Stop the bot from transcribing a live meeting. Replicates the exact same flow the Gantta web app uses when a user clicks the Stop button: (1) POST /api/bot/stop/<session_id> halts audio capture, (2) RPC meeting_ai.finalize_meeting transitions the meeting status from RECORDING to PENDING. No summa...
Part of the Gantta server.
Free to start. No card required.
AI agents invoke bot_stop_meeting to trigger processes or run actions in Gantta. Execute operations can have side effects beyond the immediate call -- triggering builds, sending notifications, or starting workflows. Rate limits and argument validation are essential to prevent runaway execution.
bot_stop_meeting can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. PolicyLayer enforces rate limits and validates arguments to keep execution within safe bounds.
Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.
{
"version": "1",
"default": "deny",
"tools": {
"bot_stop_meeting": {
"limits": [
{
"counter": "bot_stop_meeting_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}See the full Gantta policy for all 26 tools.
These attack patterns abuse exactly the kind of access bot_stop_meeting gives an agent. Each links to the full case and the policy that stops it:
Other execute tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Stop the bot from transcribing a live meeting. Replicates the exact same flow the Gantta web app uses when a user clicks the Stop button: (1) POST /api/bot/stop/<session_id> halts audio capture, (2) RPC meeting_ai.finalize_meeting transitions the meeting status from RECORDING to PENDING. No summary is generated here — the AI client can separately call get_meeting to read the transcript and present it to the user in chat. Meeting stays at PENDING (ready to view, no summary run).. It is categorised as a Execute tool in the Gantta MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Gantta MCP server in PolicyLayer and add a rule for bot_stop_meeting: 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 Gantta. Nothing to install.
bot_stop_meeting 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 bot_stop_meeting 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 bot_stop_meeting. 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.
bot_stop_meeting is provided by the Gantta MCP server (gantta/gantta-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 26 Gantta tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.