Doggi MCP Server
MCP1
远程 MCP 服务器,以 7 个工具的形式提供 Doggi(谨慎入门者)投资者心理课程。其构建目的是让 Claude 每次仅提取所需的课程片段,而不是重新摄入整个语料库。
布局
路径 | 内容 |
| 业务逻辑。 |
| HTTP 包装器。通过 MCP 可流式传输 HTTP 公开 |
| 本地客户端(Anthropic SDK)。用于在不部署的情况下测试工具流程 |
| 冒烟测试,运行每个工具 |
| 框架、原型、干预措施、进度(事实来源) |
| 第 1-6 课 Markdown(事实来源) |
| Fly.io 的部署配置 |
| 分步部署指南 |
Related MCP server: Thinking Patterns MCP Server
本地运行
# Smoke test, no API key needed
python3 tests/demo.py
# Run the HTTP server locally
MCP_API_KEY=test pip install -r requirements.txt
MCP_API_KEY=test python3 http_server.py
curl -H "X-API-Key: test" http://localhost:8000/mcp
# Live coaching client (needs ANTHROPIC_API_KEY + COACHING_MODEL)
python3 coaching_session.py部署
请参阅 DEPLOY.md — Fly.io,端到端大约 20 分钟。
工具
get_lesson(n)— 第 1-6 课get_framework()— 北极星指标get_archetype_triggers()— Doggi 触发器、红旗警告、优势get_coaching_intervention(n)— 第 n 课的辅导风格、建议/禁忌、示例get_progress_state()— 客户在旅程中所处的位置analyze_response(text, n)— 将用户文本与触发器和红旗警告进行匹配next_lesson(n)— 排序
自定义
所有内容都位于 data/ 和 lessons/ 中。编辑、提交、fly deploy。无需更改代码。
lessons/lesson{1-6}.md— 课程内容data/archetype.json— 触发器、红旗警告、优势data/interventions.json— 每节课的辅导风格data/progress_state.json— 客户状态(生产环境中替换为数据库查询)
设计说明
不要将此 README(或其他文档)放入 Claude Project 空间。 Claude 在每一轮对话中读取任何内容都会违背 MCP 的初衷。
不要硬编码过时的模型 ID。
coaching_session.py从环境变量中读取COACHING_MODEL。事实来源在磁盘上,而不是在代码中。 没有嵌入式副本。
工具描述特意保持简短(≤6 个单词)。架构描述了输入。
必须进行 API 密钥验证。
http_server.py如果没有MCP_API_KEY将拒绝启动。
安全性
所有
/mcp请求必须通过X-API-Key标头提供 API 密钥/health是开放的(Fly.io 需要它进行存活检查)路径遍历已拦截:在进行任何文件访问之前,
lesson_num会被验证为 1-6 之间的整数输入大小受限:
analyze_response会拒绝超过 10KB 的有效负载容器以非 root 用户身份运行
源代码中没有密钥 —
MCP_API_KEY和ANTHROPIC_API_KEY仅来自环境变量.gitignore和.dockerignore排除.env*和其他密钥模式
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceProvides comprehensive CRUD access to Anki flashcard data via MCP, enabling Claude to analyze decks, manage cards, create and update flashcards, organize tags, and perform advanced spaced repetition analysis through 18 data management tools.
- AlicenseBqualityDmaintenanceProvides AI systems with structured thinking frameworks and reasoning tools to maintain consistent problem-solving patterns across conversations. Enables multi-step reasoning, decision analysis, and systematic troubleshooting through invocable mental models.152419MIT
- FlicenseNot gradedqualityBmaintenanceEnables Claude to interact with IQ Option for demo trading: retrieve candles, payouts, place binary options and demo trades, all with safety guards preventing real-money trading unless explicitly allowed.2
- AlicenseNot gradedqualityAmaintenanceAI-powered investment discipline tool with investment RAG, behavior pattern mining, memory system, and multi-channel price/condition alertsAGPL 3.0
Related MCP Connectors
Read-only tools over the Safer Agentic AI framework: 238 patterns + 14 heuristics.
Calibrated world model for AI agents. 40 tools: world state, markets, trading. Kalshi + Polymarket.
Makuri (EU AI tutoring for immigrant children): 11 tools, 2 interactive panels, no user data.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/852-glitch/852-mcp12'
If you have feedback or need assistance with the MCP directory API, please join our Discord server