dispatch-query
Ask the task sender a clarifying question before delivering results. Use mid-task when you need more information to proceed. The sender receives the question via dispatch-check and can reply.
This record as markdown: /tools/dev-forgesworn-bray/dispatch-query.md
What dispatch-query does on Nostr Bray
AI agents call dispatch-query to retrieve information from Nostr Bray without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why dispatch-query is rated Low
This tool retrieves or queries information (asking for clarification) and returns results without side effects. It enables communication between an agent and task sender to gather necessary context before proceeding, but does not modify, destroy, or execute code. The action is informational and reversible, placing it squarely in the Read category with low severity.
From the tool's definition dispatch-query is described as asking a clarifying question and delivering results, with no capability to modify or delete data. The tool receives information from a sender but does not create, destroy, or execute external operations.
Attacks that exploit this kind of access
The rule that runs dispatch-query 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-query, this is the rule to start with:
dispatch-query is read-only, so it stays allowed. 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-query call is checked against it from then on.
Questions about dispatch-query
Ask the task sender a clarifying question before delivering results. Use mid-task when you need more information to proceed. The sender receives the question via dispatch-check and can reply. It is categorised as a Read tool in the Nostr Bray MCP Server, which means it retrieves data without modifying state.
Register the Nostr Bray MCP server in PolicyLayer and add a rule for dispatch-query: 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-query is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the dispatch-query 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-query. 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-query 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