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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
E2B
Using MCP to run code via e2b.