contacts_list
AI agents call contacts_list 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.
This tool retrieves and lists contact data from a Fastmail address book. It performs no modifications, deletions, or external operations—purely a data query operation. The severity is low because reading contact metadata has minimal blast radius (exposure of names, emails, phone numbers), though accessing sensitive contact information could have moderate implications.
From the tool's definition Tool name 'contacts_list' and sibling tools like 'contacts_get_contact', 'contacts_create_contact', 'contacts_delete_contact' establish this is a contact management tool. The 'list' suffix indicates retrieval/enumeration of contacts without modification.
Attacks that exploit this kind of access
contacts_list. 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_list: 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_list 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_list 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_list. 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_list 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 →