Learn how you can build agent tools to customize the HubSpot agent experience.
Last modified: September 3, 2025
In HubSpot, you can create an AI agent that will perform various actions based on your instructions. For example, you can create an agent to send an email to you every morning with notes about the day’s upcoming meetings.To perform tasks, agents rely on agent tools. Tools are like functions in a programming language: they have parameters you pass into the tool, and the tool returns an output. Tools in HubSpot are similar to the concept of tools in MCP (Model Context Protocol). An agent tool will package API calls, LLM steps, and other supporting context to enable the AI to do the job. Tools are designed to perform specific, well-defined tasks, such as querying a database, performing CRUD (Create, Read, Update, Delete) operations, or using generative AI to summarize content.In implementation terms, an agent tool is an enhanced version of a custom workflow action, which you’ll build using HubSpot’s developer project framework.
When building agent tools, keep in mind that they serve two audiences:
AI agents that need clear, unambiguous descriptions to understand when and how to use the tool
Human users (when the tool is also supported in workflows, and also in the “add tool” interface when configuring an agent) who need intuitive labels and descriptions for manual configuration.
If your agent tool is also supported in workflows, human users will interact directly with your tool’s labels and field descriptions when setting up workflow actions. Ensure these are clear and user-friendly for manual configuration.
Note the following limits at this time of the beta:
The agent does not have access to CRM data unless explicitly given tools to get that data.
The agent can’t request information from the user after it’s invoked if given insufficient information to complete the task.