contacts_update_contact
AI agents use contacts_update_contact to create or update resources in Pyfastmail — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Pyfastmail environment.
This tool updates contact information in a Fastmail account, which is a Write operation—it modifies data but does not irreversibly delete it. Severity is high because contact data often includes PII (personal identifiable information), and unauthorized modification could compromise user privacy or enable social engineering.
From the tool's definition Tool name 'contacts_update_contact' and sibling tool 'contacts_create_contact' and 'contacts_delete_contact' indicate a contacts management suite; 'update' modifies contact data reversibly.
Attacks that exploit this kind of access
contacts_update_contact. It is categorised as a Write tool in the Pyfastmail MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Pyfastmail MCP server in PolicyLayer and add a rule for contacts_update_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_update_contact is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the contacts_update_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_update_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_update_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 →