Modify a contact. fields keys: names (str), emails (list[str]), phones (list[str]), notes (str).
AI agents use update_contact to create or update resources in Nexus Core — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Nexus Core environment.
This tool creates or modifies contact information in what appears to be a personal assistant framework. While modifications are reversible (contacts can be updated again or deleted separately), incorrect updates could corrupt contact data or overwrite important information.
From the tool's definition Tool modifies contact data with fields for names, emails, phones, and notes. Description explicitly states 'Modify a contact' indicating reversible data mutation.
Attacks that exploit this kind of access
Modify a contact. fields keys: names (str), emails (list[str]), phones (list[str]), notes (str). It is categorised as a Write tool in the Nexus Core MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Nexus Core 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 Nexus Core. 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 Nexus Core MCP server (noumenon-ai/nexus-core). 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 →