Extracts and formats Bilibili video content into structured text for LLM processing.
Uses Cloudflare R2 for storing audio data extracted from videos.
Uses Replicate API for speech-to-text transcription via WhisperX.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@biliscribe Extract text from this Bilibili video: https://b23.tv/abc123"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A MCP Server that extracts and formats Bilibili video content into structured text, optimized for LLM processing and analysis.
一个 MCP Server，将 B站视频转成文字，给大模型总结。
I have only completed testing on macOS. Before running this MCP Server, you need to ensure that ffmpeg can be called from your shell environment.
我只在 macOS 上完成了测试。在运行此 MCP 服务器之前，您需要确保可以从命令行环境调用 ffmpeg。
You can install the mcp-server-biliscribe package using uvx:
您可以使用 uvx 安装 mcp-server-biliscribe 包：
uvx mcp-server-biliscribeRelated MCP server: Bilibili Mcp
Before using this service, you need to prepare: 在使用此服务之前，您需要准备：
Cloudflare R2 access credentials - for storing audio data Cloudflare R2 访问凭据 - 用于存储音频数据
Replicate API Key - for whisperx calling Replicate API Key - 用于 whisperx 调用
You need to set the following environment variables: 您需要设置以下环境变量：
REPLICATE_API_TOKEN=r8_THIS_IS_REPLICATE_API_KEY
S3_API_ENDPOINT=https://this_is_s3_api_endpoint.r2.cloudflarestorage.com
BUCKET_NAME=this_is_your_bucket_name
ACCESS_KEY=THIS_IS_YOUR_S3_AK
SECRET_KEY=THIS_IS_YOUR_S3_SKThis server supports two communication protocols: 该服务器支持两种通信协议：
Standard I/O (stdio) - default 标准输入/输出 (stdio) - 默认
Server-Sent Events (SSE) 服务器发送事件 (SSE)
You can control the protocol using the environment variable BILISCRIBE_SERVER_SSE. Set it to true to enable SSE mode.
您可以使用环境变量 BILISCRIBE_SERVER_SSE 控制协议。将其设置为 true 以启用 SSE 模式。
Extracts and formats video content into structured text, optimized for LLM processing and analysis.
Args:
video_url (str): The URL of video to process.
use_audio (bool): Whether to use audio for transcription. Should always be True.
Returns:
str: The formatted text content of the video.
| Name | Required | Description | Default |
|---|---|---|---|
| video_url | Yes | ||
| use_audio | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description must disclose all behavioral traits. It says 'extracts and formats' but does not mention limitations like supported video formats, size limits, or whether it works without audio. The reliance on audio is implied but not fully stated.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with a clear first sentence and structured Args/Returns sections. No redundant information, but could be more compact without losing clarity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 2 parameters and no output schema, the description provides essential usage info but lacks details on domain (e.g., Bilibili-specific), error handling, or output structure. It is minimally complete for a simple tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description compensates with brief arg explanations (URL and boolean usage). The note 'Should always be True' adds practical guidance. However, the explanations are minimal and do not specify expected input formats or edge cases.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it extracts and formats video content into structured text for LLM processing, with a specific verb ('extracts and formats') and resource ('video content'). No siblings exist, so differentiation is not required.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No sibling tools to compare, but the description gives parameter-level guidance ('use_audio should always be True'). However, it does not specify when to use this tool vs alternatives or conditions under which it might fail.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.8.7bili_scribeOnly one tool exists, so there is no risk of confusion between tools. The single tool has a clear and distinct purpose.
With only one tool, naming is trivially consistent. The name 'bili_scribe' follows a reasonable pattern for the domain.
A single tool for video transcription feels thin, as it lacks supporting tools for video lookup, list management, or format options. The scope is narrow but tolerable for a minimal server.
The tool covers the core transcription operation, but there are obvious gaps like no ability to list available videos, configure audio settings beyond boolean, or handle batch processing. The surface is incomplete for a general video content server.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Any video URL to LLM-ready transcript. ASR built in, no captions needed. TikTok, X, TED and more.
Bilibili public video, article, dynamic, creator, comments, reactions, and transcript tools.
Turn a TikTok/Instagram/YouTube link into text for your AI: metadata, transcript and image OCR.
Provide token-optimized, structured YouTube data to enhance your LLM applications. Access efficien…
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/mcp-server-summary/biliscribe'
If you have feedback or need assistance with the MCP directory API, please join our Discord server