WoT Blitz MCP Server
Provides AI assistants with access to authentic World of Tanks Blitz game data including tank statistics, armor values, map terrain features, equipment, crew skills, and camouflages parsed directly from local game files.
README
WoT Blitz MCP Server
An MCP server that gives AI access to authentic World of Tanks Blitz game data. Ask your AI anything about tanks, maps, equipment - it gets real data straight from the game files.
What's this for?
MCP (Model Context Protocol) lets AI assistants connect to external data sources. This server reads WoT Blitz game files and exposes all that data to AI, so you can ask things like:
- "What's the best tier 8 medium for sniping?"
- "Compare the IS-7 and E 100"
- "Where are the bushes on Mines?"
- "What crew skills should I use on my light tank?"
The AI gets actual game data to answer, not guesses.
Data available
- 800+ tanks - stats, modules, shells, armor, camo values
- 30+ maps - spawns, bush/tree/rock/building positions, minimap images
- Equipment, consumables, provisions
- Crew skills with actual bonus values
- Camouflages with invisibility bonuses
Setup
Add to your Claude Desktop config (or any MCP-compatible client):
{
"mcpServers": {
"wotblitz": {
"command": "npx",
"args": ["-y", "wotblitz-mcp"],
"env": {
"WOTB_GAME_PATH": "C:/Program Files (x86)/Steam/steamapps/common/World of Tanks Blitz/Data"
}
}
}
}
Point WOTB_GAME_PATH to your game's Data folder.
Tools
Tanks
get_tank- stats for a specific tank (fuzzy search works)search_tanks- filter by nation/tier/class/type/namecompare_tanks- side by side comparisonanalyze_matchup- detailed 1v1 breakdown
Maps
list_maps- all maps with spawn pointsget_map- terrain data (bushes, trees, rocks, buildings, walls, capture points)get_map_image- top-down minimap
Items
list_equipmentlist_consumableslist_provisions
Crew
list_crew_skills- filter by tank class
Camo
list_camouflages- filter by nation/type/nameget_camouflage- specific camo with bonus valuesget_camo_bonus- bonus table per tank class
Other
list_nationsanalyze_match- team comp analysis on a map
How it works
Reads DVPL files (LZ4 compressed), parses SC2 scene files for map geometry, decodes DDS textures for minimaps. All from your local game installation.
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。