Skip to main content
Glama
LinGeorge2

MCP-marketing

by LinGeorge2

MCP-marketing

行銷輿情 MCP Server — 提供關鍵字監控、輿情收集、AI 分析、報告產生功能。 任何業務專案皆可透過 MCP Protocol 接入使用。

專案結構

MCP-marketing/
├── mcp_server/        # MCP Server 對外介面
│   └── tools/         # start_monitoring / get_mentions / generate_report / set_alert
├── agents/            # AI Agent 團隊(Orchestrator / Crawler / Analyst / Reporter)
├── crawlers/          # 各平台爬蟲(PTT / Dcard / Twitter / Facebook / YouTube / RSS)
├── db/                # 資料模型(PostgreSQL)
├── queue/             # Celery 排程任務
├── web/               # Web Dashboard(FastAPI + Next.js)
└── config/            # 環境設定

快速開始

# 1. 建立 Python 環境
python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt

# 2. 設定環境變數
cp .env.example .env
# 編輯 .env 填入 API 金鑰

# 3. 啟動 MCP Server
python -m mcp_server.server

接入其他專案(Claude Desktop)

{
  "mcpServers": {
    "marketing-mcp": {
      "command": "/home/george/MCP/MCP-marketing/.venv/bin/python",
      "args": ["-m", "mcp_server.server"],
      "cwd": "/home/george/MCP/MCP-marketing",
      "env": {
        "MCP_PROJECT_ID": "your-project-id"
      }
    }
  }
}

可用工具

工具

說明

start_monitoring

啟動關鍵字監控排程

stop_monitoring

停止監控

get_mentions

查詢輿情資料

generate_report

產生分析報告

set_alert

設定警報閾值與 webhook

開發階段

  • Phase 1:專案骨架、PTT/Dcard 爬蟲、MCP Server 基礎工具

  • Phase 2:Twitter API、AI 分析、Celery 排程、Alert

  • Phase 3:Facebook/YouTube、Qdrant 語意搜尋、Web Dashboard

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

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

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/LinGeorge2/MCP-marketing'

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