
HubSpot MCP Server
Contribute to baryhuang/mcp-hubspot development by creating an account on GitHub.
README
HubSpot MCP Server
Overview
A Model Context Protocol (MCP) server implementation that provides integration with HubSpot CRM. This server enables AI models to interact with HubSpot data and operations through a standardized interface.
For more information about the Model Context Protocol and how it works, see Anthropic's MCP documentation.
Components
Resources
The server exposes the following resources:
hubspot://hubspot_contacts
: A dynamic resource that provides access to HubSpot contactshubspot://hubspot_companies
: A dynamic resource that provides access to HubSpot companieshubspot://hubspot_recent_engagements
: A dynamic resource that provides access to HubSpot engagements from the last 3 days
All resources auto-update as their respective objects are modified in HubSpot.
Example Prompts
-
Create Hubspot contacts by copying from LinkedIn profile webpage:
Create HubSpot contacts and companies from following: John Doe Software Engineer at Tech Corp San Francisco Bay Area • 500+ connections Experience Tech Corp Software Engineer Jan 2020 - Present · 4 yrs San Francisco, California Previous Company Inc. Senior Developer 2018 - 2020 · 2 yrs Education University of California, Berkeley Computer Science, BS 2014 - 2018
-
Get latest activities for your company:
What's happening latestly with my pipeline?
Tools
The server offers several tools for managing HubSpot objects:
Contact Management Tools
-
hubspot_get_contacts
- Retrieve contacts from HubSpot
- No input required
- Returns: Array of contact objects
-
hubspot_create_contact
- Create a new contact in HubSpot (checks for duplicates before creation)
- Input:
firstname
(string): Contact's first namelastname
(string): Contact's last nameemail
(string, optional): Contact's email addressproperties
(dict, optional): Additional contact properties- Example:
{"phone": "123456789", "company": "HubSpot"}
- Example:
- Behavior:
- Checks for existing contacts with the same first name and last name
- If
company
is provided in properties, also checks for matches with the same company - Returns existing contact details if a match is found
- Creates new contact only if no match is found
Company Management Tools
-
hubspot_get_companies
- Retrieve companies from HubSpot
- No input required
- Returns: Array of company objects
-
hubspot_create_company
- Create a new company in HubSpot (checks for duplicates before creation)
- Input:
name
(string): Company nameproperties
(dict, optional): Additional company properties- Example:
{"domain": "example.com", "industry": "Technology"}
- Example:
- Behavior:
- Checks for existing companies with the same name
- Returns existing company details if a match is found
- Creates new company only if no match is found
-
hubspot_get_company_activity
- Get activity history for a specific company
- Input:
company_id
(string): HubSpot company ID
- Returns: Array of activity objects
Engagement Tools
hubspot_get_recent_engagements
- Get HubSpot engagements from all companies and contacts from the last 3 days
- No input required
- Returns: Array of engagement objects with full metadata
Setup
Prerequisites
You'll need a HubSpot access token. You can obtain this by:
- Creating a private app in your HubSpot account: Follow the HubSpot Private Apps Guide
- Go to your HubSpot account settings
- Navigate to Integrations > Private Apps
- Click "Create private app"
- Fill in the basic information:
- Name your app
- Add description
- Upload logo (optional)
- Define required scopes:
- tickets
- crm.objects.contacts.write
- crm.objects.contacts.sensitive.read
- crm.objects.companies.sensitive.read
- sales-email-read
- crm.objects.deals.sensitive.read
- crm.objects.companies.write
- crm.objects.companies.read
- crm.objects.deals.read
- crm.objects.deals.write
- crm.objects.contacts.read
- Review and create the app
- Copy the generated access token
Note: Keep your access token secure and never commit it to version control.
Docker Installation
You can either build the image locally or pull it from Docker Hub. The image is built for the Linux platform.
Supported Platforms
- Linux/amd64
- Linux/arm64
- Linux/arm/v7
Option 1: Pull from Docker Hub
docker pull buryhuang/mcp-hubspot:latest
Option 2: Build Locally
docker build -t mcp-hubspot .
Run the container:
docker run \ -e HUBSPOT_ACCESS_TOKEN=your_access_token_here \ buryhuang/mcp-hubspot:latest
Cross-Platform Publishing
To publish the Docker image for multiple platforms, you can use the docker buildx
command. Follow these steps:
-
Create a new builder instance (if you haven't already):
docker buildx create --use
-
Build and push the image for multiple platforms:
docker buildx build --platform linux/amd64,linux/arm64,linux/arm/v7 -t buryhuang/mcp-hubspot:latest --push .
-
Verify the image is available for the specified platforms:
docker buildx imagetools inspect buryhuang/mcp-hubspot:latest
Usage with Claude Desktop
Installing via Smithery
To install mcp-hubspot for Claude Desktop automatically via Smithery:
npx -y @smithery/cli@latest install mcp-hubspot --client claude
Docker Usage
{ "mcpServers": { "hubspot": { "command": "docker", "args": [ "run", "-i", "--rm", "-e", "HUBSPOT_ACCESS_TOKEN=your_access_token_here", "buryhuang/mcp-hubspot:latest" ] } } }
Development
To set up the development environment:
License
This project is licensed under the MIT License.
推荐服务器
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
DuckDuckGo MCP Server
一个模型上下文协议 (MCP) 服务器,通过 DuckDuckGo 提供网页搜索功能,并具有内容获取和解析的附加功能。
YouTube Transcript MCP Server
这个服务器用于获取指定 YouTube 视频 URL 的字幕,从而可以与 Goose CLI 或 Goose Desktop 集成,进行字幕提取和处理。
Tavily MCP Server
使用 Tavily 的搜索 API 提供 AI 驱动的网络搜索功能,使 LLM 能够执行复杂的网络搜索、获得问题的直接答案以及搜索最近的新闻文章。

Brev
在云端运行、构建、训练和部署机器学习模型。

Crawlab MCP Server

Story Protocol SDK MCP
This server provides MCP (Model Context Protocol) tools for interacting with Story's Python SDK. Features Get license terms Mint and register IP Asset with PIL Terms Mint license tokens Send $IP to a wallet Upload image to ipfs via Pinata [External] Upload ip and nft metadata via Pinata [External]

Appwrite MCP Server
一个模型上下文协议服务器,允许 AI 助手与 Appwrite 的 API 交互,从而提供管理 Appwrite 项目中数据库、用户、函数、团队和其他资源的工具。
MCP2Lambda
通过 MCP 协议,人工智能模型能够与 AWS Lambda 函数交互,从而在安全的环境中访问私有资源、实时数据和自定义计算。
ScrapeGraph MCP Server
一个生产就绪的模型上下文协议服务器,使语言模型能够利用 AI 驱动的网络抓取功能,提供将网页转换为 Markdown、提取结构化数据和执行 AI 驱动的网络搜索的工具。