// SCAN REPORT

VOICEPEAK MCP Server

10 tools. 6 can modify or destroy data without limits.

2 destructive tools with no built-in limits. Policy required.

Last updated: 12 Jun 2026

6 can modify or destroy data

4 read-only

10 tools total

Community server · catalogue entry verified 12/06/2026

How to control VOICEPEAK MCP Server ↓

TOOL MAP

What VOICEPEAK MCP Server exposes to your agents

Read (4) Write / Execute (4) Destructive / Financial (2)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous VOICEPEAK MCP Server tools

Destructive · High dictionary_clear This tool permanently removes all dictionary entries without reverting or rollback capability. Destructive · Low dictionary_remove Removing a dictionary entry is an irreversible deletion of data (the pronunciation dictionary entry). Execute · Medium play Playing an audio file triggers an external operation (audio playback) on the system. Execute · Medium synthesize_and_play This tool both generates audio (write/create) and triggers playback on the system (an external operation/side effect).

6 of VOICEPEAK MCP Server's 10 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control VOICEPEAK MCP Server

PolicyLayer is an MCP gateway — it sits between your AI agents and VOICEPEAK MCP Server, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "dictionary_clear": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "synthesize": {
    "limits": [
      {
        "counter": "synthesize_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "dictionary_find": {
    "limits": [
      {
        "counter": "dictionary_find_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register VOICEPEAK MCP Server — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON VOICEPEAK →

Free to start. No card required.

FULL CATALOGUE

All 10 VOICEPEAK MCP Server tools

DESTRUCTIVE 2 tools

Destructive dictionary_clear Clear all dictionary entries Destructive dictionary_remove Remove a dictionary entry

EXECUTE 2 tools

Execute play Play a synthesized audio file Execute synthesize_and_play Synthesize speech from text and immediately play it (max 140 characters per synthesis)

WRITE 2 tools

Write synthesize Synthesize speech from text using VOICEPEAK (max 140 characters per synthesis) Write dictionary_add Add or update a dictionary entry for custom pronunciation

READ 4 tools

Read dictionary_find Find dictionary entries by surface form Read dictionary_list List all dictionary entries Read list_emotions List available emotions for a narrator Read list_narrators List all available narrators

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about VOICEPEAK MCP Server

Can an AI agent delete data through the VOICEPEAK MCP Server MCP server? +

Yes. The VOICEPEAK MCP Server server exposes 2 destructive tools including dictionary_clear, dictionary_remove. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through VOICEPEAK MCP Server? +

The VOICEPEAK MCP Server server has 2 write tools including synthesize, dictionary_add. 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 VOICEPEAK MCP Server.

How many tools does the VOICEPEAK MCP Server MCP server expose? +

10 tools across 3 categories: Destructive, Read, Write. 4 are read-only. 6 can modify, create, or delete data.

How do I enforce a policy on VOICEPEAK MCP Server? +

Register the VOICEPEAK MCP Server 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.

Enforce policy on every VOICEPEAK MCP Server tool call.

Deterministic rules across all 10 VOICEPEAK MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON VOICEPEAK →

Free to start. No card required.

10 VOICEPEAK MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.