Help Scout MCP Server
Provides tools for searching and analyzing Help Scout conversations, including advanced search capabilities, conversation summaries, thread retrieval, inbox monitoring, and content filtering with PII protection.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Help Scout MCP Serverfind recent tickets from customers with billing questions"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP server that gives AI assistants direct access to your Help Scout inboxes, conversations, customers, organizations, threads, and Docs knowledge base. Search tickets, pull customer and account context, inspect articles, spot patterns, and get answers without leaving your editor or chat window.
Built by a Help Scout customer who wanted to give his support team superpowers. If you handle customer conversations in Help Scout and want AI to help you work faster, this is for you.
What You Can Do
Search conversations by keyword, date range, status, tag, email domain, or ticket number
Look up customers by name, advanced query syntax, or exact email address
Explore organizations with direct customer and conversation traversal
Inspect conversation detail with raw ticket metadata, summaries, full threads, attachments, and original source
Pull full thread history into context before drafting a reply
Get conversation summaries with the original customer message and latest staff response
Search and retrieve Docs articles from the separate Help Scout Docs API
Pull Help Scout reports and metadata for company, conversations, Docs, channels, productivity, happiness, users, teams, system users, statuses, routing, and webhooks
Monitor inbox activity across multiple inboxes with a single query
Take action with opt-in writes: draft replies, internal notes, tags, status, assignment, snooze, and more, all off by default
Reduce message payloads with optional message content redaction and scoped inbox access
Related MCP server: kb-intelligence
Quick Start
Claude Desktop & Claude Cowork (Recommended)
One-click install using Desktop Extensions. One install covers both Chat and Cowork sessions in the Claude desktop app.
Download the latest
.mcpbfile from releasesDouble-click to install (or drag into Claude Desktop)
Enter your Help Scout App ID and App Secret in the extension settings; the settings also carry toggles for message redaction and the opt-in write surface
Restart Claude Desktop
If the tools don't show up in a Cowork session, update the desktop app to the latest version and start a fresh session. (Cowork walkthrough)
Optional: add the helpscout-navigator skill so Claude picks the right operation faster. Go to Customize, click + > Add marketplace from GitHub, enter drewburchfield/help-scout-mcp-server, and install helpscout-navigator.
Claude Code
Register the server, then optionally add the helpscout-navigator skill, which teaches Claude to pick the right operation for each query.
claude mcp add helpscout \
--env HELPSCOUT_APP_ID=your-app-id \
--env HELPSCOUT_APP_SECRET=your-app-secret \
-- npx -y help-scout-mcp-serverThen, for the navigation skill:
Run
/plugin marketplace add drewburchfield/help-scout-mcp-serverRun
/plugin install helpscout-navigator
The server alone gives you the tools; the skill also teaches the AI how to use them well.
For Cursor, VS Code, and Other MCP Clients
Add to your MCP client's config file (e.g., claude_desktop_config.json, .cursor/mcp.json):
{
"mcpServers": {
"helpscout": {
"command": "npx",
"args": ["help-scout-mcp-server@2.1.0"],
"env": {
"HELPSCOUT_APP_ID": "your-app-id",
"HELPSCOUT_APP_SECRET": "your-app-secret",
"HELPSCOUT_DOCS_API_KEY": "optional-docs-api-key"
}
}
}
}Docker
docker run -e HELPSCOUT_APP_ID="your-app-id" \
-e HELPSCOUT_APP_SECRET="your-app-secret" \
-e HELPSCOUT_DOCS_API_KEY="optional-docs-api-key" \
drewburchfield/help-scout-mcp-server:2.1.0Getting Your API Credentials
Go to Help Scout > My Apps > Create Private App
Copy your App ID and App Secret
Help Scout uses OAuth2 Client Credentials flow exclusively. Personal Access Tokens are not supported. The app authenticates as the user who created it, with that user's permissions; there is no separate scope selection, which is why the server's own write gating defaults to off.
Help Scout UI | Environment Variable |
App ID |
|
App Secret |
|
Alternative names HELPSCOUT_CLIENT_ID / HELPSCOUT_CLIENT_SECRET are also supported.
Docs knowledge base tools use Help Scout Docs API v1, which is separate from the Mailbox API. Set HELPSCOUT_DOCS_API_KEY only if you want to use listDocs*, searchDocsArticles, getDocsArticle, or redirect tools.
Tools
The server advertises three tools that together reach every supported read operation (55 across the Mailbox and Docs APIs):
Tool | Purpose |
| Find operations by intent ("customer conversation history", "happiness report") |
| Load the full input schemas for the operations you selected |
| Execute one operation: |
This keeps the advertised surface small enough that AI clients don't drown in schemas, while every read capability stays one search away. Operations in the current registry also remain callable by name directly. Tool names removed in the v2.0.0 consolidation (for example comprehensiveConversationSearch, structuredConversationFilter, and searchInboxes) are not; their capabilities live in searchConversations and listAllInboxes.
An optional fourth tool, write_help_scout, appears only when an operator turns writes on. See Write operations (opt-in).
For the MCP compatibility contract and roadmap, see:
Which operation should I use?
Run any of these via read_help_scout:
Task | Operation | Example |
List recent tickets |
| "Show me active tickets from this week" |
Find by keyword |
| "Find conversations about billing errors" |
Look up a ticket number |
| "Show me ticket #42839" |
Complex filters |
| "All @acme.com conversations tagged urgent" |
Browse customers |
| "Show customers named Jane" |
Find a customer by email |
| "Find customer jane@acme.com" |
Inspect a customer profile |
| "Open customer 12345" |
Pull customer contact channels |
| "Show contact details for customer 12345" |
Browse organizations |
| "Show the busiest organizations" |
Inspect an organization |
| "Open organization 456" |
List customers in an organization |
| "Who belongs to organization 456?" |
List organization conversations |
| "Show support history for organization 456" |
Raw conversation detail |
| "Open conversation 12345 with full metadata" |
Quick conversation overview |
| "Summarize this conversation" |
Full message history |
| "Show me the complete thread" |
Inspect inbox fields, folders, or routing |
| "Show routing for inbox 359402" ( |
Search Docs articles |
| "Find knowledge base articles about refunds" |
Retrieve a Docs article |
| "Open Docs article 123" |
Current MCP host time |
| Used for time-relative searches |
Inboxes are auto-discovered when the server connects. AI agents get inbox IDs in their instructions automatically, so no lookup step is needed.
Write operations (opt-in)
A default install is read-only. It advertises the three tools above and nothing else, unchanged from 2.0. Writes exist only after an operator sets a flag.
Flag | What it adds |
| A fourth tool, |
| Two more operations on that same tool: |
Tier 1 covers draft replies, internal notes, status changes, assign and unassign, adding and removing tags, custom field values, snooze and unsnooze, and moving a conversation to another inbox. None of it emails anyone: a draft is saved unsent, and a note is visible to teammates only.
Tier 2 is the only path that reaches a customer, and it needs both flags. Every call to sendReply or publishDraft must also carry confirmation naming the operation and the target:
{
"name": "sendReply",
"arguments": { "conversationId": "12345", "text": "..." },
"confirm": true,
"confirmOperation": "sendReply",
"targetId": "12345"
}Missing, false, or mismatched confirmation is refused before anything reaches Help Scout. Deletes and admin configuration writes are deliberately not exposed, under any flag.
Set "dryRun": true on any write to validate the arguments and see the exact request that would be sent, without contacting Help Scout.
Full rules: write tool contract.
Configuration
Variable | Description | Default |
| App ID from Help Scout My Apps | Required |
| App Secret from Help Scout My Apps | Required |
| Scope searches to a specific inbox | None (all inboxes) |
| Help Scout API endpoint |
|
| Optional Docs API key for knowledge base tools | None |
| Help Scout Docs API endpoint |
|
| Replace message bodies with placeholders |
|
| Advertise | Unset ( |
| Also enable | Unset ( |
| Cache duration for API responses |
|
| Logging verbosity ( |
|
Compatibility
Works with any MCP-compatible client:
Category | Clients |
AI Assistants | Claude Desktop (Chat and Cowork), Goose, and other MCP-enabled assistants |
Code Editors | Cursor, VS Code, Windsurf, Continue.dev |
Command Line | Claude Code, Codex, Gemini CLI, OpenCode |
Custom | Any application implementing the MCP standard |
Security and Privacy
Built with security-minded teams in mind:
Optional message content redaction. Message bodies are included by default. Set
REDACT_MESSAGE_CONTENT=trueto replace conversation and thread bodies with placeholders for lower-context analysis. This is not a compliance boundary and does not remove all customer identifiers.Secure authentication. OAuth2 Client Credentials with automatic token refresh.
Rate limit handling. Automatic retry with exponential backoff on 429 responses.
Scoped access. Optional default inbox configuration limits what the AI can search.
Troubleshooting
Authentication failed? Verify your credentials work with Help Scout directly:
curl -X POST https://api.helpscout.net/v2/oauth2/token \
-d "grant_type=client_credentials&client_id=$HELPSCOUT_APP_ID&client_secret=$HELPSCOUT_APP_SECRET"Empty search results? Common causes:
Forgetting that
searchConversationsis the single search tool: usecontentTerms/subjectTermsfor keyword search, plain filters for listingInbox ID mismatch. Check the IDs from server instructions, not guessed values.
Search terms too narrow. Try broader terms or a longer time range.
Need more detail? Enable debug logging:
LOG_LEVEL=debug npx help-scout-mcp-server@2.1.0Development
git clone https://github.com/drewburchfield/help-scout-mcp-server.git
cd help-scout-mcp-server
npm install && npm run build
npm startnpm test # Run tests
npm run type-check # TypeScript validation
npm run lint # Linting
npm run dev # Development server with auto-reloadContributions welcome. Please ensure tests, type checking, and linting pass before submitting a PR.
Support
License
MIT License - see LICENSE for details.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Alicense-qualityDmaintenanceEnables Claude Desktop to search and query personal document collections (PDF, Word, Markdown, text) using semantic search and conversational AI with full context preservation across exchanges.Last updatedMIT
- Flicense-qualityDmaintenanceEnables Claude Desktop to query a local Zendesk Help Center knowledge graph for semantic search, article retrieval, content gap analysis, and editorial intelligence tasks.Last updated3
- Alicense-qualityDmaintenanceEnables Claude Desktop to perform local-first semantic search, ingest documents, and manage a private knowledge base with hybrid search, PII redaction, and multi-format support.Last updated1MIT
- Flicense-qualityDmaintenanceGives Claude access to your Help Scout knowledge base for listing collections, articles, and searching content.Last updated
Related MCP Connectors
Connect your team's living knowledge base — docs, data, issues, CRM — to Claude and ChatGPT.
Your company's brain for AI agents. Cited, permission-aware knowledge across every system.
Connect Claude to Fathom meeting recordings, transcripts, and summaries
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/drewburchfield/help-scout-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server