This record as markdown: /tools/1mcp-app-agent/mcp-uninstall.md
What mcp_uninstall does on 1MCP Server
AI agents call mcp_uninstall to permanently remove resources in 1MCP Server, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why mcp_uninstall is rated Critical
Uninstalling an MCP server is a destructive operation that cannot be reversed without re-installing. While not as severe as deleting user data, removing infrastructure components that other tools depend on constitutes a destructive action with potential to disrupt service availability.
From the tool's definition The tool 'mcp_uninstall' is explicitly described as 'Remove an MCP server', which irreversibly deletes or uninstalls a server instance. This action cannot be easily undone and results in the permanent removal of a server configuration.
Attacks that exploit this kind of access
The rule that runs mcp_uninstall safely
PolicyLayer is an MCP gateway: it sits between your AI agents and 1MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For mcp_uninstall, this is the rule to start with:
mcp_uninstall 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 1MCP Server, apply this rule, and every mcp_uninstall call is checked against it from then on.
Questions about mcp_uninstall
Remove an MCP server. It is categorised as a Destructive tool in the 1MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the 1MCP Server MCP server in PolicyLayer and add a rule for mcp_uninstall: 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 1MCP Server. Nothing to install.
mcp_uninstall 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 mcp_uninstall 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 mcp_uninstall. 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.
mcp_uninstall is provided by the 1MCP Server MCP server (1mcp-app/agent). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on 1MCP Server, and thousands of servers like it.
Across the catalogue