warframe-mcp

warframe-mcp

Provides AI assistants with real-time access to Warframe game data including world state, item stats, market prices, drop tables, builds, crafting, and farming optimization through 19 tools.

Category
访问服务器

README

Warframe MCP Server

Warning: This project was 100% vibecoded and exists purely for my personal needs. Use at your own risk.

A Model Context Protocol (MCP) server that gives AI assistants real-time access to Warframe game data. 19 tools covering world state, item stats, market prices, drop tables, builds, crafting, farming optimization, task synergy planning, and color palette matching — powered by public APIs with zero authentication required.

Tools

Tool Description
world_state Current sortie, archon hunt, nightwave, invasions, open world cycles, events, Steel Path, construction progress, daily deals
baro_kiteer Baro Ki'Teer status, inventory, and plat-per-ducat value analysis
active_fissures Void Fissure listings with tier/Steel Path/Void Storm/mission type filters
lookup_warframe Warframe stats, abilities, component drops, build cost, vault status
lookup_weapon Weapon damage per fire mode, crit/status, components, build info
lookup_mod Mod stats at all ranks, polarity, drain, rarity, drop locations
lookup_item Generic item lookup (arcanes, resources, blueprints, companions)
market_price_check Live warframe.market prices — sell/buy stats, cheapest sellers, trade chat messages
search_drops Drop table search — relics, missions, enemies, with drop chances
relic_drops Which relics contain a prime part, refinement chances, relic farm locations
prime_vault_status Vaulted / farmable / Varzia resurgence status for prime items
simaris_target Today's Cephalon Simaris synthesis target and scan locations
find_enemy_spawn Where specific enemies spawn — confirmed locations from drop tables
lookup_builds Top community mod builds from Overframe.gg with mod lists and stats
crafting_requirements Full crafting recipes — components, credits, build time, sub-recipes
crafting_usage Reverse ingredient lookup — "what uses this?" / "safe to sell?"
farm_route_optimizer Best nodes to farm multiple resources — dark sector bonuses, overlap scoring
task_synergy_planner Cross-reference Nightwave with fissures/invasions/sortie for max efficiency
color_palette_finder Find closest in-game color palette match for any hex color (Fashion Frame)

Most lookup tools accept arrays (batch mode) to handle multiple items in a single call.

Quick Start

npm

git clone https://github.com/YOUR_USER/warframe-mcp.git
cd warframe-mcp
npm install
npm run build

Stdio mode (for MCP clients like Claude Desktop, OpenCode, Cursor):

npm start

HTTP mode (Streamable HTTP transport for remote/web clients):

npm run start:http
# Listening on http://127.0.0.1:3000/mcp

Docker

docker build -t warframe-mcp .

# HTTP mode (default)
docker run -p 3000:3000 warframe-mcp

# Stdio mode
docker run -i warframe-mcp node dist/index.js

Configuration

All configuration is via environment variables. None are required — defaults work out of the box.

Variable Default Description
PORT 3000 HTTP listen port
HOST 127.0.0.1 Bind address. Use 0.0.0.0 for LAN/container access
ALLOWED_HOSTS — Comma-separated hostnames/IPs allowed through DNS rebinding protection (only needed when HOST=0.0.0.0)

Example — LAN-accessible server:

HOST=0.0.0.0 PORT=3000 ALLOWED_HOSTS=192.168.1.100,mypc.local npm run start:http

Client Setup

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "warframe": {
      "command": "node",
      "args": ["/absolute/path/to/warframe-mcp/dist/index.js"]
    }
  }
}

Claude Desktop (Docker)

{
  "mcpServers": {
    "warframe": {
      "command": "docker",
      "args": ["run", "-i", "--rm", "warframe-mcp", "node", "dist/index.js"]
    }
  }
}

OpenCode

Add to opencode.json:

{
  "mcpServers": {
    "warframe": {
      "command": "node",
      "args": ["/absolute/path/to/warframe-mcp/dist/index.js"]
    }
  }
}

HTTP Clients (Streamable HTTP)

Start the server in HTTP mode, then connect to http://localhost:3000/mcp:

npm run start:http

# POST /mcp — JSON-RPC requests (initialize, tools/list, tools/call)
# GET  /mcp — SSE stream for server-to-client notifications
# DELETE /mcp — Session termination

Sessions are managed via the Mcp-Session-Id header. Send an initialize request without a session ID to start a new session.

Smoke Test

# Stdio — should return JSON with 19 tools
echo '{"jsonrpc":"2.0","method":"tools/list","id":1}' | node dist/index.js

# HTTP — initialize a session
curl -X POST http://localhost:3000/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -d '{"jsonrpc":"2.0","method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"test","version":"0.1"}},"id":1}'

System Prompt

SYSTEM_PROMPT.md contains a ready-to-use system prompt for an AI assistant that uses this MCP server. It includes tool documentation, a decision tree for tool selection, multi-tool chaining strategies, batching guidance, and Warframe domain knowledge (relics, rotations, trading, modding, Steel Path, open world cycles).

Architecture

src/
├── index.ts              # Entry point — stdio or HTTP transport
├── api/
│   ├── warframestat.ts   # warframestat.us client (items, drops, worldstate)
│   ├── warframe-market.ts # warframe.market v2 client (prices, orders)
│   ├── overframe.ts      # Overframe.gg scraper (community builds)
│   └── wiki.ts           # Fandom wiki API client (crafting recipes)
├── tools/
│   ├── worldstate.ts     # world_state, baro_kiteer, active_fissures
│   ├── items.ts          # lookup_warframe, lookup_weapon, lookup_mod, lookup_item
│   ├── market.ts         # market_price_check
│   ├── drops.ts          # search_drops, relic_drops
│   ├── primeVault.ts     # prime_vault_status
│   ├── simaris.ts        # simaris_target
│   ├── enemy.ts          # find_enemy_spawn
│   ├── builds.ts         # lookup_builds
│   ├── crafting.ts       # crafting_requirements, crafting_usage
│   ├── farmOptimizer.ts  # farm_route_optimizer
│   ├── synergy.ts        # task_synergy_planner
│   └── colors.ts         # color_palette_finder
├── types/
│   ├── warframestat.ts   # warframestat.us API types
│   ├── warframe-market.ts # warframe.market v2 types
│   ├── overframe.ts      # Overframe build types
│   └── index.ts          # Re-exports
├── data/
│   ├── color-palettes.ts # 31 Warframe color palettes (2,790 colors)
│   └── planet-resources.ts # Planet resource drops, dark sector nodes & bonuses
└── utils/
    ├── cache.ts          # TTL cache (60s–24h depending on data type)
    ├── formatting.ts     # Number/time formatting helpers
    └── lua-parser.ts     # Lua table parser for wiki blueprint data

Data Sources

API Base URL Auth Used For
warframestat.us https://api.warframestat.us None World state, items, drops, mods, weapons, warframes
warframe.market https://api.warframe.market/v2 None Live trading prices and orders
Overframe.gg https://overframe.gg None (HTML scraping) Community mod builds
Warframe Wiki MediaWiki API None Crafting recipes (blueprint data)
Bundled static data — — Planet resources, dark sector bonuses, 31 color palettes (2,790 colors)

Caching

Data Type TTL Examples
World state 60 seconds Fissures, invasions, cycles
Drop tables 5 minutes Drop search results
Market items 24 hours Item listing catalog
Static data 24 hours Warframe/weapon/mod stats
Wiki data 24 hours Crafting recipes
Overframe builds 6 hours Community builds

Development

npm run dev    # tsc --watch
npm run build  # One-shot compile
npm start      # Run stdio mode

Requirements

  • Node.js >= 18 (uses native fetch)
  • TypeScript 5.x
  • No runtime dependencies beyond @modelcontextprotocol/sdk, express, and zod

License

MIT

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选