hubspot.props.drift
AI agents call hubspot.props.drift to retrieve information from G Gremlin Hubspot without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name and server context suggest it performs drift analysis (comparison of property changes over time), which is a read operation that queries existing data. While the description is empty and reduces confidence slightly, the server's stated capability of 'property drift analysis' and the naming pattern (drift, not drift.apply or drift.fix) strongly indicate data retrieval.
From the tool's definition Tool name 'hubspot.props.drift' combined with server description mentioning 'property drift analysis' indicates this retrieves or analyzes property drift data without modifying records.
Attacks that exploit this kind of access
hubspot.props.drift. It is categorised as a Read tool in the G Gremlin Hubspot MCP Server, which means it retrieves data without modifying state.
Register the G Gremlin Hubspot MCP server in PolicyLayer and add a rule for hubspot.props.drift: 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 G Gremlin Hubspot. Nothing to install.
hubspot.props.drift 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 hubspot.props.drift 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 hubspot.props.drift. 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.
hubspot.props.drift is provided by the G Gremlin Hubspot MCP server (mikeheilmann1024/g-gremlin-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 →