agent_silence
End this turn without sending any message. Use when the thread is owned by a human operator after job.escalate, when the guest is self-resolving, when the message is a duplicate, or for observation-only turns. Calling this tool is the ONLY correct way to stay silent — narrated silence text (e.g. ...
This record as markdown: /tools/io-github-saloprj-dialogbrain/agent-silence.md
What agent_silence does on Dialogbrain
AI agents call agent_silence as a supporting operation in Dialogbrain workflows.
| Parameter | Type | Required | Description |
|---|---|---|---|
reason | string | Yes | Free-form explanation for admin audit. Stored in trace_tool_executions.tool_params (ClickHouse String; reason filters are scan-only). |
Parameters from the server's own tool schema.
Why agent_silence is rated Low
This tool takes no action beyond suppressing output for the current turn. It does not read, write, execute, delete, or move money — it simply marks the turn as a no-op to prevent accidental message delivery. The blast radius of misuse is minimal (a message that should have been sent is withheld), placing it in 'Other' with low severity.
From the tool's definition End this turn without sending any message... Calling this tool is the ONLY correct way to stay silent
Attacks that exploit this kind of access
The rule that runs agent_silence 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 agent_silence, this is the rule to start with:
agent_silence gets a rate cap, and everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Dialogbrain, apply this rule, and every agent_silence call is checked against it from then on.
Questions about agent_silence
End this turn without sending any message. Use when the thread is owned by a human operator after job.escalate, when the guest is self-resolving, when the message is a duplicate, or for observation-only turns. Calling this tool is the ONLY correct way to stay silent — narrated silence text (e.g. '*(Staying silent…)*', 'Internal:…') would be delivered to the guest verbatim. It is categorised as a Other tool in the Dialogbrain MCP Server, which means it performs auxiliary operations.
agent_silence accepts 1 parameter: reason. Required: reason. The full parameter table on this page comes from the server's own tool schema.
Register the Dialogbrain MCP server in PolicyLayer and add a rule for agent_silence: 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.
agent_silence is a Other tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the agent_silence 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.
Set action: deny in the PolicyLayer policy for agent_silence. 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.
agent_silence 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.
More on Dialogbrain, and thousands of servers like it.
This server
Across the catalogue