222wcnm-bilistalkermcp
Track Bilibili creators and get the latest updates on videos, dynamics, and articles. Fetch user p鈥�
可用工具 （5 个）
该服务在 MCP 协议中暴露的工具，AI 可按需调用
tavily_search 14 个参数 需填 1 项
Search the web for current information on any topic. Use for news, facts, or data beyond your knowledge cutoff. Returns snippets and source URLs.
必填参数：query
tavily_extract 6 个参数 需填 1 项
Extract content from URLs. Returns raw page content in markdown or text format.
必填参数：urls
tavily_crawl 11 个参数 需填 1 项
Crawl a website starting from a URL. Extracts content from pages with configurable depth and breadth.
必填参数：url
tavily_map 8 个参数 需填 1 项
Map a website's structure. Returns a list of URLs found starting from the base URL.
必填参数：url
tavily_research 2 个参数 需填 1 项
Perform comprehensive research on a given topic or question. Use this tool when you need to gather information from multiple sources to answer a question or complete a task. Returns a detailed response based on the research findings.
必填参数：input
服务介绍
BiliStalkerMCP
BiliStalkerMCP is an MCP server providing high-fidelity Bilibili data access for AI agents (Claude, ChatGPT).
English | 中文说明
# # Installation
uvx bili-stalker-mcp
# or
pip install bili-stalker-mcp
# # Configuration (Claude Desktop)
{
"mcpServers": {
"bilistalker": {
"command": "uvx",
"args": ["bili-stalker-mcp"],
"env": {
"SESSDATA": "required_sessdata",
"BILI_JCT": "optional_jct",
"BUVID3": "optional_buvid3"
}
}
}
}
Auth: Obtain
SESSDATAfrom Browser DevTools (F12) > Application > Cookies >.bilibili.com.
# # Environment Variables
| Key | Req | Description |
|- -- --|:- --:|- -- -- -- -- -- --|
| SESSDATA | Yes | Bilibili session token. |
| BILI_JCT | No | CSRF protection token. |
| BUVID3 | No | Hardware fingerprint (reduces rate-limiting risk). |
| BILI_LOG_LEVEL | No | DEBUG, INFO (Default), WARNING. |
# Available Tools
| Tool | Capability | Parameters |
|- -- -- -|- -- -- -- -- -- -|- -- -- -- -- -- -|
| get_user_info | Profile & core statistics | user_id_or_username |
| get_user_video_updates | Video uploads with subtitle analysis | user_id_or_username, page, limit |
| get_user_dynamic_updates | Dynamics with cursor pagination & filtering | user_id_or_username, cursor, limit, dynamic_type |
| get_user_articles | Long-form article retrieval | user_id_or_username, page, limit |
| get_user_followings | Subscription list analysis | user_id_or_username, page, limit |
# # Dynamic Filtering (dynamic_type)
ALL(default): Text, Image-Text, and Reposts.ALL_RAW: Unfiltered (includes Videos & Articles).VIDEO,ARTICLE,DRAW,TEXT: Specific category filtering.
Pagination: Responses include next_cursor. Pass this to subsequent requests for seamless scrolling.
# Development
# Setup
git clone https://github.com/222wcnm/BiliStalkerMCP.git
cd BiliStalkerMCP
uv pip install -e .[dev]
# Test
uv run pytest -q
# Integration & Performance (Requires Auth)
uv run python scripts/integration_suite.py -u <UID>
uv run python scripts/perf_baseline.py -u <UID> - -tools dynamics -n 3
# Release (Maintainers)
Prerequisite: Ensure that a
.pypircfile is configured in your user home directory to provide PyPI credentials.
# Build + test + twine check (no upload)
.\scripts\pypi_release.ps1
# Upload to TestPyPI
.\scripts\pypi_release.ps1 -TestPyPI -Upload
# Upload to PyPI
.\scripts\pypi_release.ps1 -Upload
# Docker
Runs via stdio transport. No ports exposed.
docker build -t bilistalker-mcp .
docker run -e SESSDATA=... bilistalker-mcp
# Troubleshooting
- 412 Precondition Failed: Bilibili anti-crawling system triggered. Refresh
SESSDATAor provideBUVID3. - Cloud IPs: Highly susceptible to blocking; local execution is recommended.
# License
MIT
This project is built and maintained with the help of AI.
