Help Scout MCP Server - Connect Claude and other AI assistants to your Help Scout data with enterprise-grade security and advanced search capabilities.
Note: This is a fork of the original help-scout-mcp-server by Drew Burchfield.
- π What's New
- β‘ Quick Start
- π API Credentials
- π οΈ Tools & Capabilities
- βοΈ Configuration
- π Troubleshooting
- π€ Contributing
- π Full Docs API Integration: Complete support for Help Scout Docs API
- Browse and search documentation sites, collections, categories, and articles
- Read full article content with PII protection
- Update articles, collections, and categories (with safety controls)
- π Complete Reports API: All Help Scout Reports endpoints implemented
- Conversation reports (chat, email, phone) with detailed metrics
- User/team performance reports with productivity analytics
- Company-wide reports with customer and team insights
- Happiness reports with satisfaction scores and feedback
- Docs analytics with article views and visitor metrics
- π― DXT Extension: One-click installation for Claude Desktop
- π§ Clear Environment Variables:
HELPSCOUT_CLIENT_IDandHELPSCOUT_CLIENT_SECRET - β‘ Connection Pooling: Improved performance with HTTP connection reuse
- π‘οΈ Enhanced Security: Comprehensive input validation and API constraints
- π Dependency Injection: Cleaner architecture with ServiceContainer
- π§ͺ Comprehensive Testing: 69%+ branch coverage with reliable tests
- Node.js 18+ (for command line usage)
- Help Scout Account with API access
- OAuth2 App or Personal Access Token from Help Scout
- Claude Desktop (for DXT installation) or any MCP-compatible client
Note: The DXT extension includes Node.js, so no local installation needed for Claude Desktop users.
Easiest setup using DXT (Desktop Extensions) - no configuration needed:
- Download the latest
.dxtfile from releases - Double-click to install in Claude Desktop
- Enter your Help Scout OAuth2 Client ID and Client Secret when prompted
- Start using immediately!
{
"mcpServers": {
"helpscout": {
"command": "npx",
"args": ["help-scout-mcp-server"],
"env": {
"HELPSCOUT_CLIENT_ID": "your-client-id",
"HELPSCOUT_CLIENT_SECRET": "your-client-secret"
}
}
}
}docker run -e HELPSCOUT_CLIENT_ID="your-client-id" \
-e HELPSCOUT_CLIENT_SECRET="your-client-secret" \
zackkatz/help-scout-mcp-serverHELPSCOUT_CLIENT_ID="your-client-id" \
HELPSCOUT_CLIENT_SECRET="your-client-secret" \
npx help-scout-mcp-serverThis method is recommended for production use and provides automatic token refresh.
Why Client Credentials? MCP servers are backend applications that run without user interaction. We use the Client Credentials flow (not Authorization Code flow) because:
- β No browser or user login required
- β Perfect for server-to-server authentication
- β Automatic token refresh
- β Works with Claude Desktop, Continue.dev, etc.
- Log in to your Help Scout account
- Click your profile icon (top right) β My Apps
- Click Create My App
- Fill out the form:
- App Name: e.g., "Help Scout MCP Server"
- Redirection URL: Use
https://example.com(required field but not used for server apps) - Description: Optional description of your integration
Select the scopes your app needs:
- β Mailbox - Read conversations, threads, and mailbox data
- β Customers - Access customer information
- β Reports - Access analytics and reporting (Plus/Pro plans only)
- β Users - Read user information
- β Webhooks - If you need webhook functionality
Note: Only select the scopes you actually need for security best practices.
- Click Create Application
- You'll see your credentials:
- App ID (this is your Client ID)
- App Secret (this is your Client Secret)
β οΈ Important: Copy these immediately! The App Secret is only shown once.
Set these environment variables:
export HELPSCOUT_CLIENT_ID="your-app-id-here"
export HELPSCOUT_CLIENT_SECRET="your-app-secret-here"Or add to your .env file:
HELPSCOUT_CLIENT_ID=your-app-id-here
HELPSCOUT_CLIENT_SECRET=your-app-secret-here# Test with environment variables
HELPSCOUT_CLIENT_ID="your-app-id" \
HELPSCOUT_CLIENT_SECRET="your-app-secret" \
npx help-scout-mcp-server
# Or if using .env file
npx help-scout-mcp-server- "Unknown URL" for Reports: Ensure your account has a Plus/Pro plan
- Authentication Failed: Double-check your Client ID and Secret
- Missing Scopes: Go back to My Apps and edit your app's permissions
- Token Expired: The server handles refresh automatically
For quick testing or personal use only. These tokens don't auto-refresh.
- Go to Help Scout β Your Profile β Authentication
- Under API Keys, click Generate an API Key
- Give it a memorable label (e.g., "MCP Server")
- Copy the generated token
- Use in configuration:
HELPSCOUT_API_KEY=Bearer your-token-here
- Go to Help Scout Docs Settings
- Generate a Docs API Key
- Use in configuration:
HELPSCOUT_DOCS_API_KEY=your-docs-api-key
Important Notes:
- The Docs API key is separate from your main Help Scout API credentials
- Ensure Help Scout Docs is enabled for your account
- You must have at least one Docs site created to access documentation
- Reports API (for analytics) requires Plus/Pro plan
- π Advanced Search: Multi-status conversation search, content filtering, boolean queries
- π Smart Analysis: Conversation summaries, thread retrieval, inbox monitoring
- π Docs Integration: Full Help Scout Docs API support for articles, collections, and categories
- π Comprehensive Reports: All Help Scout Reports API endpoints - chat, email, phone, user, company, happiness, and docs analytics
- π Enterprise Security: PII redaction, secure token handling, comprehensive audit logs
- β‘ High Performance: Built-in caching, rate limiting, automatic retry logic
- π― Easy Integration: Works with Claude Desktop, Cursor, Continue.dev, and more
| Tool | Description | Best For |
|---|---|---|
searchConversations |
β For Listing - Can omit query to list ALL recent conversations | "Show me recent tickets", browsing conversations |
comprehensiveConversationSearch |
π For Content Search - Requires search terms, searches all statuses | "Find tickets about billing issues", content-based searches |
advancedConversationSearch |
Boolean queries with content/subject/email filtering | Complex search requirements |
searchInboxes |
Find inboxes by name | Discovering available inboxes |
| Tool | Description | Use Case |
|---|---|---|
getConversationSummary |
Customer message + latest staff reply summary | Quick conversation overview |
getThreads |
Complete conversation message history | Full context analysis |
getServerTime |
Current server timestamp | Time-relative searches |
| Tool | Description | Use Case |
|---|---|---|
listDocsSites |
List all documentation sites with NLP filtering | Discover available sites |
listDocsCollections |
List collections with site NLP resolution | Browse documentation structure |
listDocsCategories |
List categories in a collection | Navigate collection organization |
listDocsArticlesByCollection |
List articles in a collection (sort by popularity) | Find articles by collection |
listDocsArticlesByCategory |
List articles in a category (sort by popularity) | Find articles by category |
getDocsArticle |
Get full article content | Read complete documentation |
updateDocsArticle |
Update article content/properties | Modify documentation |
updateDocsCollection |
Update collection properties | Manage collections |
updateDocsCategory |
Update category properties | Manage categories |
getTopDocsArticles |
Get most popular articles by views with NLP support | Find most-read documentation |
listAllDocsCollections |
List all available collections across sites | Discover available content |
getSiteCollections |
Get collections for a specific site using NLP | Find site-specific collections |
| Tool | Description | Requirements |
|---|---|---|
getTopArticles |
Get top most viewed docs articles sorted by popularity | Works with all plans |
getChatReport |
Chat conversation analytics with volume, response times, and resolution metrics | Plus/Pro plan required |
getEmailReport |
Email conversation analytics with volume, response times, and resolution metrics | Plus/Pro plan required |
getPhoneReport |
Phone conversation analytics with call volume and duration metrics | Plus/Pro plan required |
getUserReport |
User/team performance report with productivity metrics and happiness scores | Plus/Pro plan required |
getCompanyReport |
Company-wide analytics with customer volume and team performance | Plus/Pro plan required |
getHappinessReport |
Customer satisfaction scores and feedback analysis | Plus/Pro plan required |
getDocsReport |
Comprehensive docs analytics report with article views and visitor metrics | Plus/Pro plan required |
helpscout://inboxes- List all accessible inboxeshelpscout://conversations- Search conversations with filtershelpscout://threads- Get thread messages for a conversationhelpscout://clock- Current server timestamp
helpscout-docs://sites- List all documentation siteshelpscout-docs://collections- List collections with filteringhelpscout-docs://categories- List categories in a collectionhelpscout-docs://articles- Get articles with full content
π Key Distinction: Use
searchConversations(without query) for listing conversations, usecomprehensiveConversationSearch(with search terms) for finding specific content.
// Best for "show me recent tickets" - omit query parameter
searchConversations({
status: "active",
limit: 25,
sort: "createdAt",
order: "desc"
})// Best for "find tickets about X" - requires search terms
comprehensiveConversationSearch({
searchTerms: ["urgent", "billing"],
timeframeDays: 60,
inboxId: "256809"
})// Search in message bodies and subjects
comprehensiveConversationSearch({
searchTerms: ["refund", "cancellation"],
searchIn: ["both"],
timeframeDays: 30
})
// Customer organization search
advancedConversationSearch({
emailDomain: "company.com",
contentTerms: ["integration", "API"],
status: "active"
})// Advanced query syntax support
searchConversations({
query: "(body:\"urgent\" OR subject:\"emergency\") AND tag:\"escalated\"",
status: "active"
})// List all documentation sites
listDocsSites({
page: 1
})
// Get articles in a collection
listDocsArticlesByCollection({
collectionId: "123456",
status: "published",
sort: "popularity"
})
// Get full article content
getDocsArticle({
articleId: "789012"
})
// Update an article
updateDocsArticle({
articleId: "789012",
name: "Updated Article Title",
text: "<p>New article content</p>"
})// Get email conversation report with comparison
getEmailReport({
start: "2024-01-01T00:00:00Z",
end: "2024-01-31T23:59:59Z",
previousStart: "2023-12-01T00:00:00Z",
previousEnd: "2023-12-31T23:59:59Z",
mailboxes: ["123456"],
viewBy: "week"
})
// Get user performance report
getUserReport({
start: "2024-01-01T00:00:00Z",
end: "2024-01-31T23:59:59Z",
user: "789012",
types: ["email", "chat"],
officeHours: true
})
// Get happiness ratings with filters
getHappinessReport({
start: "2024-01-01T00:00:00Z",
end: "2024-01-31T23:59:59Z",
rating: ["great", "okay"],
mailboxes: ["123456"],
viewBy: "day"
})
// Get company-wide analytics
getCompanyReport({
start: "2024-01-01T00:00:00Z",
end: "2024-01-31T23:59:59Z",
viewBy: "month"
})| Variable | Description | Default |
|---|---|---|
HELPSCOUT_CLIENT_ID |
OAuth2 Client ID from Help Scout My Apps | Required |
HELPSCOUT_CLIENT_SECRET |
OAuth2 Client Secret from Help Scout My Apps | Required |
HELPSCOUT_API_KEY |
Personal Access Token (format: Bearer token) |
Alternative to OAuth2 |
HELPSCOUT_BASE_URL |
Help Scout API endpoint | https://api.helpscout.net/v2/ |
ALLOW_PII |
Include message content in responses | false |
CACHE_TTL_SECONDS |
Cache duration for API responses | 300 |
LOG_LEVEL |
Logging verbosity (error, warn, info, debug) |
info |
HELPSCOUT_DOCS_API_KEY |
API key for Help Scout Docs access | Required for Docs |
HELPSCOUT_DOCS_BASE_URL |
Help Scout Docs API endpoint | https://docsapi.helpscout.net/v1/ |
HELPSCOUT_DEFAULT_DOCS_COLLECTION_ID |
Default collection ID for queries | Optional |
HELPSCOUT_DEFAULT_DOCS_SITE_ID |
Default Docs site ID for queries | Optional |
HELPSCOUT_ALLOW_DOCS_DELETE |
Enable Docs deletion operations | false |
The MCP server includes intelligent natural language processing for Help Scout Docs sites and collections:
// These all work to find GravityKit articles:
getTopDocsArticles({ query: "GravityKit docs" })
getTopDocsArticles({ query: "top GravityKit articles" })
getTopDocsArticles({ query: "What are the most popular GravityKit help articles?" })// Natural language site queries:
listDocsCollections({ query: "GravityKit" }) // Find GravityKit site
getSiteCollections({ query: "TrustedLogin site" }) // Get TrustedLogin collections
listDocsSites({ query: "gravity" }) // Find sites matching "gravity"The system matches sites and collections using:
- Direct name match - Exact site/collection name (100% confidence)
- Company/Site name match - Company name like "GravityKit" (80-90% confidence)
- Subdomain match - Matches subdomain patterns (70-80% confidence)
- CNAME match - Custom domain matching (70% confidence)
- Partial word match - Intelligent fuzzy matching (variable confidence)
Set default site and collection for queries without specific context:
export HELPSCOUT_DEFAULT_DOCS_SITE_ID="your-site-id"
export HELPSCOUT_DEFAULT_DOCS_COLLECTION_ID="your-collection-id"- Use
listDocsSitesto see all Docs sites (with optional NLP filtering) - Use
listAllDocsCollectionsto see all available collections across sites - Use
getSiteCollectionsto get collections for a specific site using NLP - Sites and collections are automatically cached for performance
Works with any Model Context Protocol (MCP) compatible client:
- π₯οΈ Desktop Applications: Claude Desktop, AI coding assistants, and other MCP-enabled desktop apps
- π Code Editors: VS Code extensions, Cursor, and other editors with MCP support
- π Custom Integrations: Any application implementing the MCP standard
- π οΈ Development Tools: Command-line MCP clients and custom automation scripts
Primary Platform: Claude Desktop with full DXT and manual configuration support
Since this server follows the MCP standard, it automatically works with any current or future MCP-compatible client.
- π PII Protection: Message content redacted by default
- π‘οΈ Secure Authentication: OAuth2 Client Credentials or Personal Access Token with automatic refresh
- π Audit Logging: Comprehensive request tracking and error logging
- β‘ Rate Limiting: Built-in retry logic with exponential backoff
- π’ Enterprise Ready: SOC2 compliant deployment options
- Fixed Reports API response unwrapping for
getCompanyReport,getEmailReport,getChatReport,getPhoneReport,getUserReport - Fixed
getHappinessReportendpoint URL to use/v2/reports/happiness/overall - Fixed
listDocsSitesresponse structure to properly handle sites array - Added Reports API client for proper response handling
- Improved error messages for Reports API endpoints
# Quick start
git clone https://github.com/zackkatz/help-scout-mcp-server.git
cd help-scout-mcp-server
npm install && npm run build
# Create .env file with your credentials (OAuth2)
echo "HELPSCOUT_CLIENT_ID=your-client-id" > .env
echo "HELPSCOUT_CLIENT_SECRET=your-client-secret" >> .env
# Start the server
npm startAuthentication Failed
# Verify your credentials
echo $HELPSCOUT_CLIENT_ID
echo $HELPSCOUT_CLIENT_SECRET
# Test with curl
curl -X POST https://api.helpscout.net/v2/oauth2/token \
-d "grant_type=client_credentials&client_id=$HELPSCOUT_CLIENT_ID&client_secret=$HELPSCOUT_CLIENT_SECRET"Connection Timeouts
- Check your network connection to
api.helpscout.net - Verify no firewall blocking HTTPS traffic
- Consider increasing
HTTP_SOCKET_TIMEOUTenvironment variable
Rate Limiting
- The server automatically handles rate limits with exponential backoff
- Reduce concurrent requests if you see frequent 429 errors
- Monitor logs for retry patterns
Empty Search Results
- Wrong tool choice: Use
searchConversations(no query) for listing,comprehensiveConversationSearchfor content search - Empty search terms: Don't use empty strings
[""]with comprehensiveConversationSearch - Verify inbox permissions with your API credentials
- Check conversation exists and you have access
- Try broader search terms or different time ranges
If you're getting "Unknown URL" errors when accessing reports:
1. Verify Your Plan
- Reports API requires a Plus or Pro plan
- Standard plan users can purchase Reports as an add-on
- Check your plan: Help Scout β Manage β Account β Billing
2. Check OAuth App Permissions
- Go to My Apps β Edit your app
- Ensure Reports scope is selected
- Save and regenerate credentials if needed
3. Feature Availability
- Happiness Reports: Requires happiness ratings to be enabled
- Go to: Manage β Company β Email β Happiness Ratings
- Chat/Phone Reports: Only available if these channels are enabled
- Docs Reports: Requires Help Scout Docs to be enabled
4. API Response Debugging
# Enable debug logging to see actual API responses
LOG_LEVEL=debug npx help-scout-mcp-server5. Test with Personal Access Token Sometimes OAuth apps have permission issues. Test with a Personal Access Token:
HELPSCOUT_API_KEY="Bearer your-personal-token" npx help-scout-mcp-serverEnable debug logging to troubleshoot issues:
LOG_LEVEL=debug npx help-scout-mcp-serverIf you're still having issues:
- Check existing issues
- Enable debug logging and share relevant logs
- Include your configuration (without credentials!)
We welcome contributions! Here's how to get started:
git clone https://github.com/zackkatz/help-scout-mcp-server.git
cd help-scout-mcp-server
npm install# Run tests
npm test
# Type checking
npm run type-check
# Linting
npm run lint
# Build for development
npm run build
# Start development server
npm run dev- β
All tests pass (
npm test) - β
Type checking passes (
npm run type-check) - β
Linting passes (
npm run lint) - β Add tests for new features
- β Update documentation if needed
When reporting bugs, please include:
- Help Scout MCP Server version
- Node.js version
- Authentication method (OAuth2/Personal Access Token)
- Error messages and logs
- Steps to reproduce
We'd love to hear your ideas! Please open an issue describing:
- The problem you're trying to solve
- Your proposed solution
- Any alternative approaches you've considered
- Issues: GitHub Issues
- Discussions: GitHub Discussions
- NPM Package: help-scout-mcp-server
MIT License - see LICENSE file for details.
Need help? Open an issue or check our documentation.