AI agents call hs_search_contacts 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 is a retrieval/query operation with no side effects. It searches and returns contact information without creating, modifying, or deleting data. The blast radius of misuse is limited to unauthorized information disclosure of existing contact records, which is a low-severity data confidentiality risk but not operationally destructive.
From the tool's definition Tool name 'hs_search_contacts' and description explicitly states 'Full-text search across contacts' with no mention of modification, deletion, or external operations. Performs query-only operations on contact data.
Attacks that exploit this kind of access
Full-text search across contacts by name, email, company, or any indexed field. 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_search_contacts: 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_search_contacts 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_search_contacts 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_search_contacts. 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_search_contacts 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 →