Skip to main content
Glama
deenesjakoruzh
avivek-dwivedi

Admissions MCP Hub

by avivek-dwivedi
OverviewSchemaRelated ServersScoreDiscussions
Python
Remote

Admissions MCP Hub

Ein verwalteter Model Context Protocol-Server, der Kurs-, Kursdurchgang-, Gebühren-, Lead- und Rückruffunktionen über einen einzigen MCP-Vertrag für zwei unabhängige KI-Chat-Apps bereitstellt.

Was das zeigt

  • Ein MCP-Server, zwei unabhängige Clients (Lernender + Berater) — keine doppelten Integrationen

  • DB-Zugangsdaten, Auth, Audit, Validierung — alles zentral auf dem Server

  • Schreibvorgänge erfordern ein Bestätigungs-Gate (prepare → confirm) — ein LLM kann keinen Lead allein erstellen

  • Jeder Tool-Aufruf wird auditiert (Akteur, Client, Args-Hash, Ergebnis, Latenz)

  • Eine No-MCP-Vergleichsdemo zeigt, was man ohne MCP verlieren würde

Architektur

Related MCP server: ComplyOS

Schnellstart

# 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

Öffnen Sie http://localhost:8501 — zwei Chat-Tabs (Lernender + Berater).

No-MCP-Vergleich: uv run streamlit run ui/no_mcp_demo.py --server.port 8502

Ausprobieren

🎓 Lernassistent

Prompt

Was passiert

What courses do you have?

Listet 4 Kurse auf

Tell me about the agentic AI course

Termine der Kursdurchgänge + Gebührenangebot + Richtlinien

What is the admissions policy?

Gibt Richtlinientext zurück

I'd like a callback

✅/❌ Bestätigungs-Gate vor der Lead-Erstellung

🎧 Beraterkonsole

Prompt

Was passiert

What courses are available?

Listet 4 Kurse auf

Show me upcoming batches for agentic AI

3 Kursdurchgänge mit Plätzen

Generate a fee quote for mlops

Angebots-ID + Gesamtsumme (INR)

List my leads

Zeigt zugewiesene Leads

Update stage for SCAI-XXXXXXXX to enrolled

✅/❌ Bestätigungs-Gate

Siehe RUN_GUIDE.md für vollständige Prompts + erwartete Antworten.

Architektur

Port

Service

Rolle

5433

PostgreSQL

Zentrale Datenquelle (Kurse, Kursdurchgänge, Leads, Audit)

8010

MCP Server

Tools (11) + Resources (8) + Prompts (2), JWT-Auth, RBAC, Audit

8020

Learner Host

LangGraph-App – Lernender-JWT, Bestätigungs-Gate für Schreibvorgänge

8030

Counsellor Host

LangGraph-App – Berater-JWT, Lead-Verwaltung

8501

Streamlit UI

Zwei Chat-Tabs (MCP-basiert)

8502

No-MCP Demo

Gleicher Ablauf, direkter DB-Zugriff – zeigt, wovor MCP schützt

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

Kernkonzepte

Konzept

Wo

Warum es wichtig ist

Bestätigungs-Gate

leads_prepare → leads_confirm_create

LLM kann ohne menschliches ✅ keinen Lead erstellen

Idempotenz

IdempotencyRepository (Payload-Hash)

Netzwerk-Wiederholungen erzeugen keine Duplikate

RBAC

ROLE_TOOLS-Map in _runner.py

Lernender kann die Leads anderer Personen nicht sehen

Audit

ToolAuditEvent-Tabelle

Jeder Aufruf wird protokolliert: wer, was, Ergebnis, Latenz

Zustandslosigkeit

Server-generierte IDs (quote_id, lead_id)

Horizontale Skalierung ohne Sitzungen

Projektstruktur

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

Tests

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

Referenzen

This server cannot be installed

F
license - not found
Not graded
quality - not tested
C
maintenance

How are these scores calculated?

Maintenance

–Maintainers
–Response time
–Release cycle
–Releases (12mo)
Commit activity

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

  • Updation MCP

    Sai-Manvith
    F
    license
    Not graded
    quality
    D
    maintenance
    A production-grade, LLM-agnostic MCP server that integrates AI models with tools for managing subscriptions, organizations, and payments via the Updation API. It features Redis-backed conversation memory, structured logging, and role-based access control for secure, scalable orchestration.

  • ComplyOS

    simongonzalezdc
    A
    license
    Not graded
    quality
    B
    maintenance
    AI-native compliance auditing engine for enterprise LMS, enabling querying compliance status, running audits, and validating assignment rules through natural language with MCP clients like Claude or Cursor.
    Business Source 1.1

  • SchoolBridge

    NSK-394
    F
    license
    Not graded
    quality
    C
    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
    B
    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.

View all related MCP servers

Related MCP Connectors

  • GIA — Governed Intelligence Architecture

    Runtime AI governance: decision gates, human approval, hash-chained audit, compliance mapping.

  • ThinkNEO Control Plane

    Enterprise AI Control Plane: governance, guardrails, spend tracking, compliance & smart routing.

  • odoo

    Odoo ERP for AI agents: hosted OAuth endpoint, gated writes, one endpoint for every instance.

View all MCP Connectors

Latest Blog Posts

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/avivek-dwivedi/custom-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server