Delete a key (auth key, OAuth client, or federated identity). This is irreversible. For auth keys, devices already authenticated are unaffected but no new devices can use it. For OAuth clients and federated identities, any integrations using them lose access immediately.
Part of the Tailscale MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents may call tailscale_delete_key to permanently remove or destroy resources in Tailscale. Without a policy, an autonomous agent could delete critical data in a loop with no way to undo the damage. Intercept blocks destructive tools by default and requires explicit human approval before enabling them.
Without a policy, an AI agent could call tailscale_delete_key in a loop, permanently destroying resources in Tailscale. There is no undo for destructive operations. Intercept blocks this tool by default and only allows it when a human explicitly approves the action.
Destructive tools permanently remove data. Block by default. Only enable with explicit approval workflows.
tools:
tailscale_delete_key:
rules:
- action: deny
reason: "Blocked by default — enable with approval"See the full Tailscale policy for all 89 tools.
Agents calling destructive-class tools like tailscale_delete_key have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Destructive risk category across the catalogue. The same policy patterns (deny, require_approval) apply to each.
tailscale_delete_key is one of the critical-risk operations in Tailscale. For the full severity-focused view — only the critical-risk tools with their recommended policies — see the breakdown for this server, or browse all critical-risk tools across every MCP server.
Delete a key (auth key, OAuth client, or federated identity). This is irreversible. For auth keys, devices already authenticated are unaffected but no new devices can use it. For OAuth clients and federated identities, any integrations using them lose access immediately.. It is categorised as a Destructive tool in the Tailscale MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Add a rule in your Intercept YAML policy under the tools section for tailscale_delete_key. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Tailscale MCP server.
tailscale_delete_key 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 tailscale_delete_key rule in your Intercept 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 Intercept policy for tailscale_delete_key. 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.
tailscale_delete_key is provided by the Tailscale MCP server (@yawlabs/tailscale-mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.