HubSpot MCP
平台与服务by shinzo-labs
透過100+個工具存取與管理HubSpot CRM資料,可操作Contacts、Companies與Associations,並支援使用Developer API Key。
什么是 HubSpot MCP?
透過100+個工具存取與管理HubSpot CRM資料,可操作Contacts、Companies與Associations,並支援使用Developer API Key。
README
A Model Context Protocol (MCP) server implementation for the HubSpot API, providing a standardized interface for accessing and managing CRM data.
<p align="center"><img height="512" src=https://github.com/user-attachments/assets/6a0febe5-1aa5-4998-affb-6c5874ed00c4></p>Features
- Complete coverage of the HubSpot CRM API
- Support for all standard CRM objects (companies, contacts, deals, etc.)
- Advanced association management with CRM Associations v4
- Company-specific endpoints with property validation
- Batch operations for efficient data management
- Advanced search and filtering capabilities
- Type-safe parameter validation with Zod
Prerequisites
If you don't have an API key, follow the steps here to obtain an access token. OAuth support is planned as a future enhancement.
Client Configuration
There are several options to configure your MCP client with the server. For hosted/remote server setup, use Smithery's CLI with a Smithery API Key. For local installation, use npx or build from source. Each of these options is explained below.
Smithery Remote Server (Recommended)
To add a remote server to your MCP client config.json, run the following command from Smithery CLI:
npx -y @smithery/cli install @shinzo-labs/hubspot-mcp
Enter your HUBSPOT_ACCESS_TOKEN when prompted.
Smithery SDK
If you are developing your own agent application, you can use the boilerplate code here.
NPX Local Install
To install the server locally with npx, add the following to your MCP client config.json:
{
"mcpServers": {
"hubspot": {
"command": "npx",
"args": [
"@shinzolabs/hubspot-mcp"
],
"env": {
"HUBSPOT_ACCESS_TOKEN": "your-access-token-here"
}
}
}
}
Build from Source
- Download the repo:
git clone https://github.com/shinzo-labs/hubspot-mcp.git
- Install packages (inside cloned repo):
pnpm i
- Add the following to your MCP client
config.json:
{
"mcpServers": {
"hubspot": {
"command": "node",
"args": [
"/path/to/hubspot-mcp/index.js"
],
"env": {
"HUBSPOT_ACCESS_TOKEN": "your-access-token-here"
}
}
}
}
Config Variables
| Variable | Description | Required? | Default |
|---|---|---|---|
HUBSPOT_ACCESS_TOKEN | Access Token for Hubspot Application | Yes | |
PORT | Port for Streamable HTTP transport method | No | 3000 |
TELEMETRY_ENABLED | Enable telemetry | No | true |
Supported Tools
Core CRM Objects
crm_list_objects: List CRM objects with optional filtering and paginationcrm_get_object: Get a single CRM object by IDcrm_create_object: Create a new CRM objectcrm_update_object: Update an existing CRM objectcrm_archive_object: Archive (delete) a CRM objectcrm_search_objects: Search CRM objects using advanced filterscrm_batch_create_objects: Create multiple objects in a single requestcrm_batch_read_objects: Read multipl objects in a single requestcrm_batch_update_objects: Update multiple objects in a single requestcrm_batch_archive_objects: Archive (delete) multiple objects in a single request
Companies
crm_create_company: Create a new company with validated propertiescrm_update_company: Update an existing companycrm_get_company: Get a single company by IDcrm_search_companies: Search companies with specific filterscrm_batch_create_companies: Create multiple companies in a single requestcrm_batch_update_companies: Update multiple companies in a single requestcrm_get_company_properties: Get all available company propertiescrm_create_company_property: Create a new company property
Contacts
crm_create_contact: Create a new contact with validated propertiescrm_update_contact: Update an existing contact's informationcrm_get_contact: Get a single contact by IDcrm_search_contacts: Search contacts with specific filterscrm_batch_create_contacts: Create multiple contacts in a single requestcrm_batch_update_contacts: Update multiple contacts in a single requestcrm_get_contact_properties: Get all available contact propertiescrm_create_contact_property: Create a new contact property
Leads
crm_create_lead: Create a new lead with validated propertiescrm_update_lead: Update an existing lead's informationcrm_get_lead: Get a single lead by IDcrm_search_leads: Search leads with specific filterscrm_batch_create_leads: Create multiple leads in a single requestcrm_batch_update_leads: Update multiple leads in a single requestcrm_get_lead_properties: Get all available lead propertiescrm_create_lead_property: Create a new lead property
Engagement Management
engagement_details_get: Get details of a specific engagementengagement_details_create: Create a new engagementengagement_details_update: Update an existing engagementengagement_details_archive: Archive (delete) an engagementengagement_details_list: List all engagements with filteringengagement_details_get_associated: Get associated engagements
Calls
calls_create: Create a new call recordcalls_get: Get call detailscalls_update: Update a call recordcalls_archive: Archive a callcalls_list: List all callscalls_search: Search callscalls_batch_create: Create multiple callscalls_batch_read: Read multiple callscalls_batch_update: Update multiple callscalls_batch_archive: Archive multiple calls
Emails
emails_create: Create a new email recordemails_get: Get email detailsemails_update: Update an emailemails_archive: Archive an emailemails_list: List all emailsemails_search: Search emailsemails_batch_create: Create multiple emailsemails_batch_read: Read multiple emailsemails_batch_update: Update multiple emailsemails_batch_archive: Archive multiple emails
Meetings
meetings_create: Create a new meetingmeetings_get: Get meeting detailsmeetings_update: Update a meetingmeetings_archive: Archive (delete) a meetingmeetings_list: List all meetingsmeetings_search: Search meetingsmeetings_batch_create: Create multiple meetingsmeetings_batch_update: Update multiple meetingsmeetings_batch_archive: Archive multiple meetings
Notes
notes_create: Create a new notenotes_get: Get note detailsnotes_update: Update a notenotes_archive: Archive a notenotes_list: List all notesnotes_search: Search notesnotes_batch_create: Create multiple notesnotes_batch_read: Read multiple notesnotes_batch_update: Update multiple notesnotes_batch_archive: Archive multiple notes
Tasks
tasks_create: Create a new tasktasks_get: Get task detailstasks_update: Update a tasktasks_archive: Archive a tasktasks_list: List all taskstasks_search: Search taskstasks_batch_create: Create multiple taskstasks_batch_read: Read multiple taskstasks_batch_update: Update multiple taskstasks_batch_archive: Archive multiple tasks
Associations and Relationships
crm_list_association_types: List available association typescrm_get_associations: Get all associations between objectscrm_create_association: Create an associationcrm_archive_association: Archive (delete) an associationcrm_batch_create_associations: Create multiple associationscrm_batch_archive_associations: Archive (delete) multiple associations
Communication Preferences
communications_get_preferences: Get contact preferencescommunications_update_preferences: Update contact preferencescommunications_unsubscribe_contact: Global unsubscribecommunications_subscribe_contact: Global subscribecommunications_get_subscription_definitions: Get subscription definitionscommunications_get_subscription_status: Get status for multiple contactscommunications_update_subscription_status: Update status for multiple contacts
Products
products_create: Create a product with the given properties and return a copy of the object, including the ID.products_read: Read an Object identified by IDproducts_update: Perform a partial update of an Object identified by ID. Read-only and non-existent properties will result in an error. Properties values can be cleared by passing an empty string.products_archive: Move an Object identified by ID to the recycling bin.products_list: Read a page of products. Control what is returned via thepropertiesquery param.afteris the paging cursor token of the last successfully read resource will be returned as thepaging.next.afterJSON property of a paged response containing more results.products_search: Search productsproducts_batch_create: Create a batch of productsproducts_batch_read: Read a batch of products by internal ID, or unique property values. Retrieve records by theidPropertyparameter to retrieve records by a custom unique value property.products_batch_update: Update a batch of products by internal ID, or unique values specified by theidPropertyquery param.products_batch_archive: Archive a batch of products by ID
Contributing
Contributions are welcomed and encouraged! Please read CONTRIBUTING.md for guidelines on issues, contributions, and contact information.
Data Collection and Privacy
Shinzo Labs collects limited anonymous telemetry from this server to help improve our products and services. No personally identifiable information is collected as part of this process. Please review the Privacy Policy for more details on the types of data collected and how to opt-out of this telemetry.
License
MIT
常见问题
HubSpot MCP 是什么?
透過100+個工具存取與管理HubSpot CRM資料,可操作Contacts、Companies與Associations,並支援使用Developer API Key。
相关 Skills
Slack动图
by anthropics
面向Slack的动图制作Skill,内置emoji/消息GIF的尺寸、帧率和色彩约束、校验与优化流程,适合把创意或上传图片快速做成可直接发送的Slack动画。
✎ 帮你快速做出适配 Slack 的动图,内置约束规则和校验工具,少踩上传与播放坑,做表情包和演示都更省心。
MCP构建
by anthropics
聚焦高质量 MCP Server 开发,覆盖协议研究、工具设计、错误处理与传输选型,适合用 FastMCP 或 MCP SDK 对接外部 API、封装服务能力。
✎ 想让 LLM 稳定调用外部 API,就用 MCP构建:从 Python 到 Node 都有成熟指引,帮你更快做出高质量 MCP 服务器。
接口测试套件
by alirezarezvani
扫描 Next.js、Express、FastAPI、Django REST 的 API 路由,自动生成覆盖鉴权、参数校验、错误码、分页、上传与限流场景的 Vitest 或 Pytest 测试套件。
✎ 帮你把API与集成测试自动化跑顺,减少回归漏测;能力全面,尤其适合复杂接口场景的QA团队。
相关 MCP Server
Slack 消息
编辑精选by Anthropic
Slack 是让 AI 助手直接读写你的 Slack 频道和消息的 MCP 服务器。
✎ 这个服务器解决了团队协作中需要 AI 实时获取 Slack 信息的痛点,特别适合开发团队让 Claude 帮忙汇总频道讨论或发送通知。不过,它目前只是参考实现,文档有限,不建议在生产环境直接使用——更适合开发者学习 MCP 如何集成第三方服务。
by netdata
io.github.netdata/mcp-server 是让 AI 助手实时监控服务器指标和日志的 MCP 服务器。
✎ 这个工具解决了运维人员需要手动检查系统状态的痛点,最适合 DevOps 团队让 Claude 自动分析性能数据。不过,它依赖 NetData 的现有部署,如果你没用过这个监控平台,得先花时间配置。
by d4vinci
Scrapling MCP Server 是专为现代网页设计的智能爬虫工具,支持绕过 Cloudflare 等反爬机制。
✎ 这个工具解决了爬取动态网页和反爬网站时的头疼问题,特别适合需要批量采集电商价格或新闻数据的开发者。不过,它依赖外部浏览器引擎,资源消耗较大,不适合轻量级任务。