AI agents use update_contact to create or update resources in macOS Contacts MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your macOS Contacts MCP environment.
This tool modifies contact information (reversibly). It does not delete data (Destructive), execute arbitrary code (Execute), move money (Financial), or merely read (Read). The severity is medium because contact information modification could affect communication or business relationships, but the impact is limited to a user's local contact data and changes are reversible.
From the tool's definition Tool name 'update_contact' and description 'Update an existing contact' indicate modification of existing data in the Contacts app.
Documented attack patterns abuse exactly the kind of access update_contact gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and macOS Contacts MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for update_contact:
{
"version": "1",
"default": "deny",
"tools": {
"update_contact": {
"limits": [
{
"counter": "update_contact_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update_contact stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Update an existing contact. It is categorised as a Write tool in the macOS Contacts MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the macOS Contacts MCP server in PolicyLayer and add a rule for 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 macOS Contacts MCP. Nothing to install.
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 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 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.
update_contact is provided by the macOS Contacts MCP server (jcontini/macos-contacts-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from macOS Contacts MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
5 macOS Contacts MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.