token that accompanies note_id

Output Schema

NameRequiredDescriptionDefault
dataYesThe tool result payload (shape varies per tool; see each tool's docs resource).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only declare readOnlyHint and openWorldHint, so the description carries the real load and does: it discloses anonymous-access constraints, that stale tokens surface as not-found, and that comments are absent from the anonymous page state. These are genuine failure modes and data-coverage limits an agent cannot infer from the 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?

Three sentences, front-loaded with the action and provenance before the constraints. The middle sentence enumerating every returned field is the weakest part, since much of it duplicates the output schema.

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?

Covers input sourcing, token lifetime, failure behavior, and access limits, which is what an agent needs to invoke it successfully; an output schema exists, so the return-field enumeration is helpful rather than necessary. Slightly redundant against structured data but not incomplete.

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 100%, so the baseline is 3, but the description adds real semantics: URL and note_id+xsec_token are alternative input paths and the token is short-lived. It partially resolves the confusing required-array (which lists all three as required despite the stated either/or), so it compensates for a schema that would otherwise mislead.

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 ('Fetch one public Xiaohongshu note's normalized detail') and pins the source of the identifier to the sibling tool xiaohongshu_explore. An agent can tell immediately this is the single-note detail endpoint, not a feed, search, or comments call.

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?

Explicitly routes the agent through xiaohongshu_explore for the URL/token and rules out calling with a bare note id ('a note id alone is not accessible anonymously'). It also implies the boundary with xiaohongshu_note_comments via 'comments are not included', but stops short of naming that sibling as the alternative the way a 5 would.

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

All Crawlora MCP toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources