vora_update_agent · Vora MCP: Risk & Policy

WHAT IT DOES

What vora_update_agent does on Vora

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

WHY IT NEEDS A POLICY

Why vora_update_agent needs a policy

This tool creates or modifies agent configuration and responses (Write category). Severity is medium because a misconfigured voice agent could interact with users in unintended ways, but the impact is limited to the agent's behavior and reversible. The incomplete description and unclear scope of 'improvement' prevent a high confidence rating, though the evidence strongly suggests Write over other categories.

From the tool's definition Tool description states 'Incrementally improve your voice agent' and 'Add new objection responses', indicating modification of agent configuration/behavior.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

vora_update_agent Rate-limited

vora_update_agent 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "vora_update_agent": {
      "limits": [
        {
          "counter": "vora_update_agent_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Vora, so you can run agents against it safely.

FAQ

Questions about vora_update_agent

What does the vora_update_agent tool do? +

Incrementally improve your voice agent without full recompilation. Use this to: - Add new objection responses based on what you. It is categorised as a Write tool in the Vora MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on vora_update_agent? +

Register the Vora MCP server in PolicyLayer and add a rule for vora_update_agent: 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 Vora. Nothing to install.

What risk level is vora_update_agent? +

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

Can I rate-limit vora_update_agent? +

Yes. Add a rate_limit block to the vora_update_agent 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 vora_update_agent completely? +

Set action: deny in the PolicyLayer policy for vora_update_agent. 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 vora_update_agent? +

vora_update_agent is provided by the Vora MCP server (stefanstojanovicstefa-creator/vora-voice-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.