fleet_dispatch
Dispatch a task to the Asteroid Fleet. Routes through pipeline: classification → worker → QA gates → response.
This record as markdown: /tools/agent-store/fleet-dispatch.md
What fleet_dispatch does on Agent Store
AI agents invoke fleet_dispatch to trigger actions in Agent Store. 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.
Why fleet_dispatch is rated High
This tool triggers an external multi-stage pipeline (classification, worker execution, QA gates) on a fleet of agents. The effects are determined by the task arguments and dispatched to remote workers, making it an Execute-category tool. Misuse could cause unintended operations across a fleet of agents, warranting high severity due to the broad blast radius of fleet-wide execution.
From the tool's definition 'Dispatch a task to the Asteroid Fleet. Routes through pipeline: classification → worker → QA gates → response.'
Attacks that exploit this kind of access
The rule that runs fleet_dispatch safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Agent Store, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For fleet_dispatch, this is the rule to start with:
fleet_dispatch 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Agent Store, apply this rule, and every fleet_dispatch call is checked against it from then on.
Questions about fleet_dispatch
Dispatch a task to the Asteroid Fleet. Routes through pipeline: classification → worker → QA gates → response. It is categorised as a Execute tool in the Agent Store MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Agent Store MCP server in PolicyLayer and add a rule for fleet_dispatch: 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 Agent Store. Nothing to install.
fleet_dispatch is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the fleet_dispatch 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 fleet_dispatch. 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.
fleet_dispatch is provided by the Agent Store MCP server (chrisluersen/agent-store). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Agent Store, and thousands of servers like it.
Across the catalogue