Communication
Help Scout for AI agents.
Managed auth, ready-made tools.
Read and reply to conversations, add notes, change status and find customers in Help Scout on behalf of each of your users.
About Help Scout
With the Help Scout connector, your agent works in each user’s own Help Scout account. It can list conversations in a mailbox, read a thread, reply to the customer, add an internal note, change the status and look up customers, using only the tools your project allows.
Help Scout is a customer support platform with a shared inbox, help center and live chat.
Tools
What your agent can do in Help Scout.
Each tool is a capability the model can call. You decide which ones a project allows, and every call runs with the end user's own Help Scout connection.
-
List mailboxes
Readhelp_scout_list_mailboxesList the mailboxes the user can reach.
-
List conversations
Readhelp_scout_list_conversationsList conversations by mailbox, status or tag.
-
Get a conversation
Readhelp_scout_get_conversationGet a conversation with its full thread.
-
Reply to a customer
Writehelp_scout_create_replySend a reply in a conversation.
-
Add a note
Writehelp_scout_create_noteAdd an internal note to a conversation.
-
Change status
Writehelp_scout_update_conversationSet a conversation to active, pending or closed.
-
Search customers
Readhelp_scout_search_customersFind customers by name or email.
No tool matches that search.
Control
Limits you can set.
You decide what your agent may do in Help Scout, and Agent200 runs every call within those limits.
-
Turn single tools on or off
Let the agent read conversations and add notes, and switch off
help_scout_create_replyso it can never write to a customer. -
Restrict what the agent reaches
Choose the endpoints and scopes a project may use, for example conversations but not customer profiles. A call outside them is refused.
Get started
Connect Help Scout
in three steps.
-
1
Set up the SDK
Add the Agent200 SDK to the codebase you already have and authenticate with your API key. The key covers every connector enabled for the project.
agent.jsConceptual exampleSet up the SDK with the Agent200 API key // One Agent200 API key covers every connector enabled for the project. const agent200 = new Agent200({ apiKey: process.env.AGENT200_API_KEY, }); -
2
Let your user connect Help Scout
Each end user authorizes their own Help Scout account once. Agent200 runs the OAuth flow, handles the callback, stores the tokens and refreshes them.
connect.jsConceptual exampleLet an end user connect their account (managed OAuth) // Each end user authorizes their own Help Scout account, once. const connection = await agent200 .user("user_123") .connect("help_scout"); if (connection.authorizationUrl) { // Show this link to your user; Agent200 handles the rest. console.log(connection.authorizationUrl); } -
3
Run with the Help Scout tools
Name the user, the model and the tools. The model decides which Help Scout tools to call, and Agent200 executes them with that user's connection.
run.jsConceptual exampleRun a request with the connector's tools const result = await agent200 .user("user_123") .run({ model: "openai/gpt-5.6-sol", input: "Show open conversations in the support mailbox", tools: ["help_scout"], }); console.log(result.output);
Access
Sign-in and permissions.
-
Who signs in
Each of your users, once, on Help Scout's own sign-in page. You never see or store their Help Scout password.
-
What access is requested
The access the connection needs, such as reading and updating conversations and customers, listed on Help Scout's authorization screen. Users can remove the app later from their Help Scout account settings.
For agents
Instructions for AI agents.
Using a coding agent? Paste this brief into it, or give it the address of this page. It describes the Help Scout connector and how to use it.
Connector: Help Scout, through Agent200. In code: "help_scout". What it does: Read and reply to conversations, add notes, change status and find customers in Help Scout on behalf of each of your users. Page: https://www.agent200.com/connectors/help-scout/ 1. Get an Agent200 API key. If the developer has none, send them to https://agent200.com/platform/apikeys/ and ask them to choose "Create an API key". Read the key from the AGENT200_API_KEY environment variable. Never ask for it in chat, and never write it into code, prompts or logs. 2. Sign-in is managed OAuth. Each end user approves access once, on Help Scout's own page, through the authorization link Agent200 returns. Never ask a user for a Help Scout password or token in chat. 3. Give every request a stable id for the end user. Agent200 uses only that user's own connection. 4. Read tools: help_scout_list_mailboxes, help_scout_list_conversations, help_scout_get_conversation, help_scout_search_customers. Write tools: help_scout_create_reply, help_scout_create_note, help_scout_update_conversation. Name "help_scout" in the tools of a request; the model decides which tool to call. 5. Stay within the project's settings. If a tool is turned off or a call is refused, tell the user. Do not work around it. 6. Before a write, confirm with the user, unless they asked for that exact change. 7. For setup with a specific framework, follow its guide: https://www.agent200.com/connectors/help-scout/framework/claude/ https://www.agent200.com/connectors/help-scout/framework/chatgpt/ https://www.agent200.com/connectors/help-scout/framework/claude-code/ https://www.agent200.com/connectors/help-scout/framework/muse/ https://www.agent200.com/connectors/help-scout/framework/grok-bot/ https://www.agent200.com/connectors/help-scout/framework/openai-dots/ https://www.agent200.com/connectors/help-scout/framework/claude-duet/ https://www.agent200.com/connectors/help-scout/framework/hermes-agent/ https://www.agent200.com/connectors/help-scout/framework/openclaw/ The code on the connector page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/
This page is also available as Markdown, for agents and LLMs: /connectors/help-scout.md
Guides
Use Help Scout with the AI you build on.
Step-by-step setup for Help Scout with a specific model, assistant or agent framework.
-
Help Scout + Claude
How to connect Help Scout to Claude
-
Help Scout + ChatGPT
How to connect Help Scout to ChatGPT
-
Help Scout + Claude Code
How to connect Help Scout to Claude Code
-
Help Scout + Muse
How to connect Help Scout to Muse
-
Help Scout + Grok Bot
How to connect Help Scout to Grok Bot
-
Help Scout + OpenAI Dots
How to connect Help Scout to OpenAI Dots
-
Help Scout + Claude Duet
How to connect Help Scout to Claude Duet
-
Help Scout + Hermes Agent
How to connect Help Scout to Hermes Agent
-
Help Scout + OpenClaw
How to connect Help Scout to OpenClaw
FAQ
Help Scout and Agent200, answered.
Who handles the Help Scout OAuth flow and the tokens?
Agent200. It runs the authorization, handles the callback on its own domain, stores the tokens and refreshes them. You do not build or maintain an OAuth integration for Help Scout.
Does my agent act as the end user?
Within what that user authorized, yes. Every request names an end user, and Agent200 uses only that user's Help Scout connection, never another user's. It cannot reach anything the user or Help Scout has not authorized.
Can I limit what my agent can do in Help Scout?
Yes. You choose which services, endpoints and authorization scopes are allowed in your Agent200 configuration, and the agent works only within them.