contacts_query_contacts
AI agents call contacts_query_contacts to retrieve information from Pyfastmail without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Query operations retrieve data without modification. However, severity is elevated to 'high' due to the context: this tool accesses Fastmail account contact data, which is personally identifiable information (PII) with significant sensitivity. Even read-only access to complete contact lists represents a meaningful privacy and security risk if misused by an AI agent.
From the tool's definition Tool name 'contacts_query_contacts' contains 'query' which indicates a retrieval operation. Sibling tools in the contacts namespace include create, delete, and get operations, positioning this as a read/search tool. The empty description limits certainty.
Attacks that exploit this kind of access
contacts_query_contacts. It is categorised as a Read tool in the Pyfastmail MCP Server, which means it retrieves data without modifying state.
Register the Pyfastmail MCP server in PolicyLayer and add a rule for contacts_query_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 Pyfastmail. Nothing to install.
contacts_query_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 contacts_query_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 contacts_query_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.
contacts_query_contacts is provided by the Pyfastmail MCP server (pjosols/pyfastmail-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 →