dispatch-reply
Send a result back for a completed dispatch task. Use after finishing a think or build task received via dispatch-check. Only replies to trusted identities. Do not use this for human conversations — only for responding to tasks from other AI agents.
This record as markdown: /tools/dev-forgesworn-bray/dispatch-reply.md
What dispatch-reply does on Nostr Bray
AI agents use dispatch-reply to create or update resources in Nostr Bray, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Nostr Bray environment.
Why dispatch-reply is rated Medium
The tool sends a reply message to another AI agent upon task completion. This is a write/post operation (sending data to an external identity), not merely reading. It does not delete data or move money. The restriction to 'trusted identities' limits blast radius somewhat, but misuse could send unintended or malicious content to trusted AI agents, potentially influencing downstream automated workflows.
From the tool's definition 'Send a result back for a completed dispatch task' and 'Only replies to trusted identities'
Attacks that exploit this kind of access
The rule that runs dispatch-reply safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Nostr Bray, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For dispatch-reply, this is the rule to start with:
dispatch-reply 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Nostr Bray, apply this rule, and every dispatch-reply call is checked against it from then on.
Questions about dispatch-reply
Send a result back for a completed dispatch task. Use after finishing a think or build task received via dispatch-check. Only replies to trusted identities. Do not use this for human conversations — only for responding to tasks from other AI agents. It is categorised as a Write tool in the Nostr Bray MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Nostr Bray MCP server in PolicyLayer and add a rule for dispatch-reply: 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 Nostr Bray. Nothing to install.
dispatch-reply is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the dispatch-reply 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 dispatch-reply. 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.
dispatch-reply is provided by the Nostr Bray MCP server (nostr-bray). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Nostr Bray, and thousands of servers like it.
This server
Across the catalogue