シームレスな HubSpot CRM 統合を実現する強力なモデル コンテキスト プロトコル (MCP) サーバー実装により、AI アシスタントが HubSpot データと対話できるようになります。
この MCP サーバーは、HubSpot CRM API と対話するための包括的なツール セットを提供し、AI アシスタントが次のことを実行できるようにします。
HubSpot CRMで連絡先と企業を作成および管理します
詳細な企業活動履歴とエンゲージメントタイムラインを取得します
HubSpotインスタンス全体の最近のエンゲージメントデータにアクセスします
最近アクティブな企業と連絡先のリストを取得する
AIアシスタントインターフェースを離れずにCRM操作を実行
Related MCP server: HubSpot MCP Server
シームレスなAI統合：AIアシスタントをHubSpot CRMデータに直接接続
簡素化された CRM 操作: 自然言語コマンドを使用して一般的な HubSpot タスクを実行します。
リアルタイムデータアクセス：HubSpotインスタンスから最新情報を取得します
セキュア認証：HubSpotのセキュアAPIトークン認証を使用します
拡張可能な設計: 必要に応じてHubSpot API機能を簡単に追加できます
# Clone the repository
git clone https://github.com/lkm1developer/hubspot-mcp-server.git
cd hubspot-mcp-server
# Install dependencies
npm install
# Build the project
npm run buildサーバーにはHubSpot APIアクセストークンが必要です。以下の方法で取得できます。
HubSpot開発者アカウントにアクセスする
必要なスコープ（連絡先、会社、エンゲージメント）を持つプライベートアプリを作成する
生成されたアクセストークンのコピー
トークンは次の 2 つの方法で提供できます。
環境変数として:
HUBSPOT_ACCESS_TOKEN=your-access-tokenコマンドライン引数として:
npm start -- --access-token=your-access-token開発の場合は、プロジェクト ルートに.envファイルを作成して環境変数を保存します。
HUBSPOT_ACCESS_TOKEN=your-access-token# Start the server
npm start
# Or with a specific access token
npm start -- --access-token=your-access-token
# Run the SSE server with authentication
npx mcp-proxy-auth node dist/index.jsSSEサーバーは認証にmcp-proxy-authパッケージを使用します。認証を実装するには、以下の手順に従います。
パッケージをインストールします。
npm install mcp-proxy-authAUTH_SERVER_URL環境変数を、API キー検証エンドポイントを指すように設定します。
export AUTH_SERVER_URL=https://your-auth-server.com/verify認証付きで SSE サーバーを実行します。
npx mcp-proxy-auth node dist/index.jsSSE URL は次の場所で入手できます。
localhost:8080/sse?apiKey=apikey認証用の実際の API キーにapikey置き換えます。
mcp-proxy-authパッケージは、次の機能を果たすプロキシとして機能します。
SSEサーバーへのリクエストをインターセプトします
認証サーバーに対してAPIキーを検証します
認証されたリクエストのみが SSE エンドポイントに到達できるようにします
このMCPサーバーは、モデルコンテキストプロトコル（MCP）をサポートするAIアシスタントと連携するように設計されています。サーバーが起動すると、互換性のあるAIアシスタントがHubSpot CRMデータを操作するために使用できるツールセットが公開されます。
サーバーは、次の強力な HubSpot 統合ツールを公開します。
hubspot_create_contact
重複チェック機能を使ってHubSpotで新しい連絡先を作成する
パラメータ:
firstname (文字列、必須): 連絡先の名
lastname (文字列、必須): 連絡先の姓
email (文字列、オプション): 連絡先のメールアドレス
properties (オブジェクト、オプション): 会社、電話番号などの追加の連絡先プロパティ。
例：
{
"firstname": "John",
"lastname": "Doe",
"email": "john.doe@example.com",
"properties": {
"company": "Acme Inc",
"phone": "555-123-4567",
"jobtitle": "Software Engineer"
}
}ハブスポット作成会社
重複チェック機能を備えたHubSpotで新しい会社を作成する
パラメータ:
name (文字列、必須): 会社名
properties (オブジェクト、オプション): 追加の会社プロパティ
例：
{
"name": "Acme Corporation",
"properties": {
"domain": "acme.com",
"industry": "Technology",
"phone": "555-987-6543",
"city": "San Francisco",
"state": "CA"
}
}hubspot_get_company_activity
特定の企業の包括的な活動履歴を取得する
パラメータ:
company_id （文字列、必須）: HubSpotの会社ID
メール、通話、会議、メモ、タスクなどの詳細なエンゲージメントデータを返します
hubspot_get_recent_engagements
すべての連絡先と企業の最近のエンゲージメント活動を取得します
パラメータ:
days （数値、オプション、デフォルト：7）：遡る日数
limit （数値、オプション、デフォルト：50）：返されるエンゲージメントの最大数
最近の CRM アクティビティの時系列リストを返します
hubspot_get_active_companies
HubSpotから最近アクティブな企業を取得する
パラメータ:
limit （数値、オプション、デフォルト：10）：返される企業の最大数
最終更新日順に企業を返します
hubspot_get_active_contacts
HubSpotから最近アクティブな連絡先を取得する
パラメータ:
limit （数値、オプション、デフォルト：10）：返される連絡先の最大数
最終更新日順に連絡先を返します
サーバーは簡単に拡張できるように設計されています。HubSpot APIの新しい機能を追加するには、以下の手順に従ってください。
src/hubspot-client.tsのHubSpotClientクラスに新しいメソッドを追加します。
src/index.tsのsetupToolHandlersメソッドに新しいツールを登録します。
npm run buildでプロジェクトをリビルドします。
このプロジェクトは MIT ライセンスに基づいてライセンスされています - 詳細については LICENSE ファイルを参照してください。
HubSpot、CRM、モデルコンテキストプロトコル、MCP、AIアシスタント、TypeScript、API統合、HubSpot API、CRM統合、コンタクト管理、企業管理、エンゲージメントトラッキング、AIツール
Create a new company in HubSpot
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Company name | |
| properties | No | Additional company properties |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool creates a company but lacks critical details: it doesn't specify required permissions, whether the operation is idempotent, potential side effects (e.g., triggering workflows), or error handling. This is inadequate for a mutation tool with zero annotation coverage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence with zero wasted words. It's front-loaded with the core action and resource, making it easy to parse quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a mutation tool with no annotations and no output schema, the description is incomplete. It doesn't explain what happens on success (e.g., returns a company ID) or failure, nor does it cover behavioral aspects like authentication needs or rate limits, leaving significant gaps for the agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, clearly documenting both parameters (name and properties). The description adds no additional parameter semantics beyond what the schema provides, such as examples or constraints. Baseline 3 is appropriate since the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Create') and resource ('new company in HubSpot'), making the purpose immediately understandable. It distinguishes from siblings like hubspot_update_company (update vs. create) and hubspot_get_active_companies (get vs. create), though it doesn't explicitly mention these distinctions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., authentication), when not to use it, or compare it to siblings like hubspot_update_company for existing companies, leaving the agent to infer usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Create a new contact in HubSpot
| Name | Required | Description | Default |
|---|---|---|---|
| firstname | Yes | Contact's first name | |
| lastname | Yes | Contact's last name | |
| No | Contact's email address | ||
| properties | No | Additional contact properties |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool creates a contact, implying a write operation, but doesn't cover critical aspects like required permissions, whether the operation is idempotent, error handling for duplicate emails, or what the response looks like (e.g., success/failure, contact ID). This leaves significant gaps for an agent to use it effectively.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, direct sentence with no wasted words, making it highly concise and front-loaded. It efficiently communicates the core purpose without unnecessary elaboration, earning a top score for brevity and clarity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of a write operation with no annotations and no output schema, the description is insufficient. It doesn't explain the behavioral traits (e.g., mutation effects, error cases) or what to expect upon success, leaving the agent without key context needed for reliable tool invocation in a HubSpot environment.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, clearly documenting all four parameters (firstname, lastname, email, properties) with their types and purposes. The description adds no additional parameter information beyond what's in the schema, so it meets the baseline of 3 for adequate coverage without extra value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Create') and resource ('new contact in HubSpot'), making the purpose immediately understandable. However, it doesn't differentiate this tool from its sibling 'hubspot_update_contact' beyond the creation vs. update distinction, which is implicit but not explicit.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives like 'hubspot_update_contact' for existing contacts or 'hubspot_get_active_contacts' for retrieval. It also doesn't mention prerequisites, such as needing HubSpot access or when creation is appropriate versus other operations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get most recently active companies from HubSpot
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of companies to return (default: 10) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions 'most recently active' but doesn't specify what 'active' means, how recency is determined, or any limitations like rate limits, permissions required, or pagination behavior. This leaves significant gaps for an agent to understand the tool's behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence with no wasted words. It's front-loaded with the core action and resource, making it easy to scan and understand quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations and output schema, the description is incomplete. It doesn't explain what 'active' entails, how results are ordered, or what data is returned, which are critical for a tool that fetches data. This leaves the agent with insufficient context for effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, with the 'limit' parameter well-documented. The description doesn't add any additional meaning beyond the schema, such as explaining the 'active' criteria or default behavior, so it meets the baseline of 3 without compensating for gaps.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb ('Get') and resource ('most recently active companies from HubSpot'), making the purpose understandable. However, it doesn't explicitly differentiate from sibling tools like 'hubspot_get_company_activity' or 'hubspot_get_active_contacts', which would require more specificity to earn a 5.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. With siblings like 'hubspot_get_company_activity' and 'hubspot_get_active_contacts', the description lacks context on selection criteria, such as whether this tool is for recent activity versus detailed activity tracking or contacts versus companies.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get most recently active contacts from HubSpot
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of contacts to return (default: 10) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It mentions retrieving 'most recently active contacts' but doesn't explain what 'active' means, how recency is determined, whether this is a read-only operation, what permissions are required, or how results are formatted. This leaves significant behavioral gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that directly states the tool's function without unnecessary words. It's appropriately sized for a simple retrieval tool and gets straight to the point.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a data retrieval tool with no annotations and no output schema, the description is insufficient. It doesn't explain what constitutes 'active' contacts, how results are sorted, what fields are returned, or any limitations. Given the lack of structured metadata, the description should provide more operational context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, with the 'limit' parameter clearly documented. The description doesn't add any parameter-specific information beyond what the schema provides, which is acceptable given the high schema coverage. The baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Get') and resource ('most recently active contacts from HubSpot'), making the purpose understandable. However, it doesn't explicitly differentiate from sibling tools like 'hubspot_get_company_activity' or 'hubspot_get_recent_engagements', which prevents a perfect score.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. There are multiple sibling tools for retrieving HubSpot data, but no indication of when this specific 'active contacts' tool is appropriate versus other contact or activity-related tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get activity history for a specific company
| Name | Required | Description | Default |
|---|---|---|---|
| company_id | Yes | HubSpot company ID |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations are absent, so the description carries the full burden. It states 'Get activity history', which implies a read-only operation, but does not disclose any behavioral traits such as whether it returns a list or single object, whether it supports filtering, or if any side effects occur. More detail is needed for safe invocation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no wasted words. It is front-loaded with the key information. Could be slightly expanded to include more detail while remaining concise, hence 4.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simplicity of the tool (one parameter, no output schema), the description provides the core purpose and required parameter. However, it lacks information about the return format, potential pagination, or examples of activity types. It is adequate but leaves some questions unanswered for an AI agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with a single parameter 'company_id' having a description. The tool description does not add additional semantic value beyond the schema, but the schema itself is sufficient. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get' and the resource 'activity history' for a specific company. It distinguishes from sibling tools like hubspot_get_company (which likely returns company details) and hubspot_get_active_companies (list of companies). However, it could specify the type of activity for even greater clarity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided about when to use this tool versus alternatives such as hubspot_get_company or hubspot_get_recent_conversations. The description lacks context on prerequisites, such as needing a valid company_id, or when to prefer this over other activity-related tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get recent engagement activities across all contacts and companies
| Name | Required | Description | Default |
|---|---|---|---|
| days | No | Number of days to look back (default: 7) | |
| limit | No | Maximum number of engagements to return (default: 50) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool 'Get[s] recent engagement activities', which implies a read-only operation, but it doesn't disclose any behavioral traits such as authentication requirements, rate limits, pagination, or what constitutes an 'engagement activity'. This leaves significant gaps for a tool with no annotation coverage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that front-loads the core purpose without any wasted words. It's appropriately sized for a simple tool and earns its place by clearly stating what the tool does.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations and no output schema, the description is incomplete. It doesn't explain what 'engagement activities' entail, the format of the return data, or any error conditions. For a tool that retrieves data across multiple entities, more context is needed to guide the agent effectively.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, with clear documentation for both parameters (days and limit), including defaults. The description doesn't add any parameter semantics beyond what the schema provides, such as explaining what 'engagements' include or how the lookback period works. This meets the baseline of 3 since the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get' and the resource 'recent engagement activities across all contacts and companies', making the purpose specific and understandable. It distinguishes this tool from siblings like hubspot_get_company_activity by specifying 'across all contacts and companies' rather than focusing on a single entity, though it doesn't explicitly name alternatives.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for retrieving recent engagement activities, but it doesn't provide explicit guidance on when to use this tool versus alternatives like hubspot_get_company_activity or hubspot_get_active_contacts. No exclusions or prerequisites are mentioned, leaving the agent to infer context based on the tool's name and description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Update an existing company in HubSpot (ignores if company does not exist)
| Name | Required | Description | Default |
|---|---|---|---|
| company_id | Yes | HubSpot company ID to update | |
| properties | Yes | Company properties to update |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals one important behavioral trait ('ignores if company does not exist'), which is valuable context not in the schema. However, it doesn't disclose other critical behaviors: whether this is a partial or full update, what permissions are required, whether changes are reversible, rate limits, or what happens when properties are invalid. For a mutation tool with zero annotation coverage, this leaves significant gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise - a single sentence that communicates the core purpose and one key behavioral constraint. Every word earns its place with no redundancy or fluff. The structure is front-loaded with the primary action and includes the important qualifier at the end.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given this is a mutation tool with no annotations and no output schema, the description provides minimal but essential context about the update operation and its behavior with non-existent companies. However, it doesn't address what the tool returns, error conditions, authentication requirements, or how property updates interact with existing data. For a tool that modifies business data, this leaves important gaps in understanding.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already fully documents both parameters. The description adds no additional parameter semantics beyond what's in the schema - it doesn't explain property format expectations, validation rules, or provide examples. The baseline score of 3 is appropriate when the schema does all the parameter documentation work.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Update') and resource ('an existing company in HubSpot'), making the purpose immediately understandable. It distinguishes from 'hubspot_create_company' by specifying it updates existing records rather than creating new ones. However, it doesn't explicitly differentiate from 'hubspot_update_contact' beyond the resource type.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides some usage context by stating it 'ignores if company does not exist', which implies it should only be used when you know the company exists or want a no-op behavior for missing companies. However, it doesn't explicitly guide when to use this versus alternatives like 'hubspot_create_company' or provide any prerequisites about required permissions or data formats.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Update an existing contact in HubSpot (ignores if contact does not exist)
| Name | Required | Description | Default |
|---|---|---|---|
| contact_id | Yes | HubSpot contact ID to update | |
| properties | Yes | Contact properties to update |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It adds useful context by stating 'ignores if contact does not exist', which clarifies idempotent behavior. However, it lacks details on permissions, rate limits, response format, or whether updates are partial/complete, leaving gaps for a mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that is front-loaded with the core purpose and includes a key behavioral note. There is no wasted text, and it effectively communicates essential information in minimal words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity as a mutation operation with no annotations and no output schema, the description is moderately complete. It covers the basic purpose and one behavioral trait but lacks details on permissions, error responses, or update semantics. For a 2-parameter tool with high schema coverage, it's adequate but has clear gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents both parameters ('contact_id' and 'properties') adequately. The description doesn't add any additional meaning or examples beyond what the schema provides, such as property format or validation rules. Baseline 3 is appropriate when the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb ('Update') and resource ('an existing contact in HubSpot'), making the purpose specific and understandable. It distinguishes from sibling tools like 'hubspot_create_contact' by focusing on updates rather than creation. However, it doesn't explicitly differentiate from 'hubspot_update_company', which is a minor gap.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage by specifying 'ignores if contact does not exist', which suggests it's for updating existing contacts only. However, it doesn't provide explicit guidance on when to use this versus alternatives like 'hubspot_create_contact' or 'hubspot_update_company', nor does it mention prerequisites or error handling beyond the ignore behavior.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
hubspot_create_companyhubspot_create_contacthubspot_get_active_companieshubspot_get_active_contactshubspot_get_company_activityhubspot_get_recent_engagementshubspot_update_companyhubspot_update_contactScored across 8 tools
Each tool has a clearly distinct purpose targeting specific resources (companies, contacts, engagements) and actions (create, get, update). The 'get' tools differentiate by scope (active vs. specific activity vs. recent engagements), eliminating ambiguity. No tools appear to do the same thing, making misselection unlikely.
All tools follow a consistent 'hubspot_verb_noun' pattern with snake_case throughout. The verbs (create, get, update) are used predictably across resources, and the naming structure is uniform, making the set highly readable and predictable for agents.
With 8 tools, this server is well-scoped for HubSpot CRM operations, covering core entities (companies, contacts, engagements) with essential CRUD actions. Each tool earns its place without bloat, providing a focused yet functional surface for typical agent workflows.
The toolset offers strong coverage for companies and contacts with create, get (active/specific), and update operations, plus engagement retrieval. Minor gaps include no delete operations and limited get options (e.g., no general get_company or get_contact by ID), but agents can work around these with the provided tools.
The HubSpot MCP Server acts as a bridge that enables AI assistants and Large Language Models to securely interact with HubSpot CRM data through natural conversation, without requiring users to understand complex API structures. It provides read-only access to standard CRM objects (contacts, companies, deals, tickets, products, invoices, and more) and their associations, secured via OAuth 2.0, allowing AI agents to perform tasks like summarizing deals, fetching company updates, and looking up record changes.
MCP server for the HubSpot Integrations Center HubDB: search and retrieve integration data.
API-first CRM for LLMs - contacts, companies, deals and activities over a native MCP server.
Marketo MCP server for AI. 130 tools to operate Marketo from Claude, Cursor, or ChatGPT.
