End the voice conversation by saying goodbye and stopping the browser interface
AI agents invoke end_conversation to trigger actions in Jarvis MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes browser-side operations: it stops the browser interface and triggers a 'goodbye' speech output. It is not a simple read or write — it actively controls browser state and produces audio output, making Execute the most appropriate category. Severity is medium because misuse could disrupt an ongoing voice session but has limited broader blast radius.
From the tool's definition 'End the voice conversation by saying goodbye and stopping the browser interface' — triggers external browser actions (stopping the interface) and performs an automated speech action
Documented attack patterns abuse exactly the kind of access end_conversation gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Jarvis MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for end_conversation:
{
"version": "1",
"default": "deny",
"tools": {
"end_conversation": {
"limits": [
{
"counter": "end_conversation_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}end_conversation stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
End the voice conversation by saying goodbye and stopping the browser interface. It is categorised as a Execute tool in the Jarvis MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Jarvis 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 Jarvis MCP. Nothing to install.
end_conversation is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
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.
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.
end_conversation is provided by the Jarvis MCP server (shantur/jarvis-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 5 Jarvis MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
5 Jarvis MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.