Get active WhatsApp conversations. Args: instance_name, conversation_type filter, limit. Returns: list of active chats.
AI agents call my_conversations to retrieve information from Automagik Tools without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves WhatsApp conversation metadata (active chats) without creating, modifying, deleting, or executing operations. The arguments (instance_name, conversation_type filter, limit) are all read-only filtering/pagination parameters. The blast radius of misuse is minimal—an attacker gains visibility into conversation structure but cannot alter data, execute code, or cause destructive effects.
From the tool's definition Tool returns a list of active WhatsApp conversations with no mutation capabilities. The description explicitly states 'Get' and 'Returns: list', indicating data retrieval only.
Documented attack patterns abuse exactly the kind of access my_conversations gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Automagik Tools, and nothing reaches the server without passing your rules. This is the rule we recommend for my_conversations:
{
"version": "1",
"default": "deny",
"tools": {
"my_conversations": {}
}
}my_conversations is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get active WhatsApp conversations. Args: instance_name, conversation_type filter, limit. Returns: list of active chats. It is categorised as a Read tool in the Automagik Tools MCP Server, which means it retrieves data without modifying state.
Register the Automagik Tools MCP server in PolicyLayer and add a rule for my_conversations: 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 Automagik Tools. Nothing to install.
my_conversations is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the my_conversations 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 my_conversations. 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.
my_conversations is provided by the Automagik Tools MCP server (namastexlabs/automagik-tools). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Automagik Tools, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
122 Automagik Tools tools catalogued and risk-classified — across an index of 43,000+ MCP servers.