390 tools. 200 can modify or destroy data without limits.
46 destructive tools with no built-in limits. Policy required.
Last updated:
Community server · catalogue entry checked 17/09/2026 · full schemas captured for 375 of 390 tools
Running more than one server? Check your whole stack →
Full per-tool breakdown → Model it in the token calculator →
200 of Elevenlabs's 390 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.
PolicyLayer is an MCP gateway — it sits between your AI agents and Elevenlabs, and nothing reaches the server without passing your rules. These are the rules we recommend:
{
"cancel_batch_call": {
"deny_if": [
{
"conditions": [],
"on_deny": "Blocked by default. Requires approval."
}
]
}
} Destructive tools should never be available to autonomous agents without human approval.
{
"add_chapter": {
"limits": [
{
"counter": "add_chapter_per_hour",
"window": "hour",
"max": 30,
"scope": "grant"
}
]
}
} Prevents bulk unintended modifications from agents caught in loops.
{
"compose_detailed": {
"limits": [
{
"counter": "compose_detailed_per_minute",
"window": "minute",
"max": 60,
"scope": "grant"
}
]
}
} Controls API costs and prevents retry loops from exhausting upstream rate limits.
Instant setup, no code required.
Other MCP servers with similar tools — same risk classification, starter policies for each.
Yes. The Elevenlabs server exposes 46 destructive tools including cancel_batch_call, cancel_crawl_job_route, cancel_file_upload_route. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.
The Elevenlabs server has 146 write tools including add_chapter, add_documentation_to_knowledge_base, add_from_file. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Elevenlabs.
390 tools across 4 categories: Destructive, Execute, Read, Write. 190 are read-only. 200 can modify, create, or delete data.
Register the Elevenlabs MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.
Deterministic rules across all 390 Elevenlabs tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Instant setup, no code required.
390 Elevenlabs tools catalogued and risk-classified — across an index of 46,500+ MCP servers.
These policies come from Elevenlabs's registry record.
The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →