Atlas / MCP servers / huccihuang / Bilibili

BilibiliSAFE

mcp/huccihuang/bilibili

MCP Server for the Bilibili API, supporting various operations.

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
4 4r · 0w · 0d
Transport
stdio
License
MIT
Stars
190
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

用于哔哩哔哩 API 的 MCP(模型上下文协议)服务器,支持多种操作。

环境要求

  • uv - 一个项目管理工具,可以很方便管理依赖。

使用方法

  1. clone 本项目
  1. 使用 uv 安装依赖
uv sync
  1. 在任意 mcp client 中配置本 Server
{
"mcpServers": {
"bilibili": {
"command": "uv",
"args": [
"--directory",
"/your-project-path/bilibili-mcp-server",
"run",
"bilibili.py"
]
}
}
}
  1. 在 client 中使用

支持的操作

支持以下操作:

  1. general_search: 基础搜索功能,使用关键词在哔哩哔哩进行搜索。
  2. search_user: 专门用于搜索哔哩哔哩用户的功能,可以按照粉丝数排序。
  3. get_precise_results: 精确搜索功能,可以过滤掉不必要的信息,支持多种搜索类型:
  4. 用户搜索 (user):精确匹配用户名,只返回完全匹配的结果。例如搜索"双雷"只会返回用户名为"双雷"的账号信息,不会返回其他相关用户
  5. 视频搜索 (video)
  6. 直播搜索 (live)
  7. 专栏搜索 (article)

返回结果包含 exact_match 字段,标识是否找到精确匹配的结果。

  1. get_video_danmaku·: 获取视频弹幕信息。

如何为本项目做贡献

  1. Fork 本项目
  2. 新建分支,并在新的分支上做改动
  3. 提交 PR

License

MIT

Read from source at commit 9e2b4e1e2983OBSERVED · 2026-10-06
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.

claude-code
claude mcp add bilibili-mcp-server -- uvx bilibili-mcp-server
claude-desktop
{
  "mcpServers": {
    "bilibili-mcp-server": {
      "command": "uvx",
      "args": [
        "bilibili-mcp-server"
      ]
    }
  }
}
03

Exposed tools (4)

4 read · 0 write · 0 destructive.

ToolRiskDescription
general_searchread
get_precise_resultsread
get_video_danmakuread
search_userread
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
declared (1 observation(s))
Network
none-observed
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.

Audited 2026-10-06 · audit v0.4.1 · source sha 9e2b4e1e2983full audit observations/trust-audit/mcp-server/huccihuang__bilibili.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-069e2b4e1e2983SAFEB89first audit
06

Questions

What is the Bilibili MCP server?

MCP Server for the Bilibili API, supporting various operations.

What tools does Bilibili expose?

4 in total: 4 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is Bilibili safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does Bilibili need?

No credential environment variables were found in its source, so it appears to need none.

How does Bilibili run?

It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as bilibili-mcp-server.

How current is this page?

The grade is for one exact copy of the source (9e2b4e1e2983), read on 2026-10-06. The repository is watched and re-audited when it changes.

Advertisement