Ticket Management & Meeting Overview MCP Server
An MCP server for managing tickets and meetings with CRUD operations, backed by PostgreSQL, and includes a REST API and React frontend.
README
Ticket Management & Meeting Overview MCP Server
An MCP (Model Context Protocol) server covering ticket management and meeting overview functionality, backed by PostgreSQL. Ships with:
- MCP server (
app/mcp_server.py) — stdio transport, built on the official Python MCP SDK (FastMCP) - REST API (
app/api.py) — FastAPI, exposing the same operations over HTTP - Frontend (
frontend/) — a React dashboard for tickets and meetings - All share the same PostgreSQL-backed data layer (
app/data/)
Stack
- Python 3.13
- FastAPI + Uvicorn
- Official MCP Python SDK
- SQLAlchemy + psycopg 3
- PostgreSQL 16 (via Docker)
Setup
-
Start PostgreSQL (requires Docker):
docker compose up -dThis runs Postgres on host port 5433 (not 5432, since 5432 may already be used by another local Postgres install).
-
Create a virtual environment and install dependencies:
python -m venv .venv .venv\Scripts\activate pip install -r requirements.txt -
Configure the database URL. Copy
.env.exampleto.env(already matches the default docker-compose credentials, so no edits needed for local dev):cp .env.example .env -
Create tables and seed initial data:
python -m app.seed
Running
-
MCP server (stdio transport, for use with an MCP client):
python -m app.mcp_server -
REST API:
uvicorn app.api:app --reloadInteractive docs available at
http://127.0.0.1:8000/docs. -
Frontend (requires the REST API running on port 8000):
cd frontend npm install npm run devOpen
http://localhost:5173.
Running tests
pytest tests/ -v
Tests run against a separate ticketdb_test database (created automatically
on the same Postgres instance), so they never touch your dev data.
MCP tools / REST endpoints
| Operation | MCP tool | REST endpoint |
|---|---|---|
| Health check | ping |
— |
| List tickets | list_tickets |
GET /tickets |
| Create ticket | create_ticket |
POST /tickets |
| Update ticket | update_ticket |
PATCH /tickets/{id} |
| Delete ticket | delete_ticket |
DELETE /tickets/{id} |
| List meetings | list_meetings |
GET /meetings |
| Create meeting | create_meeting |
POST /meetings |
| Update meeting | update_meeting |
PATCH /meetings/{id} |
| Delete meeting | delete_meeting |
DELETE /meetings/{id} |
Tickets have a status of open, in_progress, or closed. list_tickets
can filter by status; list_meetings can filter by date (exact match) and
attendee (case-insensitive).
Project structure
app/
data/
tickets.py # Ticket model + list/create/update/delete, backed by Postgres
meetings.py # Meeting model + list/create/update/delete, backed by Postgres
db.py # SQLAlchemy engine/session, reads DATABASE_URL
models.py # SQLAlchemy ORM models (TicketRow, MeetingRow)
mcp_server.py # MCP server exposing all tools
api.py # FastAPI app exposing all REST endpoints
seed.py # Creates tables and seeds initial data
tests/ # pytest suite (data layer + REST API), isolated test DB
docker-compose.yml # Local PostgreSQL for development
frontend/ # React + Vite dashboard (tickets + meetings CRUD UI)
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。