Log inSubmit server
Bilibili MCP Server logo

Bilibili MCP Server

Read Bilibili videos, creators, subtitles, comments, chapters, and favorites through a local MCP server.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Bilibili MCP Server

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "bilibili-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@xzxzzx/bilibili-mcp@latest"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Automated check passed— started and listed 12 tools correctly (Today).

Overview

Bilibili MCP Server is a local MCP server for searching Bilibili and reading video, creator, subtitle, comment, and favorites data. It exposes tools for finding videos and UP creators, retrieving video metadata and chapters, locating phrases in timestamped transcripts, and browsing the logged-in account’s favorites. Optional local faster-whisper transcription handles videos without usable subtitles when explicitly enabled. Reach for it when an agent needs structured Bilibili research rather than browser-only page access.

Use cases

  • Search Bilibili videos by research topic
  • Locate quoted phrases in timestamped transcripts
  • Review a creator’s videos, collections, series, and updates
  • Traverse visible favorite folders from a logged-in account
  • Transcribe a selected video part without usable subtitles

Key features

  • Topic-based video search with BVID results
  • Creator discovery and content browsing
  • Timestamped subtitle and transcript lookup
  • Video metadata, chapters, comments, and replies
  • Paginated favorite-folder traversal
  • Optional local faster-whisper transcription

Tools12

What Bilibili MCP Server lets your agent do. Expand a tool for its parameters.

Verified live~2.3k tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked Today

Recent health check succeeded.

19/20 checks healthy over the last 94d

What it can do

From the 12 tools this server returned when we ran it.

Runs commands · 9Handles credentials · 10Read-only tools · 3
Network at startup3 connections
Files written at startupNone
Install scriptsNone
npm provenanceSigned build
Package age282 days
Maintainers1

Observed 2026-11-12 in an isolated sandbox. A description of reach, not a security audit.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 5d ago via OSV.dev · @xzxzzx/bilibili-mcp@latest (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars51Stargazers on the source repository.
npm downloads4kPackage downloads in the last 30 days.
Last commit13d agoMost recent push to the default branch.
Availability100%Our rolling endpoint + install checks that succeeded.
Install checkPassedOur sandbox started it and listed its tools.
Tools exposed12Callable tools this server registers over MCP.
Directory activity8 viewsConfig copies, upvotes, and views on AllMCPs.

How Bilibili MCP Server works

What Bilibili MCP Server does

Bilibili MCP Server connects an MCP-compatible agent to Bilibili content through a local stdio process. It supports topic-based video search, creator discovery, creator profile and content inspection, video metadata, chapters, subtitles, comments and replies, and traversal of the authenticated account’s visible favorites.

Transcript results can include timestamps, matching context, and links that open the corresponding moment in the Bilibili video. The server can distinguish ordinary subtitles from Bilibili AI-generated subtitles and reports the selected data source. It can also search within a specific video part instead of requiring an agent to process the entire transcript.

How it works

Install the package through npx and register it as a local stdio server. The usual command is:

Terminal
npx -y @xzxzzx/bilibili-mcp@latest

After the client reconnects, credentials can be checked with check_bilibili_credentials. Video searches return candidates with fields such as title, creator, duration, and BVID; the selected BVID can then be passed to metadata, transcript, chapter, or comment operations.

Favorite traversal is paginated. Each request reads at most one upstream page of 20 items, and the agent follows the returned next_cursor until the collection ends. Creator exploration likewise separates candidate search from reading a confirmed creator’s profile, videos, collections, series, and updates.

Setup and configuration

Node.js 20 or newer is required. Run the package’s setup command locally to configure Bilibili credentials, then use check for local configuration status and doctor --json for a redacted diagnostic report. QR-code login through the Bilibili mobile app is the recommended path; manual Cookie entry is also available. Credentials are stored under ~/.bilibili-mcp/config.json, or under the equivalent user-profile directory on Windows.

The optional ASR setup requires Python 3.9 or newer. It can install a tiny, base, or small faster-whisper model under ~/.bilibili-mcp/asr/. Device preference can be set to automatic selection, CPU, or CUDA. The MCP call does not download or change models; model installation is performed by setup.

Tools and capabilities

  • search_bilibili_videos finds videos by topic and returns ranked candidates.
  • search_bilibili_creators finds UP creator candidates by name or keyword.
  • get_bilibili_creator_content reads a selected creator’s overview and content categories.
  • list_bilibili_favorite_videos walks the authenticated account’s visible favorite folders.
  • get_video_info retrieves video context with subtitle preference, metadata, and chapters.
  • get_video_transcript returns transcript text, timestamps, keyword matches, and optional local ASR output.
  • Credential checks confirm whether local configuration exists and whether the account is logged in.

Limitations and notes

Native subtitles take precedence. AI subtitles may be rejected after consistency and language checks; users can exclude them or explicitly request local ASR. ASR is opt-in, runs one task at a time, and is limited to a single video part up to two hours, with a 128 MiB audio limit and a 30-minute transcription timeout.

Local transcription requires a ready model and can return errors such as ASR_NOT_READY, ASR_BUSY, or ASR_TRANSCRIPTION_TIMEOUT. Temporary audio is cleaned up after success, failure, or timeout. Cookies are sent only to Bilibili’s official interfaces and are not passed to the local Python transcription process. The credential file is not guaranteed to receive operating-system-level encryption.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Bilibili MCP Server

Bilibili MCP Server is an MCP server that connects AI agents to Bilibili through a local stdio process. Its main tools search videos and creators, retrieve video metadata, chapters, subtitles, transcripts, comments, and browse the logged-in account’s favorites, with optional local faster-whisper transcription for videos without usable subtitles.

Install it by registering `npx -y @xzxzzx/bilibili-mcp@latest` as a local stdio server, then run its `setup` command in a terminal. Configure credentials locally, run `check`, reconnect the MCP client, and verify login with `check_bilibili_credentials`.

Yes, it can be added to an MCP client that supports local stdio servers, including Cursor. Configure the server with `npx` and the package’s `@latest` tag, then restart or reconnect Cursor after completing local credential setup.

Yes, if the optional local ASR model is installed and the transcript request explicitly enables ASR fallback. The server uses faster-whisper locally, preserves timestamped transcript behavior, and limits transcription to one selected video part at a time.

Related MCP servers

All in Social Media All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewBilibili MCP Server AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/bilibili-mcp-server?style=directory)](https://allmcps.com/mcp/bilibili-mcp-server)
HTML Embed
<a href="https://allmcps.com/mcp/bilibili-mcp-server"><img src="https://allmcps.com/api/badge/bilibili-mcp-server?style=directory" alt="Bilibili MCP Server on AllMCPs" /></a>