end_conversation · Copilot Studio Agent Direct Line MCP

WHAT IT DOES

What end_conversation does on Copilot Studio Agent Direct Line

AI agents use end_conversation to create or update resources in Copilot Studio Agent Direct Line — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Copilot Studio Agent Direct Line environment.

WHY IT NEEDS A POLICY

Why end_conversation needs a policy

This tool modifies the state of an active conversation by ending it and cleaning up associated resources. While it terminates a conversation, this is a normal cleanup operation that is conceptually reversible (a new conversation can be started). It does not permanently delete data or have irreversible consequences. The blast radius is minimal - ending one conversation affects only that session's state.

From the tool's definition Tool performs 'end' and 'clean up resources' actions - modifying/terminating a conversation state, which is a reversible write operation rather than destructive deletion

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

end_conversation Rate-limited

end_conversation stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "end_conversation": {
      "limits": [
        {
          "counter": "end_conversation_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Copilot Studio Agent Direct Line, so you can run agents against it safely.

FAQ

Questions about end_conversation

What does the end_conversation tool do? +

End an existing conversation and clean up resources. It is categorised as a Write tool in the Copilot Studio Agent Direct Line MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on end_conversation? +

Register the Copilot Studio Agent Direct Line MCP server in PolicyLayer and add a rule for end_conversation: 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 Copilot Studio Agent Direct Line. Nothing to install.

What risk level is end_conversation? +

end_conversation is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit end_conversation? +

Yes. Add a rate_limit block to the end_conversation 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 end_conversation completely? +

Set action: deny in the PolicyLayer policy for end_conversation. 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 end_conversation? +

end_conversation is provided by the Copilot Studio Agent Direct Line MCP server (swigerb/copilot-studio-agent-direct-line-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.