About Hubspot Mcp Server
Hubspot Mcp Server connects MCP clients to HubSpot data and deal operations. It combines entity browsing and filtering with semantic search and caching tools.
Key features
- 01Browse contacts, companies, deals, and engagements
- 02Search entities with filters
- 03Read entity properties and schemas
- 04Create and update deals
- 05Semantic search with FAISS
- 06Cache and bulk-load entities
Use cases
- 01Find HubSpot records using natural-language queries
- 02Review deal details and update deal records
- 03Explore available fields for HubSpot entities
MCP support
An MCP server exposing 18 tools for HubSpot contacts, companies, deals, and engagements, including search, deal management, semantic search, and cache operations.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEHubSpot MCP Server
MCP (Model Context Protocol) server for integrating HubSpot with MCP clients (like Claude Desktop). Provides access to HubSpot contacts, companies, and deals through conversational tools.
🛠️ Available Tools
The server provides 18 tools for comprehensive HubSpot integration:
| Category | Tools | Description |
|---|---|---|
| 📋 Entity Listing | list_hubspot_contactslist_hubspot_companieslist_hubspot_dealslist_hubspot_engagements | List and browse HubSpot entities with pagination support |
| 🔧 Properties | get_hubspot_contact_propertiesget_hubspot_company_propertiesget_hubspot_deal_properties | Retrieve field properties and schemas for each entity type |
| 🔍 Search & Filtering | search_hubspot_contactssearch_hubspot_companiessearch_hubspot_deals | Advanced search with filters for each entity type |
| 💼 Deal Management | get_deal_by_namecreate_dealupdate_deal | Complete deal lifecycle management |
| 🤖 AI-Powered Search | semantic_search_hubspotmanage_hubspot_embeddingsbrowse_hubspot_indexed_data | Semantic search using natural language with FAISS vector database |
| ⚡ Cache & Performance | load_hubspot_entities_to_cachemanage_hubspot_cache | Bulk loading, caching, and performance optimization |
A complete documentation of the tools can be found here : Tools documentation
⚡ Usage Examples
Once fully installed and configured (following the complete installation guides), use natural language phrases with your MCP client:
🗣️ Natural Language Queries
- "List my HubSpot contacts"
- "Find tech sector companies"
- "Show current deals"
- "Create a new deal for Project X"
- "Search for the 'Project X' deal"
- "What contact properties are available?"
🤖 AI-Powered Semantic Search
- "Find software engineers" → matches "Developer", "Programmer", "Software Architect"
- "Search for enterprise clients" → finds large companies without exact keywords
- "Technology companies in Paris" → contextual location and industry search
A complete documentation of the differents usage can be found here : Usage examples
📚 Documentation Table of Contents
🚀 Getting Started
| Section | Description |
|---|---|
| Client Integration | Complete Guide for MCP Client Integration |
| Claude Desktop Integration | Complete guide for stdio and SSE modes with Claude Desktop |
🔧 Extra Features
| Section | Description |
|---|---|
| Semantic Search | AI-powered semantic search capabilities and usage |
| Cache System | How the shared TTL cache works and how to manage it |
| SSE Endpoints | REST API endpoints for health monitoring and data management |
🛠️ Development and Testing
| Section | Description |
|---|---|
| Developer Guide | Testing, quality assurance, and development workflow |
| MCP Inspector | Visual debugging and testing with MCP Inspector |
| Troubleshooting | Common issues and solutions |
| Integration Testing | Comprehensive testing procedures |
| Local Installation (stdio) | Install and run locally |
| Remote Deployment (SSE) | Deploy to Kubernetes for production use |
| Environment Setup | Advanced environment configuration |
📋 Quality Assurance: Pre-commit hooks ensure automatic code formatting, documentation linting, and broken link checking on every commit. Install with just install-dev.
🤝 Contributing
Check the contributing guide for:
- Development standards
- Tool creation process
- Code and testing conventions
- Git workflow and semantic versioning
📄 License
This project is licensed under the MIT License - see the LICENSE file for details.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.