Drop a channel's pinned session so the next dispatch starts a
AI agents call reset_channel to permanently remove resources in Claude Bridge — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The 'drop' operation permanently removes a channel's pinned session, making this a destructive action. While not data deletion in the traditional sense, it irreversibly clears session state that likely cannot be recovered. This is more severe than Write (which is reversible) and qualifies as Destructive.
From the tool's definition Tool name 'reset_channel' combined with description 'Drop a channel's pinned session' uses the word 'drop', which indicates irreversible deletion or clearing of state. The action cannot be undone and affects the channel's persistent session state.
Attacks that exploit this kind of access
Drop a channel's pinned session so the next dispatch starts a. It is categorised as a Destructive tool in the Claude Bridge MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Claude Bridge MCP server in PolicyLayer and add a rule for reset_channel: 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 Bridge. Nothing to install.
reset_channel 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_channel 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_channel. 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_channel is provided by the Claude Bridge MCP server (josiahsiegel/claude-bridge). 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 →