add_conversation_reply · SparrowDesk MCP: Risk & Policy

WHAT IT DOES

What add_conversation_reply does on SparrowDesk

AI agents use add_conversation_reply to create or update resources in SparrowDesk — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your SparrowDesk environment.

WHY IT NEEDS A POLICY

Why add_conversation_reply needs a policy

This tool creates or appends data (a reply or note) to a conversation without deleting or overwriting existing data, and does not execute arbitrary code or move financial resources. It is reversible (replies can typically be edited or removed in ticketing systems).

From the tool's definition Tool description explicitly states 'Add a reply or internal note to a conversation' — this creates new content (reply/note) within an existing ticket/conversation, modifying the state reversibly.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

add_conversation_reply Rate-limited

add_conversation_reply 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": {
    "add_conversation_reply": {
      "limits": [
        {
          "counter": "add_conversation_reply_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 SparrowDesk, so you can run agents against it safely.

FAQ

Questions about add_conversation_reply

What does the add_conversation_reply tool do? +

Add a reply or internal note to a conversation (also called a ticket) in SparrowDesk. It is categorised as a Write tool in the SparrowDesk MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on add_conversation_reply? +

Register the SparrowDesk MCP server in PolicyLayer and add a rule for add_conversation_reply: 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 SparrowDesk. Nothing to install.

What risk level is add_conversation_reply? +

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

Can I rate-limit add_conversation_reply? +

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

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

add_conversation_reply is provided by the SparrowDesk MCP server (sparrowdesk/sparrowdesk-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.