How to Use the Bilibili Live MCP in Claude Code

Q: How do I pipe Bilibili Live chat data into other CLI tools using Claude Code?

You can ask Claude Code to execute getdanmuconfig and format the output as JSON. From there, you can pipe it into grep or jq to extract the host and token details for your custom terminal scripts.

Q: How do I send chat messages to Bilibili Live using Claude Code?

Use the command-line interface to tell Claude Code to call senddanmu with your message text. The agent will execute the tool through the server and post the chat message instantly.

Q: What command adds this MCP Server to my Claude Code configuration?

Run claude mcp add --transport http bilibili-live-mcp -- in your terminal. You can check that the connection is active by running claude mcp list.

Pipe real-time Bilibili Live chat streams and room metadata straight into your terminal tools using Claude Code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Bilibili Live MCP to Claude Code

Create your Vinkius account to connect Bilibili Live to Claude Code and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Bilibili Live with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pipe Bilibili Live chat into terminal utilities with this MCP Server

The `get_danmu_config` tool provides the WebSocket configurations you need to stream live chat directly to your terminal. From there, you can use `send_danmu` to broadcast system alerts or commit logs straight to your stream chat using simple shell commands. This lets you build lightweight shell scripts that listen to the live chat without opening a heavy browser tab. You can pipe the terminal output directly into other command-line tools to grep for specific keywords.

Run automated cron jobs for your Bilibili Live broadcast

Using `get_room_play_info`, Claude Code checks your live stream status and playback URLs directly from a cron job. If the stream goes down, the agent can run `update_room_title` to change your room status and alert your audience. This headless execution works perfectly in remote server environments where you don't have a GUI. You get absolute control over your broadcast status with simple terminal scripts.

Extract stream financial logs from the CLI

The `get_super_chats` tool extracts paid messages, and `get_gift_history` retrieves recent virtual item logs directly to stdout. This lets you pipe financial data into local spreadsheets or text ledgers without opening a browser. You can run this query on demand or schedule it to archive your stream earnings at the end of every broadcast. The raw JSON output makes it easy to append data to your existing ledger files.

Setup guide

Set up Bilibili Live MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see bilibili-live-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Bilibili Live transactions." It will automatically discover and invoke the available Bilibili Live tools.

Terminal

claude mcp add --transport http bilibili-live-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Bilibili Live MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "bilibili-live-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Bilibili Live. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Bilibili Live now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Bilibili Live MCP in Claude Code

You can ask Claude Code to execute `get_danmu_config` and format the output as JSON. From there, you can pipe it into `grep` or `jq` to extract the host and token details for your custom terminal scripts.

Yes. You can run Claude Code in a screen session or a Docker container to repeatedly query `get_room_play_info` and log stream health metrics to a local file.

Use the command-line interface to tell Claude Code to call `send_danmu` with your message text. The agent will execute the tool through the server and post the chat message instantly.

Run `claude mcp add --transport http bilibili-live-mcp -- ` in your terminal. You can check that the connection is active by running `claude mcp list`.

The server uses an isolated V8 sandbox hosted by Vinkius, which secures your developer tokens. This MCP Server processes your stream credentials and viewer transaction logs through an ephemeral tunnel, leaving zero footprint on the host machine.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript