Fetch full contact card(s) by ID.
AI agents call contacts_get_contact 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 contact information by ID without any capability to modify, delete, or execute operations. It is a straightforward read operation on contact data. While contact information can be sensitive (names, email addresses, phone numbers), the read-only nature and the caller's need to already know the contact ID limits the blast radius.
From the tool's definition Tool name 'contacts_get_contact' and description 'Fetch full contact card(s) by ID' indicate data retrieval with no modification or deletion. The verb 'Fetch' is explicitly a read-only operation.
Attacks that exploit this kind of access
Fetch full contact card(s) by ID. 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_get_contact: 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_get_contact 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_get_contact 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_get_contact. 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_get_contact 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 →