This record as markdown: /tools/io-github-devopam-mcpg/drop-publication.md
What drop_publication does on Mcpg
AI agents call drop_publication to permanently remove resources in Mcpg, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why drop_publication is rated Critical
The tool name 'drop_publication' directly indicates deletion of a database publication object. Despite the empty description, the semantic meaning of 'drop' in PostgreSQL context is unambiguous—it permanently removes objects. This is a destructive operation affecting database infrastructure and replication configuration.
From the tool's definition Tool name is 'drop_publication' which contains the verb 'drop', a SQL operation that irreversibly removes database objects.
Attacks that exploit this kind of access
The rule that runs drop_publication safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Mcpg, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For drop_publication, this is the rule to start with:
drop_publication is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Mcpg, apply this rule, and every drop_publication call is checked against it from then on.
Questions about drop_publication
drop_publication is a destructive tool on the Mcpg MCP server. It is categorised as a Destructive tool in the Mcpg MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mcpg MCP server in PolicyLayer and add a rule for drop_publication: 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 Mcpg. Nothing to install.
drop_publication 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 drop_publication 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 drop_publication. 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.
drop_publication is provided by the Mcpg MCP server (pypi:mcpg). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Mcpg, and thousands of servers like it.
Across the catalogue