MCP server
HubSpot MCP server
HubSpot's official hosted MCP server lets AI search and manage CRM records, query CRM data and work with marketing emails, pages and posts.
- Official server
- CRM and sales
Why it matters
What it does and why it matters
HubSpot is the CRM and marketing platform for a great many small and mid-size businesses. Its official hosted MCP server lets an assistant search contacts, companies, deals and other records, create and update them, query CRM data, read campaign attribution and work with marketing emails, landing pages and blog posts.
For sales teams, that means "what is the history with this account" and "create a follow-up task for Tuesday" in plain English. For marketing, it means drafts and reports without switching tools.
The server is in production at review time and signs in through HubSpot, so it follows the user's permissions. Record changes happen in your live CRM, so we start with search and reporting and add create and update actions for narrow, tested tasks.
Use cases
Best business use cases
Account briefs
Pipeline questions
Marketing drafts
Tools
Available tools
Tool names as published by the maintainer at review time. Versions change, so check the repository for the current list.
Read and write: Read and write: CRM records (contacts, companies, deals, tickets, engagements), marketing emails, landing pages and blog posts. Sensitive data properties excluded.
-
get_user_detailsReturn the signed-in user, account and access levels.
-
search_crm_objectsSearch and filter CRM records.
-
manage_crm_objectsCreate or update CRM records, with user confirmation.
-
query_crm_dataQuery CRM data with SQL plus HubSpot extensions.
-
get_campaign_attribution_reportsGet revenue and deal attribution data.
-
manage_marketing_emailCreate and update marketing email drafts.
-
manage_landing_pageCreate and publish landing pages.
-
manage_blog_postCreate and publish blog posts.
-
tool_guidanceGet usage instructions for any tool.
Workflows
Example workflows
After-call CRM update
-
1
Paste the call notes.
-
2
The assistant finds the contact and deal.
-
3
It drafts a note and next steps.
-
4
You approve the update.
-
5
It saves the note and creates a task.
Weekly pipeline check
-
1
Ask for deals with no activity in 14 days.
-
2
The assistant queries the CRM.
-
3
It lists deals and owners.
-
4
It drafts nudges for owners.
-
5
Managers review and send.
Prompts
Example prompts
“Summarize everything about Harbor Group in HubSpot before my call.”
“Which deals in the proposal stage have had no activity for two weeks?”
“Create a follow-up task for next Tuesday on this deal.”
Setup
Installation and configuration
Examples for Claude Desktop and Claude Code. Replace the placeholder values with your own keys, and store secrets outside version control.
Claude Code: terminal
claude mcp add --transport http --client-id YOUR_CLIENT_ID --client-secret --callback-port 8080 hubspot https://mcp.hubspot.com- Hosted server: https://mcp.hubspot.com.
- Needs: OAuth 2.0 with PKCE. Create an MCP connector in HubSpot (Development > MCP Connectors), set redirect URLs, and use its Client ID and Secret..
Security
Security considerations
-
Right user, right access
Connect with a user whose CRM role fits the task, not an admin.
-
Start read-only
Begin with lookups. Add create and update actions one at a time.
-
Customer data
Limit which objects and properties the user can see.
-
Audit changes
Review records changed through the assistant, especially in the first weeks.
Related servers
Servers that pair well with it
Salesforce
Salesforce's official DX MCP server lets AI query data with SOQL, manage orgs and metadata, run tests and assign permission sets.
Pipedrive
Pipedrive's official hosted MCP server, in beta, lets AI search deals, people, organizations and leads, and create and update records.
Gmail
Google's own Gmail MCP server lets AI search and read threads, manage labels and create drafts. It has no send tool.
Keep exploring
Solutions and services that use it
Related services
View all related services- MCP integration Connect AI assistants to your CRM, files, databases and tools through Model Context Protocol servers, with safe permissions.
- CRM integration Connect your CRM to forms, email, billing and support so customer records stay complete without typing.
- AI agents AI that takes actions in your systems, such as qualifying leads or processing requests, with people checking the results.
- AI Product Development AI agents, knowledge assistants, copilots and document automation built into the way your team already works.
- Automation and Integrations CRM, payment and API integrations, MCP connections and workflows that stop people copying data by hand.
- Landing pages Single-purpose pages for a campaign, a launch or a product, built to load fast and test quickly.
Solutions
View all solutions- AI lead qualification Score, research and route every new inquiry so your team talks to the best leads first.
- AI sales research agent Short, sourced briefings on each prospect before a call, drafted by an AI agent from public information and your CRM.
- Automated quoting Draft accurate quotes and proposals from a request, your price rules and past work, for a person to approve.
- Email triage Sort a shared inbox by topic and urgency, pull out the key details and draft replies for a person to send.
- Meeting notes automation Transcribe meetings and calls, summarize decisions and push action items into your CRM or project tool.
- AI automation and integrations Connect the tools you already use so data moves once, correctly, and AI reads the parts that arrive as text or documents.
Industries
View all industries- Real estate Listing sites, lead handling, CRM automation and document workflows for agencies, brokers and developers.
- Professional services Client portals, proposal drafting, knowledge assistants and internal tools for consultancies, agencies and firms.
- Marketing agencies Landing pages, content workflows, client reporting and white-label development capacity for marketing agencies.
- Recruiting and staffing Candidate screening assistants, ATS integrations, interview notes and onboarding automation for recruiters and staffing firms.
Guides and articles
View all guides and articles- What are AI agents and how do businesses use them? What AI agents are, real business uses, the controls they need and how to start with one safely.
- How to connect AI to your CRM Connect AI assistants to HubSpot, Salesforce or other CRMs safely, with the tasks worth automating first.
- How to build an AI workflow with MCP servers Plan, connect and test an AI workflow that uses MCP servers, from a single task to a reliable process.
- AI chatbot vs AI agent What separates a chatbot that answers from an agent that acts, and when you need each.
- What is the Model Context Protocol? A business guide to MCP: what it is, how MCP servers work, who supports it and how to start using it.
AI models
View all ai models- Claude Fable 5.1 The top tier of the Claude family, for the most demanding reasoning and long-horizon agent work, priced above Opus.
- Claude Opus 5.5 Anthropic's recommended starting point for most serious work: long-running agentic coding and knowledge work, with a 1M token context window.
- GPT-6 Astra OpenAI's most capable model, built for the hardest end-to-end work: complex reasoning, coding, computer use and research.
- DeepSeek V4 Pro DeepSeek's model for demanding reasoning and agent work, with thinking effort levels, tool calling, JSON output and a 1 million token window.
- Grok 4.7 xAI's current flagship for coding, agent tasks and knowledge work, with image input, tool calling, structured outputs, reasoning effort levels and a 500K window.
Glossary terms
View all glossary terms- CRM A CRM, or customer relationship management system, stores contacts, companies, deals and interactions so a team can manage its customer relationships in one place.
- AI agent An AI agent is software that uses a language model to plan steps, call tools and act toward a goal, instead of only answering one question.
- MCP server An MCP server is a program or hosted service that exposes a system's data and actions as tools that AI assistants can use through the Model Context Protocol.
- Model Context Protocol The Model Context Protocol, or MCP, is an open standard for connecting AI assistants to external tools and data in a consistent way.
- Tool calling Tool calling is when an AI model asks the application to run a tool, such as a search or database lookup, and then uses the result in its answer.
FAQ
Questions people ask us
Have a question that is not here? Ask us directly.
Yes. HubSpot hosts it, and it was in production at review time.
Yes, it can create and update records. Start with read-only tasks.
Yes. It can work with marketing emails, landing pages and blog posts.