AI agents invoke tts to trigger actions in MCP TTS Server. 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.
Text-to-speech execution qualifies as Execute because it runs an external operation (TTS engine invocation) whose effects depend on input arguments (text content, voice selection, engine choice). While not destructive or financial, it performs an action beyond passive data retrieval.
From the tool's definition Tool name is 'tts' with empty description, but sibling tools ('tts_stop_playback_and_clear_queue', 'get_tts_instructions') and server description indicate this tool triggers text-to-speech conversion—a media output operation.
Documented attack patterns abuse exactly the kind of access tts gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP TTS Server, and nothing reaches the server without passing your rules. This is the rule we recommend for tts:
{
"version": "1",
"default": "deny",
"tools": {
"tts": {
"limits": [
{
"counter": "tts_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}tts 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.
tts. It is categorised as a Execute tool in the MCP TTS Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP TTS Server MCP server in PolicyLayer and add a rule for tts: 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 MCP TTS Server. Nothing to install.
tts 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 tts 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 tts. 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.
tts is provided by the MCP TTS Server MCP server (kristofferv98/mcp_tts_server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP TTS Server, 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.
4 MCP TTS Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.