reset_team
AI agents call reset_team to permanently remove resources in Claude Team MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The name 'reset_team' strongly suggests resetting the team's state, configuration, memory, or coordination data. In the context of a multi-agent coordination server that manages tasks, assignments, memory (brain_*), and backups, a reset operation is likely destructive and potentially irreversible. However, the empty description significantly lowers confidence — it could be a soft reset or reconfiguration.
From the tool's definition Tool name 'reset_team' implies resetting team state, which could be irreversible; description is empty and uninformative.
Attacks that exploit this kind of access
reset_team. It is categorised as a Destructive tool in the Claude Team MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Claude Team MCP server in PolicyLayer and add a rule for reset_team: 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 Claude Team MCP. Nothing to install.
reset_team is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the reset_team 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 reset_team. 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.
reset_team is provided by the Claude Team MCP server (lakshan12367/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 →