Remove an installed package and drop it from retrieval.
AI agents call uninstall_semantic_package to permanently remove resources in TalkDB — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently deletes an installed semantic package and its associated data from the system. The use of 'drop' (a database/system term implying irreversible removal) and the irreversible nature of uninstalling packages with data cleanup classifies this as Destructive rather than Write.
From the tool's definition 'Remove an installed package and drop it from retrieval' — the word 'drop' combined with 'remove' indicates irreversible deletion of package data.
Attacks that exploit this kind of access
Remove an installed package and drop it from retrieval. It is categorised as a Destructive tool in the TalkDB MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the TalkDB MCP server in PolicyLayer and add a rule for uninstall_semantic_package: 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 TalkDB. Nothing to install.
uninstall_semantic_package 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 uninstall_semantic_package 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 uninstall_semantic_package. 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.
uninstall_semantic_package is provided by the TalkDB MCP server (nitin-gupta1109/talkdb). 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 →