数字营销工具
经 AI Skill Hub 精选评估，数字营销工具 获评「推荐使用」。这款MCP工具在功能完整性、社区活跃度和易用性方面表现出色，AI 评分 7.5 分，适合有一定技术背景的用户使用。
通过安装 数字营销工具，你的 AI 助手将获得额外的工具调用能力，可以用自然语言直接操控该工具的功能，无需学习复杂的命令行语法。MCP 工具的核心价值在于"一次配置，永久增强"——配置完成后，每次与 AI 对话时都可以无缝调用这些工具。
在技术实现上，MCP 工具通过标准的 JSON-RPC 协议与 AI 客户端通信，工具的功能以"工具列表"的形式暴露给 AI 模型，AI 可以按需调用。数字营销工具 提供了结构化的工具调用接口，使 AI 模型能够精确地理解和使用每个功能点，显著降低 AI 在工具使用上的错误率。
与传统的 API 集成相比，MCP 工具的优势在于无需编写代码——用户只需在配置文件中添加几行 JSON，即可让 AI 获得全新能力。AI Skill Hub 将 数字营销工具 评为 AI 评分 7.5 分，属于同类工具中的优质选择。
数字营销工具 是一款遵循 MCP（Model Context Protocol）标准协议的 AI 工具扩展。通过 MCP 协议，它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务，实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用，都可以通过自然语言在 AI 对话中直接触发，极大提升生产效率。
数字营销工具 是一款遵循 MCP（Model Context Protocol）标准协议的 AI 工具扩展。通过 MCP 协议，它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务，实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用，都可以通过自然语言在 AI 对话中直接触发，极大提升生产效率。
- 通过标准 MCP 协议与 Claude、Cursor 等主流 AI 客户端深度集成
- 提供结构化工具调用接口，显著降低 AI 集成复杂度
- 支持 Claude Desktop 和 Claude Code 无缝接入，开箱即用
- 可与其他 MCP 工具组合叠加，构建完整 AI 工作站
- 轻量无侵入设计，不影响现有系统架构
- 在 Claude Desktop 对话中直接调用本地工具，实现 AI 与系统的深度联动
- 通过自然语言驱动复杂的多步骤自动化任务，代替繁琐手动操作
- 将多个 MCP 工具组合使用，构建个人专属 AI 工作站
# 方式一：通过 Claude Code CLI 一键安装
claude skill install https://github.com/indranilbanerjee/digital-marketing-pro
# 方式二：手动配置 claude_desktop_config.json
{
"mcpServers": {
"------": {
"command": "npx",
"args": ["-y", "digital-marketing-pro"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
- 确认已安装 Node.js（v18 或以上版本）
- 打开 Claude Desktop 或 Claude Code 的 MCP 配置文件
- 按「交给 Agent 安装 → Claude Desktop」标签中的 JSON 配置填入 mcpServers 字段
- 保存配置文件并重启 Claude 客户端
- 重启后，在对话中即可使用本工具
# 安装后在 Claude 对话中直接使用 # 示例： 用户: 请帮我用 数字营销工具 执行以下任务... Claude: [自动调用 数字营销工具 MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入："列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"______": {
"command": "npx",
"args": ["-y", "digital-marketing-pro"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
Digital Marketing Pro
End-to-end engagement methodology for marketing teams running on Claude Code & Cowork.
DM Pro is the most ambitious marketing plugin in the Neelverse suite. It runs every brand engagement through a canonical 12-Part Strategy Flow producing the Four Core Documents (61 explicit steps), the Two-Views Model (v1 unbiased + v2 client-validated), the Decision Matrix for selective re-runs, and the Living Project Instruction File. 25 specialist agents, 150 skills, 71 Python scripts, 14 HTTP MCP connectors, 16 industry profiles, 16 privacy-law jurisdictions. v3.5.0 is a May-2026-ecosystem refresh: Google AI Mode now treated as a distinct AEO surface (6 platforms, not 5), May 2026 broad core update triage guidance, EU AI Act Article 50 draft implementing guidelines (8 May 2026; consultation closes 3 June), Meta Advantage+ Leads global rollout + Threads ads + tightened brand-safety controls, Gemini Omni / Nano Banana Pro / Veo 3.1 added to AI creative-brief skills with mandatory C2PA + deepfake-disclosure clauses, and Claude Code v2.1.149+ /usage per-model cost tracking integrated into the agency dashboard. Designed for digital marketing agencies, in-house teams running 50–200 brands, and consultancies who want consistent depth and auditable handoffs.
Current version: 3.5.0 — see Release notes at the bottom of this README.
---
Python dependencies (optional)
The plugin works fully without any Python installation. All marketing knowledge, frameworks, agent capabilities, and slash commands work out of the box.
Knowledge-only mode (0 MB, no install) — Default All 16 modules, 25 agents, 149 skills, and 170+ reference knowledge files work with zero dependencies.
Lite mode (~15 MB) — Enables scoring scripts
pip install nltk textstatFull mode (~50 MB) — Enables all scripts
pip install -r scripts/requirements.txtbeautifulsoup4, requests), QR code generation, AI visibility API checking.
---
1. Install the plugin
```bash
Install Digital Marketing Pro
/plugin install digital-marketing-pro@neels-plugins ```
Tested in Claude Code CLI, Claude Code Desktop, and Anthropic Cowork. Web chat (claude.ai) does not support /plugin commands.
Installs in Cowork
Cowork is the Anthropic Desktop computer-use product (macOS/Windows). It supports third-party plugins from custom marketplaces — same /plugin marketplace add indranilbanerjee/neels-plugins install pattern, then /plugin install digital-marketing-pro@neels-plugins. Cowork has local filesystem access, so the full DM Pro pipeline including all 70 Python scripts runs natively. The only Cowork-specific limitation is HTTP MCPs only (no stdio/npx) — DM Pro's 14 HTTP connectors are all Cowork-compatible; for stdio servers see .mcp.json.example.
---
Manifest install error: "repository field is an object" or "$schema unknown"
Fixed in v3.2.1. Update via the Updating section.
Quick start
Quick examples
```bash
Status with options
/digital-marketing-pro:status --brand acme-corp --section engagements /digital-marketing-pro:status --json ```
Re-enable hooks at your own settings level
Plugin hooks fire globally regardless of working directory. If you genuinely want a global PreToolUse content-check or SessionStart brand banner, copy the snippet from hooks/hooks-reference.example.json into your own ~/.claude/settings.json. That keeps the hook scoped to your installation, not pushed onto everyone who installs the plugin.
---
Connectors (MCP integrations)
DM Pro ships with 14 HTTP MCP connectors that work in both Cowork and Claude Code:
Notion · Slack · Canva · Figma · HubSpot · Amplitude · Ahrefs · Similarweb · Klaviyo · Google Calendar · Gmail · Stripe · Asana · Webflow
For Claude Code users who want the full ~68-server stdio configuration (Google Ads, Meta Ads, GA4, GSC, Mixpanel, Marketo, Brevo, etc. via npx), copy the example:
cp .mcp.json.example .mcp.jsonFor Cowork users who need services without first-party HTTP MCPs (Google Sheets, Drive, Salesforce, dozens more SaaS), see .mcp.json.connectors-reference for Pipedream / Composio / Zapier / Make.com aggregator paths.
See CONNECTORS.md for the full reference and MCP Integration Guide for setup walkthroughs.
---
Multi-client workflow (agencies)
- Create profiles per client:
/digital-marketing-pro:brand-setup - Switch clients:
/digital-marketing-pro:switch-brandor just say "switch to [client name]" - Outputs adapt to the active client's voice, compliance, jurisdictions, history
- Each client's data lives in its own
~/.claude-marketing/<brand-slug>/directory
See Multi-Brand & Agency Guide for detailed workflows.
---
The plugin claims `/dm:check` will run automatically on every Write/Edit
That was the v3.0/v3.1 behavior via a global PreToolUse hook. Removed in v3.1 because plugin hooks fire across every project regardless of context. Now use /digital-marketing-pro:check explicitly before publishing, or re-enable the hook at your own user-settings level — see hooks/hooks-reference.example.json for the snippet.
Troubleshooting
FAQ
Q: Which Claude interface should I use?
| Claude Code | Claude Cowork | Claude Desktop (no Cowork) | claude.ai web | |
|---|---|---|---|---|
| Full plugin support | Yes | Yes | Partial | No |
| Brand memory | Yes | Yes | No | No |
| MCP integrations | All | HTTP only | HTTP only | No |
| Document creation (Excel, PPT) | No | Yes | No | No |
| Recommended for | Terminal workflows + scripting | Visual desktop workflows | Quick content | One-off questions |
Q: How does this compare to Anthropic's official marketing plugins? Anthropic's directory has not yet accepted a full multi-agent marketing methodology plugin. DM Pro covers a much wider surface — full 12-part methodology, 16 industry profiles, 16 jurisdictions, multi-brand operations — than any single official marketing plugin currently in the directory.
Q: How much does it cost to run? Plugin is MIT-licensed and free. Claude API costs vary with engagement complexity. A full 12-part engagement using Opus 4.7 typically runs $15–40 in API costs across 50–60 documents.
Q: Can I run multiple brands in parallel? Yes. Each brand has its own ~/.claude-marketing/<brand-slug>/ directory and Python script state. Switch brands with /digital-marketing-pro:switch-brand.
Q: What if I only want a campaign plan, not the full 12-part methodology? Skip straight to /digital-marketing-pro:campaign-plan. The full engagement is the canonical path but every individual surface (campaign / SEO audit / content / competitor / email / report) is independently runnable.
---
该工具提供了丰富的数字营销功能和高效的MCP服务器，值得关注和学习。
- 通过标准 MCP 协议与 Claude、Cursor 等主流 AI 客户端深度集成
- 提供结构化工具调用接口，显著降低 AI 集成复杂度
- 支持 Claude Desktop 和 Claude Code 无缝接入，开箱即用
- 可与其他 MCP 工具组合叠加，构建完整 AI 工作站
- 轻量无侵入设计，不影响现有系统架构
- 在 Claude Desktop 对话中直接调用本地工具，实现 AI 与系统的深度联动
- 通过自然语言驱动复杂的多步骤自动化任务，代替繁琐手动操作
- 将多个 MCP 工具组合使用，构建个人专属 AI 工作站
- +MIT 协议，可免费商用
- +标准化 MCP 协议，生态互联性强
- +与 Claude 官方生态无缝对接
- +即插即用，配置简单快捷
- −依赖 Claude 客户端，非 Claude 用户无法使用
- −MCP 协议仍在持续演进，接口可能变更
- −需要一定的配置步骤
AI Skill Hub 为第三方内容聚合平台，本页面信息基于公开数据整理，不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后，再部署至生产环境，并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一，可自由商用、修改、分发，仅需保留版权声明。
AI Skill Hub 点评：数字营销工具 的核心功能完整，质量良好。对于Claude Desktop / Claude Code 用户来说，这是一个值得纳入个人工具库的选择。建议先在非生产环境试用，再逐步推广。
| 原始名称 | digital-marketing-pro |
| Topics | 数字营销MCPPython |
| GitHub | https://github.com/indranilbanerjee/digital-marketing-pro |
| License | MIT |
| 语言 | Python |
收录时间：2026-05-23 · 更新时间：2026-05-23 · License：MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。