AI agents invoke speak_text to trigger actions in Joinly. 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.
Based on the server context (video call participation) and the tool name, 'speak_text' most likely synthesizes and broadcasts audio speech into a live video call. This is an Execute-level action as it triggers an external operation (audio output in a meeting) whose effects depend on the text argument.
From the tool's definition Tool name 'speak_text' on a server that 'Enables AI agents to join and actively participate in video calls' with sibling tools like send_chat_message, share_screen, join_meeting
Documented attack patterns abuse exactly the kind of access speak_text gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Joinly, and nothing reaches the server without passing your rules. This is the rule we recommend for speak_text:
{
"version": "1",
"default": "deny",
"tools": {
"speak_text": {
"limits": [
{
"counter": "speak_text_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}speak_text 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.
speak_text. It is categorised as a Execute tool in the Joinly MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Joinly MCP server in PolicyLayer and add a rule for speak_text: 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 Joinly. Nothing to install.
speak_text 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 speak_text 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 speak_text. 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.
speak_text is provided by the Joinly MCP server (joinly-ai/joinly). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Joinly, 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.
12 Joinly tools catalogued and risk-classified — across an index of 43,000+ MCP servers.