Skip to main content
Glama
Sign In
bilibili-learning-mcp

bilibili-learning-mcp

by Unc1e-2ack
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Get Bilibili video info

get_video_info

Retrieve detailed metadata for a single Bilibili video—title, description, uploader, duration, stats, and part list with cid—to inspect content or confirm parts before fetching subtitles or comments.

Instructions

读取单个 B 站视频的详细信息：标题、简介、UP主、分P列表（含 cid）、互动数据、时长。

何时调用：
    - 用户给了 BV 号或视频链接，想了解这个视频讲了什么时。
    - 调用 get_subtitles 或 get_hot_comments 之前，先确认分P数量和 cid。
    - 视频没有字幕时，用简介判断内容是否值得看。

参数：
    bv_id: BV 号或完整链接。支持 "BV1GJ411x7h7"、
        "https://www.bilibili.com/video/BV1GJ411x7h7"、
        "https://www.bilibili.com/video/BV1GJ411x7h7?p=2" 等写法。
        注意 BV 号主体区分大小写，请原样复制，不要手打。

返回示例：
    标题：线性代数的本质
    BV号：BV1GJ411x7h7 | AV号：8047632
    UP主：3Blue1Brown
    时长：1:02:03（3723 秒）
    播放：1234.5万 | 点赞：8.9万 | 收藏：3.2万 | 投币：1.1万 | 评论：4321
    发布时间：2020-05-01
    链接：https://www.bilibili.com/video/BV1GJ411x7h7

    简介：
    （最多 800 字，超出会标注「已截断」）

    分P列表（共 2 P）：
    P1 | cid=12345678 | 00:12:34 | 向量是什么
    P2 | cid=12345679 | 00:15:01 | 线性组合

失败时：
    返回以「获取视频信息失败：」开头的说明。BV 号格式错误时会提示正确写法，
    视频不存在或被删除时会说明原因，不要用同样的参数重试。

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": {
      "bv_id": "<bv_id>"
    },
    "name": "get_video_info"
  }
}

Input Schema

NameRequiredDescriptionDefault
bv_idYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior4/5

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

No annotations are supplied, so the description carries the full burden, and it does most of it: it discloses the 800-character description truncation marker, named failure prefixes, and the crucial instruction not to retry with the same parameters after a format or not-found error. It omits auth requirements, rate limits, and pagination behavior for the part list, which keeps it below 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?

The layout is strongly front-loaded with labeled sections (何时调用 / 参数 / 返回示例 / 失败时) so an agent can extract what it needs fast. The multi-line return example is longer than necessary given an output schema exists, which is the main cost, but the failure section earns its space.

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 single-parameter read tool this is close to complete: input format, return shape, truncation behavior, and error semantics are all covered. Because an output schema already exists, the verbose 返回示例 partially duplicates structured data, leaving only the truncation and error guidance as unique value.

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

Parameters5/5

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

Schema description coverage is 0%, so the description must compensate entirely, and it does: bv_id is defined as either a bare BV number or a full URL, with three concrete accepted formats including one with a ?p=2 query, plus an explicit case-sensitivity warning to copy rather than retype the number.

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 opens with a specific verb+resource (读取单个 B 站视频的详细信息) and enumerates exactly what is returned: title, description, uploader, multi-part list with cid, interaction stats, duration. It is clearly distinguishable from siblings because it explicitly positions itself as the prerequisite for get_subtitles and get_hot_comments.

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?

A dedicated 何时调用 section gives three concrete triggers, including a sequencing rule (call this before get_subtitles/get_hot_comments to confirm part count and cid) and a fallback when no subtitles exist. This is explicit when-to-use plus alternatives, not implied.

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