广告合作
MCP.so
登录

Onboard MCP Server

@viaonboard

代码仓库

基本信息

分类

其他

传输方式

stdio

作者

viaonboard

提交者

Matthew Majewski

关于 Onboard MCP Server

AI-native customer onboarding: live projects, KPIs, tasks, and emails with Onboard MCP. Connect Onboard to Claude or any MCP-compatible AI client to seamlessly surface blocked tasks, draft customer emails, monitor KPIs, and take action—right from your AI workspace. Access 27+ pur

#onboarding#project-management#customer-success#automation#productivity#ai#claude#saas#workflows#integrations#task-management#email-automation#kpis#customer-experience#risk-management#feedback#rest-api

Onboard MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "onboard": {
      "type": "sse",
      "url": "https://rest.onboard.io/mcp/sse",
      "oauth": {
        "clientId": "<YOUR_OAUTH_CLIENT_ID>",
        "scopes": [
          "openid",
          "profile",
          "email"
        ],
        "resource": "https://rest.onboard.io/mcp/"
      }
    },
    "onboard-api-token": {
      "type": "sse",
      "url": "https://rest.onboard.io/mcp/sse",
      "headers": {
        "X-Onboard-Api-Token": "<YOUR_ONBOARD_API_TOKEN>"
      }
    }
  }
}

Onboard MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

点击上方按钮,直接连接服务器端点实时获取工具列表。

概览

What is Onboard MCP?

Onboard MCP is an MCP server that connects AI assistants to an Onboard workspace, enabling teams to read, reason about, and act on live customer onboarding data with human approval before any writes. It is designed for customer onboarding teams juggling multiple projects, customers, and stakeholders.

How to use Onboard MCP?

Connect any MCP-compatible client (e.g., Claude Desktop, Cursor, Amazon Quick) to an Onboard workspace using OAuth 2.0 (hosted) or an API token. Once connected, ask natural language questions or invoke tools — all write operations default to preview mode and require confirmation. A valid Onboard subscription is required.

Key features of Onboard MCP

  • Read live project data, tasks, KPIs, and inbox
  • Generate structured risk reviews with owners and next steps
  • Draft data-rich follow-up emails from project snapshots
  • Detect blocked tasks and assign owners in one step
  • Surface KPI dashboards for launch rates and velocity trends
  • Launch project templates and create tasks with preview-first safety
  • 27+ purpose-built tools covering the full onboarding lifecycle
  • Custom automations via read_api_request and write_api_request tools

Use cases of Onboard MCP

  • Morning digest: ask “what are my active projects and what’s blocked?” for a structured portfolio summary
  • Risk reviews: run a weekly risk scan for any customer or project with prioritized mitigations
  • Customer follow-ups: draft data-rich emails using live task progress, overdue items, and key contacts
  • Quick task management: update status, assign owners, and post comments from a chat interface
  • KPI reporting: pull launch rates, velocity trends, and overdue task metrics for exec updates or QBR prep

常见问题

1

Is Onboard MCP safe to use with my project data?

Yes. All write operations default to preview mode — nothing is written to your workspace until you confirm. This applies to task updates, comments, and project launches.

2

How do I authenticate with Onboard MCP?

You can authenticate using hosted OAuth 2.0 or an API token. The server supports both methods, and you connect via any MCP-compatible client.

3

What do I need to use Onboard MCP?

You need an active Onboard subscription (visit onboard.io) and an MCP-compatible client such as Claude Desktop, Cursor, or Amazon Quick.

4

Which data does Onboard MCP access?

It reads your live Onboard workspace data: projects, tasks, KPIs, and inbox. All writes require your explicit approval unless you use the `write_api_request` tool for custom automations.

5

Can I send feedback about the MCP experience?

Yes. Use the `give_us_feedback` tool to report bugs, request features, or share notes — it emails support@onboard.io with your message and contact email.

评论

其他 分类下的更多 MCP 服务器

Blender

ahujasid

Open-source MCP to use Blender with any LLM

23.6K

Handl

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

Activepieces

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

23.2K

Yuppsy

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code

N

Next Generation Movers: free moving quotes (remote MCP)

Next Generation Movers

Free moving quotes for AI agents from Next Generation Movers, a licensed interstate mover (USDOT 3764697). US long-distance nationwide and local DC/MD/VA. Indicative ballpark price and booking options; optional $0.01 x40

广告合作