# invoke_agents_parallel

Call several Agents in parallel: all invocations run at once and return together. Use it when sending independent requests to multiple Agents — far faster than calling invoke_agent serially. Important: relay each Agent\

Agent View of the PolicyLayer registry record for `invoke_agents_parallel`. HTML page: https://policylayer.com/tools/a2wave/invoke-agents-parallel

## Facts

- Tool: `invoke_agents_parallel`
- Server: A2wave (`LilithGames/a2wave`) — https://policylayer.com/tools/a2wave.md
- Homepage: https://github.com/LilithGames/a2wave
- 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": "invoke_agents_parallel",
    "arguments": {}
  }
}
```

## Why invoke_agents_parallel is rated High

Executes external agents in parallel; effects depend on agent definitions and arguments provided.

From the tool's own definition: "Call several Agents in parallel: all invocations run at once"

## Use case

AI agents invoke invoke_agents_parallel to trigger actions in A2wave. 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 A2wave:

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

## Other tools on A2wave (21)

- `call_tool` — Execute — https://policylayer.com/tools/a2wave/call-tool.md
- `invoke_agent` — Execute — https://policylayer.com/tools/a2wave/invoke-agent.md
- `get_agent` — Read — https://policylayer.com/tools/a2wave/get-agent.md
- `get_agent_card` — Read — https://policylayer.com/tools/a2wave/get-agent-card.md
- `get_mcp_server` — Read — https://policylayer.com/tools/a2wave/get-mcp-server.md
- `get_platform_overview` — Read — https://policylayer.com/tools/a2wave/get-platform-overview.md
- `get_provider` — Read — https://policylayer.com/tools/a2wave/get-provider.md
- `get_run_detail` — Read — https://policylayer.com/tools/a2wave/get-run-detail.md
- `get_run_stats` — Read — https://policylayer.com/tools/a2wave/get-run-stats.md
- `get_settings` — Read — https://policylayer.com/tools/a2wave/get-settings.md
- `get_skill` — Read — https://policylayer.com/tools/a2wave/get-skill.md
- `get_tool_schema` — Read — https://policylayer.com/tools/a2wave/get-tool-schema.md
- `list_agents` — Read — https://policylayer.com/tools/a2wave/list-agents.md
- `list_audit_logs` — Read — https://policylayer.com/tools/a2wave/list-audit-logs.md
- `list_groups` — Read — https://policylayer.com/tools/a2wave/list-groups.md
- `list_mcp_servers` — Read — https://policylayer.com/tools/a2wave/list-mcp-servers.md
- `list_providers` — Read — https://policylayer.com/tools/a2wave/list-providers.md
- `list_runs` — Read — https://policylayer.com/tools/a2wave/list-runs.md
- `list_skills` — Read — https://policylayer.com/tools/a2wave/list-skills.md
- `list_tools` — Read — https://policylayer.com/tools/a2wave/list-tools.md
- `list_users` — Read — https://policylayer.com/tools/a2wave/list-users.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=a2wave · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/a2wave