Delete a space and all its contents
AI agents call delete_space to permanently remove resources in Dart MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently deletes an entire space and all its nested contents without reversibility. This is a destructive operation that cannot be undone, affecting potentially numerous documents, folders, and tasks. The blast radius is critical as an AI agent with access to this tool could accidentally or maliciously wipe out entire workspaces.
From the tool's definition Tool name 'delete_space' combined with description 'Delete a space and all its contents' explicitly indicates irreversible deletion of potentially large amounts of data.
Attacks that exploit this kind of access
Delete a space and all its contents. It is categorised as a Destructive tool in the Dart MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Dart MCP Server MCP server in PolicyLayer and add a rule for delete_space: 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 Dart MCP Server. Nothing to install.
delete_space 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 delete_space 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 delete_space. 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.
delete_space is provided by the Dart MCP Server MCP server (jmanhype/dart-mcp-server). 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 →