calls_agent_duel

SERVERDialogbrain SOURCEhttps://api.dialogbrain.com/mcp

High RISK CLASS

Category Execute

Parameters 43 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-saloprj-dialogbrain/calls-agent-duel.md

WHAT IT DOES

What calls_agent_duel does on Dialogbrain

AI agents invoke calls_agent_duel to trigger actions in Dialogbrain. 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.

Parameter	Type	Required	Description
`task`	string	Yes	The caller's brief — objective, persona details (name, phone), and when to end the call. Woven into its prompt as call instructions.
`max_duration_s`	integer	—	Hard cap on the call in seconds (30-900, default 300).
`callee_agent_id`	integer	Yes	Agent under test (answers and greets first). From agents.list.
`caller_agent_id`	integer	Yes	Customer-persona agent that places the call. Must be a different agent, active, with empty voice_greeting.

Parameters from the server's own tool schema.

RISK

Why calls_agent_duel is rated High

This tool executes an external operation (initiating a LiveKit voice session with two AI agents) whose side effects and outcomes are contingent upon the arguments supplied (caller persona, callee agent under test, task brief).

From the tool's definition Tool description explicitly states it will 'Start an agent-vs-agent VOICE test call' and 'share one LiveKit room', which are network and external system operations.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs calls_agent_duel safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Dialogbrain, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For calls_agent_duel, this is the rule to start with:

calls_agent_duel Rate-limited

calls_agent_duel 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "calls_agent_duel": {
      "limits": [
        {
          "counter": "calls_agent_duel_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Dialogbrain, apply this rule, and every calls_agent_duel call is checked against it from then on.

FAQ

Questions about calls_agent_duel

What does the calls_agent_duel tool do? +

Start an agent-vs-agent VOICE test call: two AI voice agents share one LiveKit room — a 'caller' persona agent pursues a task brief against the 'callee' business agent under test. Use to evaluate booking flows, latency, and conversation quality without a human caller. The CALLER agent should have an EMPTY voice_greeting (it must stay silent until the callee greets) and voice_filler_enabled=false. Afterwards inspect both call_ids with agents.traces_list / calls.get_transcript. A subscribe-only listen token is returned for listening in live. It is categorised as a Execute tool in the Dialogbrain MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

What parameters does calls_agent_duel accept? +

calls_agent_duel accepts 4 parameters: task, max_duration_s, callee_agent_id, caller_agent_id. Required: task, callee_agent_id, caller_agent_id. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on calls_agent_duel? +

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

What risk level is calls_agent_duel? +

calls_agent_duel is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit calls_agent_duel? +

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

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

calls_agent_duel is provided by the Dialogbrain MCP server (https://api.dialogbrain.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Dialogbrain, and thousands of servers like it.

This server

All 225 Dialogbrain tools → High-risk tools on this server →

Across the catalogue

All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →