Help Scout MCP server for AI agents

Live

OAUTH 2.0

CUSTOMER SUPPORT

Customer Support

Help Scout gives your agent customer support across your inboxes: search and read conversations, send replies and internal notes, tag, assign, and snooze conversations, manage customer profiles, and read happiness and productivity reports.

  • Per-user credentials: each call uses the actual user's token, never a shared bot.
  • Encrypted per-tenant vault: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: pre-call scope check, 90-day SIEM-exportable audit chain.
Help Scout
agent · Acme Q3
Run
What were customers unhappy about last week?
S
helpscout_report_happiness_ratings
128ms
Support agent
12 of 140 ratings last week were Not Good. 7 mention slow replies on billing questions, mostly in the Billing inbox.
Sources: Help Scout happiness ratings, 140 ratings
helpscout
140 ratings
18:29
Message Claude...

Tools your support agent reaches for on Help Scout, scoped per user.

CALL ANY TOOL
100 tools for customer support in Help Scout: search and read conversations and threads, send replies and notes, tag, snooze, and run workflows, manage customers and organizations, use saved replies, and read company, happiness, and productivity reports.
helpscout_conversation_attachment_create
Create conversation attachment
Attach a file, sent as Base64 text, to a thread in a Help Scout conversation. Help Scout scans uploads and blocks malicious files. Returns an empty body on success; the new attachment ID is in the Resource-Id response header. Use conversation_attachment_create to add a file to an existing thread. To attach files while writing, use the attachments input of conversation_reply_create or conversation_note_create.
Parameters
Name
Type
Required
Description
conversation_id
integer
Required
Help Scout conversation ID (the internal `id`, not the conversation `number` shown in the app). Get it from List Conversations or Search Conversations.
data
string
Required
File content encoded as Base64.
file_name
string
Required
File name, with extension.
mime_type
string
Required
MIME type of the file.
thread_id
integer
Required
Thread ID inside the conversation. Get it from List Threads (`_embedded.threads[].id`).
helpscout_conversation_attachment_data_get
Get conversation attachment data
helpscout_conversation_attachment_delete
Delete conversation attachment
helpscout_conversation_custom_fields_update
Update conversation custom fields
helpscout_conversation_customer_thread_create
Create conversation customer thread
helpscout_conversation_reply_create
Create conversation reply
helpscout_conversation_snooze
Conversation snooze
helpscout_conversation_thread_schedule_publish
Publish conversation thread schedule
helpscout_conversation_threads_list
List conversation threads
helpscout_conversation_unsnooze
Conversation unsnooze
helpscout_conversation_update
Update conversation
helpscout_conversations_search
Search conversations
helpscout_customer_address_get
Get customer address
helpscout_customer_chat_handles_delete
Delete customer chat handles
helpscout_customer_create
Create customer
helpscout_customer_phones_list
List customer phones
helpscout_customer_phones_update
Update customer phones
helpscout_customer_social_profiles_create
Create customer social profiles
helpscout_customer_social_profiles_delete
Delete customer social profiles
helpscout_customer_websites_update
Update customer websites
helpscout_inbox_custom_fields_list
List inbox custom fields
helpscout_inbox_routing_get
Get inbox routing
helpscout_organization_properties_list
List organization properties
helpscout_organization_property_value_remove
Remove organization property value
helpscout_organization_property_value_set
Set organization property value
helpscout_rating_get
Get rating
helpscout_report_happiness
Report happiness
helpscout_tag_get
Get tag
helpscout_team_members_list
List team members
helpscout_workflow_run
Run workflow

For more tools, view docs.

Build your Agent
Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.
Python · LlamaIndex
import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Help Scout tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["helpscout"], toolNames: [
    "helpscout_conversations_search",
    "helpscout_conversation_threads_list",
    "helpscout_conversation_note_create"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Find open refund conversations from this week and add a summary note to each" }] });
import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["helpscout"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Find open refund conversations from this week and add a summary note to each" }],
  tools,
});

// Execute the tool call with the user's vaulted Help Scout OAuth token
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");
import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["helpscout"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Find open refund conversations from this week and add a summary note to each" }],
  tools,
});

// Tool call runs with the user's vaulted Help Scout OAuth token
await sk.tools.executeTool(msg.content, "user_123");
import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["helpscout"] }, pageSize: 100,
});

const agent = new Agent({
  name: "support_agent",
  model: "gemini-2.5-pro",
  instruction: "Help Scout tools scoped to this user",
  tools,
});

await agent.run("Find open refund conversations from this week and add a summary note to each");
Try these prompts
Copy any prompt into your agent. Each maps directly to a Help Scout tool. Click to copy, paste into your agent, done.
Conversations
Copy the prompt
Copied
Search for open conversations that mention refund from the last 7 days.
Copy the prompt
Copied
Reply to conversation 98213 with our Refund Policy saved reply.
Copy the prompt
Copied
Add an internal note to the Acme conversation that engineering is on it.
Customers
Copy the prompt
Copied
Look up the customer jane@acme.com and show her recent conversations.
Copy the prompt
Copied
Create a customer for Priya Shah at Globex with her email.
Copy the prompt
Copied
List all conversations from customers in the Initech organization.
Reports
Copy the prompt
Copied
Show last week's happiness report for the Support inbox.
Copy the prompt
Copied
What was our first response time this month?
Copy the prompt
Copied
Show Maria's replies and resolutions for last week.
SEE HOW AUTH WORKS
Each user signs in to Help Scout once, and Scalekit stores and refreshes their tokens. Credentials stay vaulted, every call is scope checked, and every action is logged.
1
Authorize
Your user connects
Help Scout
once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access
Who:
user ‘A’
when:
Once per user
access:
Limited to user
2
Store
Their
Help Scout
token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection
vault:
encrypted
scope:
per-user
tokens:
auto-refreshed
3
Resolve
When your agent calls a
Help Scout
tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs
speed:
~40ms
check:
before every call
seen by:
nobody
4
Audit
Every
Help Scout
tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it
history:
90 days
export:
SIEM-ready
logged:
every call
Test other agents
See the same per-user auth pattern across other customer support connectors.
Support and Ops Teams
Support triage agent
Fetches new Zendesk tickets, classifies them by type and urgency, searches the Notion knowledge base for an answer, and routes what it cannot resolve to Slack. Every call runs on the support agent's own delegated OAuth.
Support and Ops Teams
Support ticket automation agent
Fetches new Zendesk tickets, drafts a reply from Notion knowledge base articles, digests what it cannot answer to Slack, and archives the rest, acting as the support agent rather than a shared API key.
Support and Ops Teams
Freshdesk CSAT agent
Watches Freshdesk for resolved tickets, emails each requester a CSAT survey from Gmail, and writes the score and the verbatim back onto the ticket, every call on the support rep's own delegated OAuth.
Test other agents
See the same per-user auth pattern across other customer support connectors.
SUPPORT
Support triage agent
Classify new Zendesk tickets, search the Notion knowledge base for an answer, and route what it cannot resolve to Slack.
SUPPORT
Support ticket automation (Google ADK)
Fetch, annotate, and archive Zendesk tickets with Notion context, digesting anything it cannot answer to Slack.
SUPPORT
Freshdesk CSAT follow-up agent
Spot resolved Freshdesk tickets, email the CSAT survey from Gmail, and write the score back onto the ticket.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
01.
Shared tokens break per-user analytics
A shared Help Scout token looks fine in a demo. In production every reply and note looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.
// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
Help Scout today. Ten connectors tomorrow.
“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”
Venu Madhav Kattagoni
Head of Engineering / Von
FAQs
Frequently Asked Questions
Does the agent access Help Scout as the user or through a shared token?
As the user. Each user signs in to Help Scout once, and Scalekit stores and refreshes their tokens. Replies and notes the agent writes are attributed to that user in your audit trail, not a shared service account.
Where is the Help Scout OAuth token stored?
In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.
Can I limit what the agent does in Help Scout?
Yes. Filter by tool name in listScopedTools to expose only what you want, for example the conversation and report tools without helpscout_conversation_delete or helpscout_customer_delete, which permanently delete records. Scalekit also enforces scope checks before every API call.
What happens when a user revokes Help Scout access?
The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.
Which Help Scout inboxes can the agent see?
The inboxes the connected user can access in Help Scout. helpscout_inboxes_list returns them, and conversation, folder, saved reply, and workflow tools take an inbox id to work within one of them.
Start in your coding agent
Up and running in one command
Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up
Claude Code REPL
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""helpscout"": {
""url"": ""https://mcp.scalekit.com/helpscout"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.helpscout]
url = ""https://mcp.scalekit.com/helpscout""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""helpscout"": {
""url"": ""https://mcp.scalekit.com/helpscout"",
""type"": ""http""
}
}
}