Skip to main content
Glama
Sign In
deenesjakoruzh
Admissions MCP Hub

Admissions MCP Hub

by avivek-dwivedi
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Admissions MCP Hub

一个受治理的 Model Context Protocol 服务器，通过单一 MCP 契约向两个独立的 AI 聊天应用提供课程、批次、费用、潜在学员和回调能力。

这证明了什么

  • 一个 MCP 服务器、两个独立客户端（学员 + 顾问）——无需重复集成

  • 数据库凭据、认证、审计、验证——全部集中在服务器端

  • 写入操作需要确认门禁（prepare → confirm）——LLM 无法单独创建潜在学员

  • 每次工具调用都会被审计（操作者、客户端、参数哈希、结果、延迟）

  • 一个无 MCP 对比演示展示了没有 MCP 时你会失去什么

Architecture

Related MCP server: company-state-mcp

快速开始

# 1. PostgreSQL
docker compose up -d postgres

# 2. Migrate + seed
uv sync
uv run alembic upgrade head
uv run python scripts/seed_demo.py

# 3. Start services (4 terminals)
uv run uvicorn services.mcp_server.app:asgi_app --port 8010
uv run uvicorn services.learner_host.api:app --port 8020
uv run uvicorn services.counsellor_host.api:app --port 8030
uv run streamlit run ui/app.py --server.port 8501

打开 http://localhost:8501——两个聊天标签页（学员 + 顾问）。

无 MCP 对比： uv run streamlit run ui/no_mcp_demo.py --server.port 8502

试用

🎓 学员助手

提示词

结果

What courses do you have?

列出 4 门课程

Tell me about the agentic AI course

批次日期 + 费用报价 + 政策

What is the admissions policy?

返回政策文本

I'd like a callback

✅/❌ 创建潜在学员前的确认门禁

🎧 顾问控制台

提示词

结果

What courses are available?

列出 4 门课程

Show me upcoming batches for agentic AI

3 个有名额的批次

Generate a fee quote for mlops

报价 ID + 总计（INR）

List my leads

显示已分配的潜在学员

Update stage for SCAI-XXXXXXXX to enrolled

✅/❌ 确认门禁

完整提示词与预期答案请参阅 RUN_GUIDE.md。

架构

端口

服务

角色

5433

PostgreSQL

权威数据源（课程、批次、潜在学员、审计）

8010

MCP Server

工具（11）+ 资源（8）+ 提示词（2）、JWT 认证、RBAC、审计

8020

Learner Host

LangGraph 应用——学员 JWT、写入确认门禁

8030

Counsellor Host

LangGraph 应用——顾问 JWT、潜在学员管理

8501

Streamlit UI

两个聊天标签页（基于 MCP）

8502

No-MCP Demo

相同流程、直连数据库——展示 MCP 所防护的风险

技术栈： Python 3.11 · MCP SDK · LangGraph · FastAPI · SQLAlchemy 2 · PostgreSQL 16 · Pydantic v2 · Ollama (qwen3.5:2b) · Streamlit

核心概念

概念

位置

重要性

确认门禁

leads_prepare → leads_confirm_create

没有人工 ✅，LLM 无法创建潜在学员

幂等性

IdempotencyRepository（参数哈希）

网络重试不会产生重复数据

RBAC

_runner.py 中的 ROLE_TOOLS 映射

学员无法查看他人的潜在学员

审计

ToolAuditEvent 表

每次调用均记录：谁、什么操作、结果、延迟

无状态性

服务器生成的 ID（quote_id、lead_id）

无需会话即可水平扩展

项目结构

scai-mcp-admissions/
├── services/
│   ├── mcp_server/          # MCP server (tools, resources, prompts, auth, audit)
│   ├── learner_host/        # LangGraph learner app (port 8020)
│   └── counsellor_host/     # LangGraph counsellor app (port 8030)
├── ui/
│   ├── app.py               # Streamlit — 2 chat tabs (MCP)
│   └── no_mcp_demo.py       # Streamlit — no-MCP comparison (direct DB)
├── packages/
│   ├── contracts/           # Pydantic tool inputs/outputs + domain models
│   ├── shared/              # Config, LLM adapter, JWT tokens
│   └── observability/       # Structured logging, tracing
├── scripts/
│   ├── seed_demo.py         # Seed 4 courses, 4 batches, 4 fee plans, 3 policies
│   ├── issue_dev_token.py   # Issue dev JWTs for manual testing
│   └── run_demo_checks.py   # Smoke tests against running server
├── tests/                   # unit, contract, integration, security, e2e
├── migrations/              # Alembic migrations
├── data/demo_seed/          # Seed data + knowledge_base.json
├── mcp_concept.ipynb        # MCP concept notebook (what/why/how/scale/use cases)
├── mcp_flow_diagram.mmd     # Mermaid source for architecture diagram
├── mcp_flow_diagram.png     # Rendered architecture diagram
├── RUN_GUIDE.md             # Step-by-step run guide with test prompts
└── docker-compose.yml        # PostgreSQL 16

测试

uv run pytest              # all tests
uv run pytest -m unit      # just unit tests
uv run pytest -m contract  # contract tests

参考资料

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Resources

Related MCP Connectors

Related MCP Servers

  • SchoolBridge

    NSK-394
    F
    license
    Not graded
    quality
    D
    maintenance
    An MCP server that enables AI agents to safely query and act on school data (attendance, fees, student records) with strict role-based access control and a two-step write approval flow.
    -

  • company-state-mcp

    kcole16
    F
    license
    Not graded
    quality
    D
    maintenance
    Single source of truth and control for agent-operated companies, managing business state with deterministic policy enforcement, seat identity, and hash-chained audit trail.
    -

  • enterprise-agent-lab

    isaac-dev-ai
    F
    license
    Not graded
    quality
    C
    maintenance
    Enables controlled AI-agent access to enterprise-shaped tools with a deny-by-default gated write path, human approval, dry-run execution, and append-only audit logging.
    1
    -

  • Nexus MCP Enterprise Gateway

    JayNabasu
    A
    license
    Not graded
    quality
    C
    maintenance
    Enables secure enterprise integration by bridging SQL, financial, SCADA, and document backends to LLM agents with RBAC, DLP redaction, human-in-the-loop approvals, and OpenTelemetry tracing.
    MIT