Context7
Up-to-date docs for AI agents
作者による説明(英語の原文)
Search Help Scout conversations, customers, organizations, threads, and inboxes with AI assistants
この3つを1つのスコアにまとめることはしません。意見、測定、人気はそれぞれ別のものだからです。
このサーバーのやさしい解説はまだ書いていません。以下はレジストリから読み取った事実です。
使っているAIアプリを選んで、設定をコピーしてください。
HELPSCOUT_APP_ID, HELPSCOUT_APP_SECRET, REDACT_MESSAGE_CONTENT「秘密」と表示された値は、あなたのアカウントの鍵です。絶対に人に教えたり、チャットに貼り付けたりしないでください。
必要なもの
どのアプリを使っていますか?
上でアプリを選んでください。選んだアプリを覚えておくので、次からはボタンに「…にインストール」と表示されます。
Claude Desktop → Settings → Developer → Edit Config を開き、claude_desktop_config.json にこれを貼り付けます
{
"mcpServers": {
"help-scout": {
"command": "npx",
"args": [
"-y",
"help-scout-mcp-server"
],
"env": {
"HELPSCOUT_APP_ID": "your-value",
"HELPSCOUT_APP_SECRET": "your-value",
"REDACT_MESSAGE_CONTENT": "your-value"
}
}
}
}ターミナルでこれを実行します
claude mcp add help-scout --env HELPSCOUT_APP_ID=your-value --env HELPSCOUT_APP_SECRET=your-value --env REDACT_MESSAGE_CONTENT=your-value -- npx -y help-scout-mcp-server動かす前に、空欄の値を入力してください。
プロジェクトの .cursor/mcp.json、または ~/.cursor/mcp.json に貼り付けます
{
"mcpServers": {
"help-scout": {
"command": "npx",
"args": [
"-y",
"help-scout-mcp-server"
],
"env": {
"HELPSCOUT_APP_ID": "your-value",
"HELPSCOUT_APP_SECRET": "your-value",
"REDACT_MESSAGE_CONTENT": "your-value"
}
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
プロジェクトの .vscode/mcp.json に貼り付けます
{
"servers": {
"help-scout": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"help-scout-mcp-server"
],
"env": {
"HELPSCOUT_APP_ID": "your-value",
"HELPSCOUT_APP_SECRET": "your-value",
"REDACT_MESSAGE_CONTENT": "your-value"
}
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
これはパソコンで動くサーバーですが、ChatGPTがつなげるのはインターネット上のサーバーだけです。ほかのアプリを選んでください。
選んだアプリは、この端末のCookieに保存されます。アカウントは不要です。
REDACT_MESSAGE_CONTENT envこの設定は、作者のレジストリ登録情報から作成しています。READMEと違う場合は、READMEに従ってください。
パソコンで動くサーバーです。インストールすると、ツール一覧がAIアプリに表示されます。
誰でも見られる情報をチェックしており、コードは読んでいません。当てはまらない項目は数に入れていません。 · 2026年11月7日にチェック
レジストリ名は、リポジトリを所有するGitHubアカウント drewburchfield で確認済みです
このリポジトリはまだGitHubから読み取っていません
このリポジトリはまだGitHubから読み取っていません
これはパソコンで動くため、インターネット上のエンドポイントはありません
パソコンで動き、代わりにローカルの設定を使います
パソコンで動くサーバーです。ツール一覧を読み取れるのは、インターネット上のエンドポイントがある場合だけです
レジストリでこのカテゴリにある有効なすべてのサーバーと比較しています。スターは、公開者がリポジトリの所有者である場合だけ数えます。
当てはまる基本チェック1項目のうち1項目に合格しました。コードは読んでいません。キーやトークンを追加する前に、サーバーがどんなアクセスを求めているかを確認し、必要な権限だけを持つキーを使ってください。
入力が必要なもの:HELPSCOUT_APP_ID, HELPSCOUT_APP_SECRET
あなたのパソコンで動きます。必要なときにAIアプリが起動し、データは作者のサーバーを通りません(サーバー自体がオンラインサービスを呼び出す場合を除きます)。
GitHubリポジトリの最終更新は–、最新バージョン(1.7.0)がレジストリに届いたのは8 か月前です。
Claude Desktop、Claude Code、Cursor、VS CodeなどのMCP対応アプリで使えます。パソコンにNode.jsも必要です。
同じカテゴリには:Context7, Codebase Memory, Exa
同じカテゴリで、ほかの作者が作ったサーバー。スターの多い順。
カードの見方:★ GitHubスターi3つの柱:レビュー · チェック · 利用状況i更新=最新バージョンをレジストリに公開した日i
Up-to-date docs for AI agents
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
作者のリポジトリから書かれたとおりにコピーしたものです。PopNx MCPは内容を確認・推奨していません。HTML、画像、スクリプトは取り除いています。リンクはこのサイトの外へ移動します。
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.
One-click install using Desktop Extensions. One install covers both Chat and Cowork sessions in the Claude desktop app.
.mcpb file from releasesIf 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.
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-server
Then, for the navigation skill:
/plugin marketplace add drewburchfield/help-scout-mcp-server/plugin install helpscout-navigatorThe server alone gives you the tools; the skill also teaches the AI how to use them well.
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 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:2.1.0
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 | HELPSCOUT_APP_ID |
| App Secret | HELPSCOUT_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.
The server advertises three tools that together reach every supported read operation (55 across the Mailbox and Docs APIs):
| Tool | Purpose |
|---|---|
search_help_scout | Find operations by intent ("customer conversation history", "happiness report") |
describe_help_scout | Load the full input schemas for the operations you selected |
read_help_scout | Execute one operation: { "name": "getThreads", "arguments": { ... } } |
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:
Run any of these via read_help_scout:
| Task | Operation | Example |
|---|---|---|
| List recent tickets | searchConversations | "Show me active tickets from this week" |
| Find by keyword | searchConversations (contentTerms) | "Find conversations about billing errors" |
| Look up a ticket number | searchConversations (conversationNumber) | "Show me ticket #42839" |
| Complex filters | searchConversations (emailDomain, tag) | "All @acme.com conversations tagged urgent" |
| Browse customers | listCustomers | "Show customers named Jane" |
| Find a customer by email | searchCustomersByEmail | "Find customer jane@acme.com" |
| Inspect a customer profile | getCustomer | "Open customer 12345" |
| Pull customer contact channels | getCustomerContacts | "Show contact details for customer 12345" |
| Browse organizations | listOrganizations | "Show the busiest organizations" |
| Inspect an organization | getOrganization | "Open organization 456" |
| List customers in an organization | getOrganizationMembers | "Who belongs to organization 456?" |
| List organization conversations | getOrganizationConversations | "Show support history for organization 456" |
| Raw conversation detail | getConversation | "Open conversation 12345 with full metadata" |
| Quick conversation overview | getConversationSummary | "Summarize this conversation" |
| Full message history | getThreads | "Show me the complete thread" |
| Inspect inbox fields, folders, or routing | getInbox (include) | "Show routing for inbox 359402" (include: ["routing"]) |
| Search Docs articles | searchDocsArticles | "Find knowledge base articles about refunds" |
| Retrieve a Docs article | getDocsArticle | "Open Docs article 123" |
| Current MCP host time | getServerTime | 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.
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 |
|---|---|
HELPSCOUT_ENABLE_WRITES=true | A fourth tool, write_help_scout, carrying 11 tier-1 conversation operations |
HELPSCOUT_ENABLE_CUSTOMER_VISIBLE_WRITES=true | Two more operations on that same tool: sendReply and publishDraft |
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.
| Variable | Description | Default |
|---|---|---|
HELPSCOUT_APP_ID | App ID from Help Scout My Apps | Required |
HELPSCOUT_APP_SECRET | App Secret from Help Scout My Apps | Required |
HELPSCOUT_DEFAULT_INBOX_ID | Scope searches to a specific inbox | None (all inboxes) |
HELPSCOUT_BASE_URL | Help Scout API endpoint | https://api.helpscout.net/v2/ |
HELPSCOUT_DOCS_API_KEY | Optional Docs API key for knowledge base tools | None |
HELPSCOUT_DOCS_BASE_URL | Help Scout Docs API endpoint | https://docsapi.helpscout.net/v1/ |
REDACT_MESSAGE_CONTENT | Replace message bodies with placeholders | false |
HELPSCOUT_ENABLE_WRITES | Advertise write_help_scout with the tier-1 conversation writes | Unset (false) |
HELPSCOUT_ENABLE_CUSTOMER_VISIBLE_WRITES | Also enable sendReply and publishDraft, which email the customer | Unset (false) |
CACHE_TTL_SECONDS | Cache duration for API responses | 300 |
LOG_LEVEL | Logging verbosity (error, warn, info, debug) | info |
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 |
Built with security-minded te
冒頭だけを表示しています。続きはリポジトリで読めます