Medium Risk

dictionary_add

Add or update a dictionary entry for custom pronunciation

How to control dictionary_add ↓

What dictionary_add does on VOICEPEAK MCP Server

AI agents use dictionary_add to create or update resources in VOICEPEAK MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your VOICEPEAK MCP Server environment.

Medium Risk

Why dictionary_add needs a policy

This tool creates or modifies pronunciation dictionary entries, which is a reversible write operation. It affects only configuration data (custom pronunciation rules) with no side effects on other systems or destructive capabilities. The blast radius is minimal—worst case an AI agent misconfigures pronunciations for a few words, easily corrected by removing or clearing dictionary entries.

From the tool's definition Tool name 'dictionary_add' and description 'Add or update a dictionary entry for custom pronunciation' indicate data modification that is reversible through dictionary_remove or dictionary_clear operations.

Documented attack patterns abuse exactly the kind of access dictionary_add gives an agent:

How to control dictionary_add

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

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "dictionary_add": {
      "limits": [
        {
          "counter": "dictionary_add_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

dictionary_add stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

  1. Create a free account and register VOICEPEAK MCP Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about dictionary_add

What does the dictionary_add tool do? +

Add or update a dictionary entry for custom pronunciation. It is categorised as a Write tool in the VOICEPEAK MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on dictionary_add? +

Register the VOICEPEAK MCP Server MCP server in PolicyLayer and add a rule for dictionary_add: 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 VOICEPEAK MCP Server. Nothing to install.

What risk level is dictionary_add? +

dictionary_add is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit dictionary_add? +

Yes. Add a rate_limit block to the dictionary_add 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.

How do I block dictionary_add completely? +

Set action: deny in the PolicyLayer policy for dictionary_add. 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.

What MCP server provides dictionary_add? +

dictionary_add is provided by the VOICEPEAK MCP Server MCP server (k2wanko/voicepeak-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every VOICEPEAK MCP Server tool call.

Start from VOICEPEAK MCP 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.

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

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.