SCHOOL101

SCHOOL101

A unified Model Context Protocol server that consolidates global educational platforms, enabling AI agents to seamlessly integrate with Canvas LMS, K-12 standards, assessment tools, and educational data analytics.

Category
访问服务器

README

SCHOOLME101 MCP Server v1

Production-ready TypeScript MCP server foundation for Cloudflare Workers, focused on Africa and South Africa education, with Android-ready contracts.

Highlights

  • Cloudflare Worker MCP transport (POST /mcp)
  • 27 validated education tools across curriculum, study, STEM, language, assessment, progress, teacher, and accessibility workflows
  • South Africa CAPS-first curriculum metadata with Africa extension placeholders
  • Security-by-default hooks: token verification, role checks, approval gate, audit logging
  • Optional D1-backed teacher progress history and dashboard flows, with Android integration contracts and offline sync hook conventions

Architecture

  • src/server - MCP transport, JSON-RPC handling, route registration
  • src/tools - tool catalog, validation schemas, execution mapping
  • src/domain - curriculum, assessment, progress, language, STEM, teacher, accessibility logic
  • src/security - auth, policy, approval, audit hooks
  • src/integrations - Canvas/Google Classroom placeholders
  • src/android - endpoint conventions and JSON contract examples

Tool Catalog

Curriculum

  1. list_curriculum_frameworks
  2. get_subjects_by_grade
  3. get_learning_objectives

Study and Revision

  1. create_study_plan
  2. spaced_repetition_schedule
  3. generate_revision_pack

STEM

  1. solve_math_stepwise
  2. generate_math_practice
  3. explain_science_concept
  4. generate_science_quiz

Language

  1. language_reading_passage
  2. language_comprehension_questions
  3. grammar_practice_generator

Assessment

  1. generate_exam_paper
  2. generate_assignment
  3. rubric_generator
  4. mark_scheme_generator

Progress and Analytics

  1. record_student_progress
  2. identify_learning_gaps
  3. recommend_interventions
  4. class_progress_summary
  5. get_student_progress_history
  6. teacher_dashboard

Teacher Workflow

  1. lesson_plan_generator
  2. classroom_activity_generator

Accessibility

  1. simplify_text_for_level
  2. dyslexia_friendly_format

All tools are strongly validated using Zod and include locale/country/grade/phase/language context support. Progress history and dashboard tools degrade safely when D1 is not configured.

MCP Examples

Initialize

{"jsonrpc":"2.0","id":1,"method":"initialize"}

List tools

{"jsonrpc":"2.0","id":2,"method":"tools/list"}

Call tool

{
  "jsonrpc": "2.0",
  "id": 3,
  "method": "tools/call",
  "params": {
    "name": "create_study_plan",
    "arguments": {
      "topic": "Linear Equations",
      "weeks": 4,
      "locale": "en-ZA",
      "country": "ZA",
      "grade": "8",
      "phase": "senior",
      "language": "English"
    }
  }
}

Security Model

  • Token verification hook: src/security/auth.ts (stub; replace with JWT/OIDC)
  • Role-aware authorization: student, teacher, lecturer, admin
  • Approval gate: destructive tool record_student_progress requires approval code
  • Audit trail stub: tool usage event logging in src/security/audit.ts
  • Rate limit strategy: configured via RATE_LIMIT_* vars, enforce using Cloudflare edge controls/WAF

Android Integration Notes

  • Endpoints: /mcp, /health, /android/contracts
  • Contract helpers: src/android/contracts.ts
  • Token handling: send a bearer token in the Authorization header
  • Offline sync hook: operation IDs + retry/backoff + idempotency key
  • D1-backed progress workflows are optional in local/dev mode and return safe stub notes when storage is not configured

Scripts

  • npm run dev - local worker via Wrangler
  • npm run build - compile TypeScript
  • npm run typecheck - strict static checks
  • npm run lint - alias for typecheck
  • npm test - unit tests
  • npm run deploy - Cloudflare production deploy

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