プロトタイプ · プレビュー版:公式レジストリのすべてのサーバーを掲載し、30分ごとに同期しています。レビューとアカウント機能は今後のステップで始まります。
PopNx MCPAIを使う人のためのMCPサーバー · やさしい言葉で解説

HubSpot

作者:ohnebenバージョン 2.0.1i★ –iパソコンで動く
レジストリ名io.github.ohneben/hubspot-mcp

インストール

概要

作者による説明(英語の原文)

HubSpot API: 1,000+ endpoints as safety-categorized, hub- and plan-aware MCP tools, stdio or HTTP.

PopNx MCPの3つの柱

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。

できること

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。

  • 接続方法: パソコンで動く
  • トランスポート: stdio
  • カテゴリ: マーケティング・SNS
  • 入力が必要なもの:MCP_TRANSPORT, HUBSPOT_ACCESS_TOKEN, MCP_AUTH_TOKEN

インストール

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。

インストールの前に

  • 基本チェック:1項目中1項目に合格
  • あなたのパソコンで、あなたのユーザーと同じ権限(ファイル、ネットワーク、アプリ)で動きます。
  • 自分で入力するもの: MCP_TRANSPORT, HUBSPOT_ACCESS_TOKEN, HUBSPOT_BASE_URL, HUBSPOT_TOOL_MODE, HUBSPOT_READ_ONLY, HUBSPOT_CAPABILITY_CHECK, MCP_AUTH_TOKEN

「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

  • DockerDockerのインストール

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": {
    "hubspot": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "MCP_TRANSPORT",
        "-e",
        "HUBSPOT_ACCESS_TOKEN",
        "-e",
        "HUBSPOT_BASE_URL",
        "-e",
        "HUBSPOT_TOOL_MODE",
        "-e",
        "HUBSPOT_READ_ONLY",
        "-e",
        "HUBSPOT_CAPABILITY_CHECK",
        "-e",
        "MCP_AUTH_TOKEN",
        "ghcr.io/ohneben/hubspot-mcp:2.0.1"
      ],
      "env": {
        "MCP_TRANSPORT": "your-value",
        "HUBSPOT_ACCESS_TOKEN": "your-value",
        "HUBSPOT_BASE_URL": "your-value",
        "HUBSPOT_TOOL_MODE": "your-value",
        "HUBSPOT_READ_ONLY": "your-value",
        "HUBSPOT_CAPABILITY_CHECK": "your-value",
        "MCP_AUTH_TOKEN": "your-value"
      }
    }
  }
}

ターミナルでこれを実行します

claude mcp add hubspot --env MCP_TRANSPORT=your-value --env HUBSPOT_ACCESS_TOKEN=your-value --env HUBSPOT_BASE_URL=your-value --env HUBSPOT_TOOL_MODE=your-value --env HUBSPOT_READ_ONLY=your-value --env HUBSPOT_CAPABILITY_CHECK=your-value --env MCP_AUTH_TOKEN=your-value -- docker run -i --rm -e MCP_TRANSPORT -e HUBSPOT_ACCESS_TOKEN -e HUBSPOT_BASE_URL -e HUBSPOT_TOOL_MODE -e HUBSPOT_READ_ONLY -e HUBSPOT_CAPABILITY_CHECK -e MCP_AUTH_TOKEN ghcr.io/ohneben/hubspot-mcp:2.0.1

動かす前に、空欄の値を入力してください。

Cursorで開く

または、設定を自分でコピーする

プロジェクトの .cursor/mcp.json、または ~/.cursor/mcp.json に貼り付けます

{
  "mcpServers": {
    "hubspot": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "MCP_TRANSPORT",
        "-e",
        "HUBSPOT_ACCESS_TOKEN",
        "-e",
        "HUBSPOT_BASE_URL",
        "-e",
        "HUBSPOT_TOOL_MODE",
        "-e",
        "HUBSPOT_READ_ONLY",
        "-e",
        "HUBSPOT_CAPABILITY_CHECK",
        "-e",
        "MCP_AUTH_TOKEN",
        "ghcr.io/ohneben/hubspot-mcp:2.0.1"
      ],
      "env": {
        "MCP_TRANSPORT": "your-value",
        "HUBSPOT_ACCESS_TOKEN": "your-value",
        "HUBSPOT_BASE_URL": "your-value",
        "HUBSPOT_TOOL_MODE": "your-value",
        "HUBSPOT_READ_ONLY": "your-value",
        "HUBSPOT_CAPABILITY_CHECK": "your-value",
        "MCP_AUTH_TOKEN": "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。

VS Codeで開く

または、設定を自分でコピーする

プロジェクトの .vscode/mcp.json に貼り付けます

{
  "servers": {
    "hubspot": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "MCP_TRANSPORT",
        "-e",
        "HUBSPOT_ACCESS_TOKEN",
        "-e",
        "HUBSPOT_BASE_URL",
        "-e",
        "HUBSPOT_TOOL_MODE",
        "-e",
        "HUBSPOT_READ_ONLY",
        "-e",
        "HUBSPOT_CAPABILITY_CHECK",
        "-e",
        "MCP_AUTH_TOKEN",
        "ghcr.io/ohneben/hubspot-mcp:2.0.1"
      ],
      "env": {
        "MCP_TRANSPORT": "your-value",
        "HUBSPOT_ACCESS_TOKEN": "your-value",
        "HUBSPOT_BASE_URL": "your-value",
        "HUBSPOT_TOOL_MODE": "your-value",
        "HUBSPOT_READ_ONLY": "your-value",
        "HUBSPOT_CAPABILITY_CHECK": "your-value",
        "MCP_AUTH_TOKEN": "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。

自分で入力する値

  • MCP_TRANSPORT 必須 env
    Server transport. Set to 'stdio' for local MCP clients; the image otherwise starts the Streamable HTTP transport.
  • HUBSPOT_ACCESS_TOKEN 秘密 必須 env
    HubSpot service key or legacy private app token (pat-...), from Settings -> Integrations. An OAuth access token also works.
  • HUBSPOT_BASE_URL env
    API host. Default https://api.hubapi.com; use https://api-eu1.hubapi.com for EU data residency portals.
  • HUBSPOT_TOOL_MODE env
    'discovery' (default) exposes 3 meta-tools that search, inspect and call all 1,076 endpoints; 'all' exposes the ~690 endpoint tools directly.
  • HUBSPOT_READ_ONLY env
    Set to 'true' to expose only read-only tools.
  • HUBSPOT_CAPABILITY_CHECK env
    Read the token's scopes and probe paid-tier or beta API groups at startup (read-only, up to about 30 API calls). Set to 'false' to skip.
  • MCP_AUTH_TOKEN 秘密 env
    Only for MCP_TRANSPORT=http: bearer token required on /mcp. Without it a non-loopback bind refuses to start.

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。

できること

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。

基本チェックi

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9日にチェック

  • ✓ 合格

    作者とリポジトリが一致

    レジストリ名は、リポジトリを所有するGitHubアカウント ohneben で確認済みです

  • … 未チェック

    今もメンテナンスされている

    このリポジトリはまだGitHubから読み取っていません

  • … 未チェック

    ライセンスがある

    このリポジトリはまだGitHubから読み取っていません

  • – 対象外

    エンドポイントが応答する

    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

  • – 対象外

    OAuthでサインイン

    パソコンで動き、代わりにローカルの設定を使います

  • … 未チェック

    ツールの説明に隠れた指示がない

    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

マーケティング・SNSのほかのサーバーとの比較i

  • このカテゴリのほかの3631件のうち0%よりスターが多い
  • このカテゴリのほかの3631件のうち34%より最近レジストリに公開
  • 基本チェックの結果が、このカテゴリのほかの3631件のうち100%と同じかそれ以上

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。

よくある質問

HubSpotは安全ですか?

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。

どんなキーやコードが必要ですか?

入力が必要なもの:MCP_TRANSPORT, HUBSPOT_ACCESS_TOKEN, MCP_AUTH_TOKEN

パソコンで動きますか、それともクラウドですか?

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)。

今もメンテナンスされていますか?

GitHubリポジトリの最終更新は–、最新バージョン(2.0.1)がレジストリに届いたのは2 か月前です。

どのアプリで使えますか?

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Dockerも必要です。

代わりに使えるものは?

同じカテゴリには:MCP YouTube Transcript, Google Analytics MCP, BibiGPT YouTube Video Summarizer

代わりの候補

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:↓ 週あたりのダウンロードi★ 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

Google Analytics MCP

GA4 MCP server for AI agents: schema discovery, server-side aggregation, analysis-ready defaults.

作者:surendranb成長中↓ 1088/週★ 24412 日前更新

パソコンで動く

作者のREADME

READMEを開く

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。

ohneben's HubSpot MCP


License & checks
MCP registries

The most complete HubSpot MCP server there is. Run your entire HubSpot account in plain language from Claude, Cursor, or any other MCP client.

This Model Context Protocol server exposes the whole public HubSpot API — all 1,076 endpoints across 102 APIs, in 687 tools — CRM, CMS, Marketing, Automation, Conversations, Commerce, Files, Settings, Webhooks and more, generated straight from HubSpot's own OpenAPI definitions. Endpoints HubSpot repeats per object type are one tool each (crm_objects_search with objectType: "deals" instead of 32 separate search tools), and every tool description says when to use it. Every tool is safety-categorized (🟢 read-only / 🟡 write / 🔴 destructive) and — unique to this server — hub & plan aware: HubSpot publishes which hub and tier every API needs (Free / Starter / Professional / Enterprise), and this server carries that straight into each tool plus a live capability report for *your* portal. It runs over stdio (Claude Desktop and other local launchers) or Streamable HTTP (hosted in Docker), and ships with retries, client-side rate limiting tuned to HubSpot's burst caps, and request timeouts so it holds up against a live account.

Why you'll want this

Some MCP servers just forward a slice of the API. This one is built to be safe to hand to an LLM, complete, and easy to run for real:

What you getWhy it matters
All 1,076 endpoints — the whole public APIContacts, companies, deals, tickets, every engagement type, associations v4, properties, pipelines, lists, imports/exports, marketing emails & events, campaigns, forms, transactional email, sequences, workflows/actions, conversations & custom channels, CMS pages/posts/HubDB/source code, files, commerce (invoices, orders, carts, payments, subscriptions), settings, webhooks — nothing hand-picked or left behind. Most servers stop at ~30 CRM tools.
687 tools, not 1,076 look-alikesHubSpot repeats the same endpoints for 32 CRM object types, for landing and site pages, and for blog posts, authors and tags. Those are one tool each with a selector argument (objectType, pageType, blogResource), so crm_objects_search covers contacts, deals, tickets and custom objects. Every call still goes to exactly the endpoint it went to before, with that endpoint's scopes and plan hints.
Descriptions that say when to use a toolEach description opens with what the tool does, then when to prefer a sibling (crm_objects_list points to crm_objects_search for filtering and crm_objects_batch_read for known IDs), what it changes, plan and scopes, and the endpoint it calls. Undocumented HubSpot parameters get a description.
Hub & plan awareness *(nobody else has this)*HubSpot gates APIs by hub and tier — HubDB needs Content/Marketing Hub Professional, custom-object schemas need Enterprise, sequences need Sales/Service Professional. Every tool states its requirement, straight from HubSpot's own API index.
Access check at startupWhen the server starts it reads the token's scopes and probes every paid-tier or beta API group with one cheap read. The model gets the result in the server instructions, search results say per tool whether this token can use it, and hubspot_get_capabilities explains each status with the scopes to add. No more walls of mystery 403s.
Curated safety categories 🟢 / 🟡 / 🔴Not naive "GET = safe": a POST …/search is a read-only query, merge is flagged irreversible, gdpr-delete is a permanent purge (vs. archive → recycle bin), list-membership calls are reversible links, POST /crm/v3/imports is a bulk import, and transactional email is sends messages.
Machine-readable MCP annotations (readOnlyHint, destructiveHint)Hosts that honor annotations (Claude included) can auto-trust reads and demand confirmation before anything destructive.
Actionable error hints403 with MISSING_SCOPES → the exact scopes to add and where; plain 403 on a gated API → the plan tier it needs; 401 → token type & expiry guidance; 429 → your limits. The model gets *how to fix it*, not just *what broke*.
Read-only mode & group filteringExpose only the 302 🟢 read-only tools (HUBSPOT_READ_ONLY=true), or narrow to the groups you use (HUBSPOT_INCLUDE_GROUPS=contacts,deals,cms:*). Area wildcards included.
Discovery mode by defaultOut of the box the model sees 6 tools (~2k tokens): search, inspect and invoke over all 687 endpoint tools, plus the capability, GraphQL and raw-request tools. HUBSPOT_TOOL_MODE=all exposes every endpoint tool directly. Read-only mode applies either way.
Real file uploadsThe multipart endpoints (Files, CRM imports, HubDB import, CMS source code) actually work — pass file content inline or as base64. Most generated servers can't do multipart at all.
Automatic retries with backoffTransient 429 / 5xx responses are retried with jittered exponential backoff, honoring HubSpot's Retry-After header.
Built-in rate limitingSelf-throttles under HubSpot's burst caps (default 100 req / 10 s) with a separate limiter for the `/search` endpoints (~5 req/s cap). A burst of tool calls won't trip a 429.
Response-size guardOptionally cap huge list responses (HUBSPOT_MAX_RESPONSE_CHARS) so one call can't blow the model's context window.
CRM GraphQL passthroughHubSpot's GraphQL endpoint is query-only, so it's a 🟢 tool here — fetch a contact, its company and that company's deals in one round-trip.
Raw-request escape hatchhubspot_api_request reaches brand-new or beta endpoints the moment HubSpot ships them — auth, throttling and retries still handled server-side.
**Two transports: stdio *and* Streamable HTTP**Use it locally in Claude Desktop, or run one always-on server that any number of MCP clients reach over HTTP.
Docker + docker-compose, health check, auto-restartProduction-style deployment out of the box: docker compose up and it stays up.
Optional bearer-token auth on the HTTP endpointPut the server behind a shared secret the moment it's reachable beyond localhost.
Your token never reaches the modelThe access token lives in the server's environment and is injected on every request — the assistant only ever sees tool inputs and API responses.
Drop-in spec updatesnpm run fetch-specs pulls HubSpot's latest OpenAPI definitions (and their hub/tier metadata) from HubSpot's public index — new endpoints become new tools on rebuild, no code changes.

How it compares

There are a few ways to reach HubSpot from an AI assistant today. Here's how this server stacks up against the alternatives:

This serverOfficial HubSpot MCPshinzo-labs hubspot-mcpmcp-hubspot (buryhuang)CData MCP
Approx. tools~690 (all 1,076 endpoints)~7 curated (remote)100+~73 (generic SQL)
Whole public API (CRM and CMS · Marketing · Automation · Commerce · Files · Settings · Webhooks)✅➖ CRM + some content reads➖ CRM-centric❌❌
Hub & plan-tier awareness per tool✅❌❌❌❌
Account capability report (scopes · usage · unlocks)✅❌❌❌❌
Reads and writes✅✅✅➖ partial❌ read-only
Curated 🟢 / 🟡 / 🔴 safety categories✅➖➖➖n/a
readOnlyHint / destructiveHint annotations✅➖➖➖➖
Read-only mode + group filtering✅❌❌❌always read-only
File uploads (multipart)✅❌❌❌❌
GraphQL passthrough✅❌❌❌❌
Rate limiting + auto-retry (429/5xx)✅➖➖❌❌
stdio transport✅✅ local package✅✅✅
Streamable-HTTP transport✅✅ hosted remote✅❌❌
Docker + compose + health check✅❌➖ Dockerfile➖ image only❌
Self-hosted on your own infra✅➖ vendor cloud✅✅✅
LanguageTypeScriptTypeScriptTypeScriptPythonJava
LicenseMIT—MITMITMIT

✅ = yes · ➖ = partial / not documented · ❌ = no. Compiled from each project's public documentation; this is an unofficial project, not affiliated with HubSpot or the projects listed. Tool counts are approximate and move as APIs evolve.

The short version: the official remote server is a great managed on-ramp but covers a handful of curated tools. The community servers are solid but CRM-centric, without plan awareness or safety guardrails. This one gives you the entire public API, hub/plan awareness no one else has, both transports, a production Docker deployment, and curated safety categories — self-hosted, on your token, MIT.

What you can do

Once it's connected, ask your assistant things like:

  • "Find jane@example.com, show her company, open deals and the last emails we exchanged."
  • "Create a $12,000 deal 'Acme expansion' in the Sales pipeline, stage Qualified, associated with Acme Corp."
  • "Search contacts created this month with lifecycle stage MQL and add them to the 'Q3 nurture' list."
  • "Which HubDB tables exist? Add a row to 'pricing' and publish the table."
  • "Clone last month's newsletter as a draft — don't publish."
  • "Upload this CSV and start a contact import mapped to email + first name."
  • "What can my token do? Check my API usage and which scopes are missing for HubDB." *(→ hubspot_get_capabilities)*
  • "Merge these two duplicate contacts — after showing me both records first."

Tools are generated automatically from HubSpot's specs and grouped into 🟢 read-only, 🟡 write and 🔴 destructive — so a well-behaved host can treat each group differently.

How it works

Claude / Cursor / any MCP client  ──MCP──►  this server  ──HTTPS──►  api.hubapi.com (your portal)

The server parses 104 bundled OpenAPI definitions (fetched from HubSpot's public API index, which also publishes per-API hub/tier requirements) into MCP tools — resolving $refs, guarding against recursive schemas, merging endpoints that only differ by object type into one tool, deriving clean names like crm_objects_search and hubdb_tables_create_table, and tagging each tool with a curated safety category, its plan requirement and its OAuth scopes. Your access token is injected server-side on every request; the model never sees or handles it.

Hub & plan awareness

HubSpot isn't one API — what you can call depends on which hubs (Marketing, Sales, Service, Content, Commerce, Operations) and which tier (Free, Starter, Professional, Enterprise) the portal has, plus the scopes gr

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

PopNxに聞く