AI agents call hs_pipeline_summary 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.
The tool performs data retrieval and aggregation only. It queries existing pipeline data to produce a funnel snapshot summary, with no side effects, data modification, execution of external operations, or deletion. This is characteristic of a Read operation with minimal security risk even if misused by an AI agent.
From the tool's definition Tool retrieves and aggregates deal counts and amounts by pipeline stage — a read-only query operation that returns summary statistics without modifying, executing, or destructively altering any data.
Attacks that exploit this kind of access
Deal counts and total amounts aggregated by pipeline stage — a quick funnel snapshot for a given pipeline. 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_pipeline_summary: 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_pipeline_summary 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_pipeline_summary 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_pipeline_summary. 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_pipeline_summary 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 →