Vitally MCP Server
Provides access to Vitally customer success platform data, enabling users to search accounts and users, view health scores, manage conversations and tasks, and create notes through natural language interactions.
README
<!-- Copyright (c) 2024 John Jung -->
Vitally MCP Server
An MCP (Model Context Protocol) server that provides access to Vitally customer data via the Vitally API.
Features
- List customer accounts as resources
- Read account details
- Search for users by email or external ID
- Find accounts by name
- Query account health scores
- View account conversations and tasks
- Create notes for accounts
- Search through available tools
- Demo mode with mock data when no API key is provided
Setup for running locally
-
Install dependencies:
npm install -
Create a
.envfile in the root directory with the following:# Vitally API Configuration VITALLY_API_SUBDOMAIN=nylas # Your Vitally subdomain VITALLY_API_KEY=your_api_key_here # Your Vitally API key VITALLY_DATA_CENTER=US # or EU depending on your data center -
Build the project:
npm run build
Note: If you don't have a Vitally API key yet, the server will run in demo mode with mock data.
Getting your Vitally API Key
- Navigate to your Vitally account
- Go to Settings (⚙️) > Integrations > (new page) Vitally REST API
- Toggle the switch to enable the integration
- Copy the API Key (Secret Token)
Usage
There are three ways to use this MCP server:
Using the MCP Inspector
Run the MCP Inspector to test and debug the server:
npm run inspector
This will open the MCP Inspector interface where you can interact with your server.
Running the MCP locally
-
First, find your Claude Desktop configuration file:
- On macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - On Windows:
%APPDATA%\Claude\claude_desktop_config.json
- On macOS:
-
Edit the config file to add the Vitally MCP server:
{ "mcpServers": { "vitally": { "command": "node", "args": ["--experimental-modules", "--experimental-specifier-resolution=node", "/Users/johnjung/nylas/vitally/vitally/build/index.js"] } } } -
Restart Claude Desktop and you'll be able to use the Vitally MCP server.
Running the MCP via Docker
-
Edit the config file to add the Vitally MCP server from the GitHub package repository:
{ "mcpServers": { "vitally": { "command": "docker", "args": [ "run", "--rm", "-i", "-e", "VITALLY_API_SUBDOMAIN", "-e", "VITALLY_API_KEY", "-e", "VITALLY_DATA_CENTER", "ghcr.io/fiscaltec/vitally-mcp" ], "env": { "VITALLY_API_SUBDOMAIN": "VITALLY_API_SUBDOMAIN", "VITALLY_API_KEY": "VITALLY_API_KEY", "VITALLY_DATA_CENTER": "VITALLY_DATA_CENTER" } } } } -
Restart Claude Desktop and you'll be able to use the Vitally MCP server.
Available Tools
Tool Discovery
search_tools- Search for available tools by keyword
Account Management
search_accounts- Search for accounts using multiple criteria (name, externalId)find_account_by_name- Find accounts by their name (partial matching supported)refresh_accounts- Refresh the cached list of accountsget_account_health- Get health scores for a specific account
User Management
search_users- Search for users by email, external ID, or email subdomain
Communication & Tasks
get_account_conversations- Get recent conversations for an accountget_account_tasks- Get tasks for an account (can filter by status)create_account_note- Create a new note for an account
Example Questions to Ask
When connected to an MCP client like Claude, you can ask questions such as:
- "List all our customers"
- "Find accounts with 'Acme' in their name"
- "What's the health score for account X?"
- "Find user with email example@company.com"
- "Show me details about customer Y"
- "Get recent conversations for account Z"
- "What tasks are open for account A?"
- "Add a note to account B about our recent call"
- "What tools can I use for account management?"
Troubleshooting
- If you encounter JSON parsing errors, ensure you've removed all console.log statements from the code
- Make sure your
.envfile contains the correct API credentials - Check that you've built the project (
npm run build) after making changes - Verify the path in claude_desktop_config.json is absolute and correct for your system
- If you don't have a valid API key, the server will run in demo mode with mock data
Attibution
As mentioned previously and in other files, this MCP has been created with original code from John Jung and containerised by Dan Searle.
All rightts go to John Jung.
Notes
- This has only been tested with Claude Desktop as of this moment however, is likely to woth with others but the configuration may not translate and is untested.
- Please raise an issue in either this repository, or the original if you find an issue or if you would like an improvement.
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。