AI agents call hubspot_pipelines to retrieve information from Access without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only query tool that retrieves pipeline configuration data from HubSpot without modifying, creating, deleting, or executing any operations. It serves purely to enumerate valid identifiers needed by other tools. The low severity reflects minimal blast radius if misused by an agent—worst case, it returns existing pipeline information already accessible to a HubSpot user with API credentials.
From the tool's definition Tool description explicitly states 'List all HubSpot deal pipelines' — a retrieval operation with 'no side effects' that returns metadata (pipelines, stages, stage IDs, display order) for reference purposes.
Attacks that exploit this kind of access
List all HubSpot deal pipelines with their stages, stage IDs, and display order. Use this to get valid pipeline and stage IDs before creating deals with hubspot_create_deal. It is categorised as a Read tool in the Access MCP Server, which means it retrieves data without modifying state.
Register the Access MCP server in PolicyLayer and add a rule for hubspot_pipelines: 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 Access. Nothing to install.
hubspot_pipelines 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_pipelines 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_pipelines. 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_pipelines is provided by the Access MCP server (scottpedia0/access). 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 →