MCP Riddle Game Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP Riddle Game ServerGive me a random riddle"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Riddle Game Server
一个基于 Starlette 的 MCP 猜谜游戏服务,支持 HTTP POST 和 SSE 两种通信方式。
功能
提供 4 个 MCP 工具:
get_riddle_random:获取谜语(random/sequential/category)get_riddle_answer:校验答案list_categories:列出分类get_riddle_count:谜语统计
支持从
riddles.json加载数据可通过环境变量
RIDDLES_JSON覆盖谜语库
Related MCP server: WordComb MCP Server
项目结构
mcp-riddle/
├── server_sse.py
├── riddles.json
├── requirements.txt
├── Dockerfile
├── DEPLOY.md
└── README.md本地运行
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
python server_sse.py启动后默认监听 0.0.0.0:8000。
接口
SSE:
GET /sseMCP 消息:
POST /messages健康检查:
GET /health
兼容端点(用于部分第三方 Agent):
GET /mcp(SSE 别名)POST /sse(部分平台会对同一路径发消息)POST /sse/messages(SSE 消息别名)POST /mcp(单路径兼容)
健康检查示例
curl http://127.0.0.1:8000/healthHTTP 模式调用示例
curl -X POST http://127.0.0.1:8000/messages \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'curl -X POST http://127.0.0.1:8000/messages \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"get_riddle_random","arguments":{"mode":"sequential"}}}'Docker
docker build -t mcp-riddle .
docker run -d --name mcp-riddle-server -p 48080:8000 --restart always mcp-riddle
curl http://127.0.0.1:48080/healthAI Agent 接入
SSE 方式
{
"mcpServers": {
"riddle-game": {
"url": "http://<server-ip>:48080/sse",
"transport": "sse"
}
}
}如果平台只允许填一个端点路径,优先使用 /mcp。
HTTP 方式
{
"mcpServers": {
"riddle-game": {
"url": "http://<server-ip>:48080/messages",
"transport": "http"
}
}
}This server cannot be deployed
Maintenance
Related MCP Connectors
AI Reasoning Cache & Consensus Layer with 11 MCP tools via Streamable HTTP.
Exposes FEDLIN's public security scanners as agent-callable tools over Streamable HTTP.
16 AI-native tools with dual SSE + streamable-http transport. Free tier available.
Human-input bridge for AI agents with voice-first answer links, MCP tools, and HTTP APIs.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceProvides integrated access to location-based weather, reporting history, and infrastructure status data for safety reporting systems. It supports both SSE and stdio protocols for flexible integration with various AI agents and clients.-
- FlicenseNot gradedqualityDmaintenanceExposes a word combination engine with tools to generate permutations and check words against English and Arabic dictionaries, accessible via SSE.-
- FlicenseNot gradedqualityBmaintenanceEnables AI agents to dynamically discover and call backend tools for arithmetic, SQLite-backed task management, GitHub repository lookups, and text statistics, while also exposing the same functionality through a REST API.-
- FlicenseNot gradedqualityCmaintenanceEnables external AI clients to autonomously execute backend tools via SSE, including system health checks, within a FastAPI async microservice with conversational memory.-