# fleet_dispatch

Dispatch a task to the Asteroid Fleet. Routes through pipeline: classification → worker → QA gates → response.

Agent View of the PolicyLayer registry record for `fleet_dispatch`. HTML page: https://policylayer.com/tools/agent-store/fleet-dispatch

## Facts

- Tool: `fleet_dispatch`
- Server: Agent Store (`chrisluersen/agent-store`) — https://policylayer.com/tools/agent-store.md
- Homepage: https://github.com/chrisluersen/agent-store
- Risk category: Execute (High risk)
- Registry record: grade D, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "fleet_dispatch",
    "arguments": {}
  }
}
```

## 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 own definition: "'Dispatch a task to the Asteroid Fleet. Routes through pipeline: classification → worker → QA gates → response.'"

## Use case

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.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Agent Store:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "fleet_dispatch": {
      "limits": [
        {
          "counter": "fleet_dispatch_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Agent Store (18)

- `gbrain_query` — Execute — https://policylayer.com/tools/agent-store/gbrain-query.md
- `gbrain_think` — Execute — https://policylayer.com/tools/agent-store/gbrain-think.md
- `reindex_wiki` — Execute — https://policylayer.com/tools/agent-store/reindex-wiki.md
- `file_synthesis` — Other — https://policylayer.com/tools/agent-store/file-synthesis.md
- `suggest_edges` — Other — https://policylayer.com/tools/agent-store/suggest-edges.md
- `find_related` — Read — https://policylayer.com/tools/agent-store/find-related.md
- `fleet_ping` — Read — https://policylayer.com/tools/agent-store/fleet-ping.md
- `gbrain_brain_stats` — Read — https://policylayer.com/tools/agent-store/gbrain-brain-stats.md
- `gbrain_doctor` — Read — https://policylayer.com/tools/agent-store/gbrain-doctor.md
- `gbrain_get_page` — Read — https://policylayer.com/tools/agent-store/gbrain-get-page.md
- `gbrain_list_pages` — Read — https://policylayer.com/tools/agent-store/gbrain-list-pages.md
- `gbrain_search` — Read — https://policylayer.com/tools/agent-store/gbrain-search.md
- `lint_wiki` — Read — https://policylayer.com/tools/agent-store/lint-wiki.md
- `list_wiki_pages` — Read — https://policylayer.com/tools/agent-store/list-wiki-pages.md
- `read_wiki_page` — Read — https://policylayer.com/tools/agent-store/read-wiki-page.md
- `search_wiki` — Read — https://policylayer.com/tools/agent-store/search-wiki.md
- `synthesize_answer` — Read — https://policylayer.com/tools/agent-store/synthesize-answer.md
- `wiki_stats` — Read — https://policylayer.com/tools/agent-store/wiki-stats.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=agent-store · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/agent-store