HubSpot MCP Server
HubSpot MCP Server
[]
概述
一个 Model Context Protocol (MCP) 服务器,使 AI 助手能够与 HubSpot CRM 数据交互。该服务器将 AI 模型与您的 HubSpot 账户连接起来,提供对联系人、公司和互动数据的直接访问。内置的向量存储和缓存机制有助于克服 HubSpot API 的限制,同时缩短响应时间。
我们的实现优先处理最常用、高价值的 HubSpot 操作,并具备稳健的错误处理和 API 稳定性。每个组件都针对 AI 友好交互进行了优化,确保即使在复杂的多步骤 CRM 工作流中也能保持可靠性能。
Related MCP server: HubSpot MCP Server
为什么选择 MCP-HubSpot?
直接 CRM 访问:将 Claude 和其他 AI 助手直接连接到您的 HubSpot 数据,无需中间步骤
上下文保留:使用 FAISS 的向量存储支持对先前交互进行语义搜索
零配置:简单的 Docker 部署,设置极少
示例提示词
Create HubSpot contacts and companies from this LinkedIn profile:
[Paste LinkedIn profile text]What's happening lately with my pipeline?可用工具
该服务器提供用于 HubSpot 管理和数据检索的工具:
工具 | 用途 |
| 创建联系人并防止重复 |
| 创建公司并防止重复 |
| 检索特定公司的活动 |
| 检索最近活跃的公司 |
| 检索最近活跃的联系人 |
| 检索带有消息的最近对话线程 |
| 对先前检索的 HubSpot 数据进行语义搜索 |
性能特性
向量存储:利用 FAISS 进行高效的语义搜索和检索
线程级索引:单独存储每个对话线程,以实现精确检索
嵌入缓存:使用带有自动缓存的 SentenceTransformer
持久化存储:数据在会话之间持久保存于可配置的存储目录中
多平台支持:针对多种架构优化的 Docker 镜像
设置
先决条件
您需要一个具有以下范围的 HubSpot 访问令牌:
crm.objects.contacts(读/写)
crm.objects.companies(读/写)
sales-email-read
Docker 配置
用于在 Claude desktop 中进行手动配置:
{
"mcpServers": {
"hubspot": {
"command": "docker",
"args": [
"run", "-i", "--rm",
"-e", "HUBSPOT_ACCESS_TOKEN=your_token",
"-v", "/path/to/storage:/storage", # Optional persistent storage
"dennis/mcp-hubspot:latest"
]
}
}
}构建 Docker 镜像
要在本地构建 Docker 镜像:
git clone https://github.com/dennis19741216/AI-assistant-with-HubSpot-CRM.git
cd mcp-hubspot
docker build -t mcp-hubspot .对于多平台构建:
docker buildx create --use
docker buildx build --platform linux/amd64,linux/arm64 -t dennis/mcp-hubspot:latest --push .开发
pip install -e .Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
CRM, inbox, meetings, revenue intelligence, analytics and automations for AI agents.
Connect AI assistants to Nimble CRM to access and work with customer relationship data.
Connect AI to your Attio CRM. Manage contacts, companies, deals, and sales pipelines. Create tasks…
Open-source CRM for AI agents: humans, orgs, interactions, deals, tasks, links and an activity log.
Related MCP Servers
- FlicenseNot gradedqualityAmaintenanceEnables AI assistants to interact with HubSpot CRM data for creating and retrieving contacts, companies, activity, and conversations, with built-in vector storage and caching for faster semantic search.-
- FlicenseNot gradedqualityAmaintenanceEnables AI assistants to interact with HubSpot CRM data by creating contacts and companies, retrieving activity and recent conversations, and performing semantic search across previously retrieved records with built-in caching and vector storage.-
- FlicenseNot gradedqualityAmaintenanceEnables AI assistants to interact with HubSpot CRM data, including creating contacts and companies, retrieving activity and conversations, and performing semantic search over previously retrieved data. It includes vector storage and caching to improve response times and address HubSpot API limitations.-
- FlicenseNot gradedqualityAmaintenanceEnables AI assistants to interact with HubSpot CRM data by creating and retrieving contacts, companies, and recent activity, while providing semantic search over stored conversations with vector storage and caching.-