AI agents use resolve_contacts to create or update resources in VibeMCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your VibeMCP environment.
An AI agent can call resolve_contacts faster than any human can review — one bad instruction and it creates or modifies resources in VibeMCP by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
Resolve email addresses to display names using the account contacts. Useful for enriching email threads with sender names. It is categorised as a Write tool in the VibeMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Vibe MCP server in PolicyLayer and add a rule for resolve_contacts: 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 VibeMCP. Nothing to install.
resolve_contacts 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 resolve_contacts 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 resolve_contacts. 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.
resolve_contacts is provided by the Vibe MCP server (vibetensor/vibemcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.