Delete a scheme by ID.
AI agents call delete_scheme to permanently remove resources in Government Scheme MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool permanently removes government scheme records from the system without possibility of recovery. This is inherently destructive as deletion cannot be undone. The high severity reflects that loss of authoritative government scheme data could disrupt public access to critical information and administrative functions, though the blast radius is somewhat contained compared to financial systems.
From the tool's definition Tool name 'delete_scheme' and description 'Delete a scheme by ID' explicitly perform irreversible deletion of data.
Attacks that exploit this kind of access
Delete a scheme by ID. It is categorised as a Destructive tool in the Government Scheme MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Government Scheme MCP Server MCP server in PolicyLayer and add a rule for delete_scheme: 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 Government Scheme MCP Server. Nothing to install.
delete_scheme 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_scheme 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_scheme. 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_scheme is provided by the Government Scheme MCP Server MCP server (magicstack-llp/gov-scheme-mcp-py). 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 →