AI agents call hs_get_workflow to retrieve information from Hubspot without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries workflow configuration details (triggers, actions, settings) without modifying or executing any workflows. It has no side effects on the CRM system. While workflows can be sensitive business logic, merely viewing their details poses minimal risk compared to creating, executing, or deleting workflows. Classified as Read with low severity.
From the tool's definition Tool name 'hs_get_workflow' and description 'Get full details of a workflow' — the verb 'get' and phrase 'Get full details' indicate read-only retrieval of workflow configuration data.
Attacks that exploit this kind of access
Get full details of a workflow including enrollment triggers, actions, and settings. It is categorised as a Read tool in the Hubspot MCP Server, which means it retrieves data without modifying state.
Register the Hubspot MCP server in PolicyLayer and add a rule for hs_get_workflow: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Hubspot. Nothing to install.
hs_get_workflow is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the hs_get_workflow rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for hs_get_workflow. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
hs_get_workflow is provided by the Hubspot MCP server (zleventer/hubspot-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →