Delete multiple context entries by their IDs
AI agents call delete_contexts_batch to permanently remove resources in Context MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly removes data in bulk. Deletion is the hallmark of the Destructive category, which ranks higher than Write (reversible modifications). The batch operation increases severity from what a single delete might pose, as it can remove large volumes of stored context in one call.
From the tool's definition Tool name contains 'delete' and description states 'Delete multiple context entries by their IDs'. The batch operation amplifies the destructive impact by enabling deletion of many records at once.
Attacks that exploit this kind of access
Delete multiple context entries by their IDs. It is categorised as a Destructive tool in the Context MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Context MCP server in PolicyLayer and add a rule for delete_contexts_batch: 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 Context MCP. Nothing to install.
delete_contexts_batch 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_contexts_batch 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_contexts_batch. 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_contexts_batch is provided by the Context MCP server (raunak-dev-18/context-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 →