conversation-manage · MCP LLM Generator v2 MCP

WHAT IT DOES

What conversation-manage does on MCP LLM Generator v2

AI agents call conversation-manage to permanently remove resources in MCP LLM Generator v2 — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

WHY IT NEEDS A POLICY

Why conversation-manage needs a policy

The tool explicitly supports 'delete' and 'clear' operations on conversations, which are irreversible destructive actions. While 'list' is a read operation, the most severe applicable category must be chosen. Deleting or clearing conversations could permanently remove conversation history and context data, representing a high blast radius if misused by an AI agent.

From the tool's definition Manage conversations within contexts (list, delete, clear)

Attacks that exploit this kind of access

Questions about conversation-manage

What does the conversation-manage tool do? +

Manage conversations within contexts (list, delete, clear). It is categorised as a Destructive tool in the MCP LLM Generator v2 MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on conversation-manage? +

Register the MCP LLM Generator v2 MCP server in PolicyLayer and add a rule for conversation-manage: 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 MCP LLM Generator v2. Nothing to install.

What risk level is conversation-manage? +

conversation-manage is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit conversation-manage? +

Yes. Add a rate_limit block to the conversation-manage 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.

How do I block conversation-manage completely? +

Set action: deny in the PolicyLayer policy for conversation-manage. 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.

What MCP server provides conversation-manage? +

conversation-manage is provided by the MCP LLM Generator v2 MCP server (mako10k/mcp-llm-generator). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.