datavessel

datavessel

Hosted MCP server that gives AI agents read and write access to your full marketing & ecommerce stack — Google Analytics, Search Console, Google & Meta Ads, Shopify, WooCommerce, Shopware, Slack and LinkedIn. 100+ tools across 10 connectors. BYOK, OAuth 2.1.

Category
访问服务器

README

<div align="center">

datavessel — MCP server for your marketing & ecommerce stack

Connect your AI agent to 100+ read/write tools across Google Analytics, Search Console, Google & Meta Ads, Shopify, WooCommerce, Shopware, Slack and LinkedIn.

Website · App · MCP · Blog · Pricing

License MCP

</div>

This repository is the public home and setup guide for the datavessel MCP server. datavessel is a hosted, remote MCP server — there's nothing to install or run. Point your AI client at the URL below with your own API key.

What it is

datavessel gives AI agents (Claude, Cursor, and any MCP client) read and write access to your entire marketing and ecommerce stack through a single connection. One agent, your whole stack — pull data and take action.

  • Bring your own key (BYOK). Your data, your credentials.
  • Hosted & remote. No local install; Streamable HTTP.
  • 100+ typed tools across 10 connectors, plus 20+ guided workflows.

Connectors

Connector What your agent can do
Google Analytics 4 Traffic, realtime, custom reports, property config
Google Search Console Search performance, top queries/pages, sitemaps, keyword opportunities
Google Ads Campaign, ad-group, keyword & search-term performance
Meta Ads Campaigns, ad sets, ads, account & campaign insights
Shopify Orders, products, customers, inventory, discounts — incl. writes
WooCommerce Orders, products, customers, sales reports, coupons
Shopware Catalog, orders, customers — create/update CMS & landing pages, SEO URLs, products
Slack Channels, history, post messages & DMs
LinkedIn Publish text & article posts
datavessel Reports, alerts, domain checks & utilities

Example: "Find Search Console keywords where we rank well but get few clicks, rewrite those product titles in Shopify, and post the summary to #seo in Slack."

Setup

  1. Create your account — sign up at www.datavessel.io and connect the data sources you want (Google, Shopify, etc.) via OAuth in the dashboard. See datavessel.io/mcp for the full MCP overview.
  2. Add the server to your MCP client using the remote Streamable HTTP URL https://mcp.datavessel.io/mcp.

Authentication is handled automatically over OAuth — there is no API key to copy or paste. datavessel implements the MCP authorization spec: the first time you connect, your client discovers the server's OAuth metadata, registers itself dynamically (DCR), and opens a browser to sign you in. Tokens (with PKCE) are issued and refreshed by the client for you.

Clients with native remote MCP support (Claude, etc.)

Add the remote server by URL — your client runs the OAuth flow on first connect:

{
  "mcpServers": {
    "datavessel": {
      "type": "streamable-http",
      "url": "https://mcp.datavessel.io/mcp"
    }
  }
}

Clients without native remote support (via mcp-remote)

mcp-remote bridges a stdio client to the remote server and performs the same OAuth/DCR handshake — again, no token in the config:

{
  "mcpServers": {
    "datavessel": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.datavessel.io/mcp"]
    }
  }
}

On first connect a browser window opens to authorize datavessel; approve it once and the tools appear. If a connection ever fails with an auth error, clear your client's saved tokens and reconnect — it will re-register automatically.

Pricing

Tier API calls Price
Free 100 / month $0
Professional 1,000 / month $49 / month

All tools are available on both tiers — discovery calls don't count toward the limit.

Links & support

  • 🌐 Website: https://www.datavessel.io
  • 🚀 App / dashboard: https://app.datavessel.io
  • 🔌 MCP details: https://datavessel.io/mcp
  • ✍️ Blog: https://blog.datavessel.io
  • 💬 Support: open an issue or contact us via the website

License

Apache-2.0 — see LICENSE.

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选