Bulk-import contacts from a .vcf file inside ALLOWED_ROOTS.
AI agents use import_vcard 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 data in bulk (Write category). Severity is medium because: (1) it's scoped to ALLOWED_ROOTS, limiting blast radius, (2) contact data is typically non-financial and reversible, and (3) it doesn't execute arbitrary code or delete data.
From the tool's definition Tool performs 'Bulk-import contacts' which creates/adds new contact records into the system. The verb 'import' combined with 'from a .vcf file' indicates data creation/population rather than deletion or execution of arbitrary code.
Attacks that exploit this kind of access
Bulk-import contacts from a .vcf file inside ALLOWED_ROOTS. 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 import_vcard: 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.
import_vcard 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 import_vcard 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 import_vcard. 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.
import_vcard 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 →