# create_agent

A write tool on the A2a Cloud MCP server.

Agent View of the PolicyLayer registry record for `create_agent`. HTML page: https://policylayer.com/tools/a2a-cloud/create-agent

## Facts

- Tool: `create_agent`
- Server: A2a Cloud (`robGetsTheJobDone/a2a-cloud`) — https://policylayer.com/tools/a2a-cloud.md
- Homepage: https://github.com/robGetsTheJobDone/a2a-cloud
- Risk category: Write (Medium risk)
- Registry record: grade C, 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": "create_agent",
    "arguments": {}
  }
}
```

## Why create_agent is rated Medium

Creating agents in a long-term memory system is a reversible modification operation (Write category). Severity is medium because misuse could spawn unauthorized agents, pollute the memory store, or interfere with legitimate CLI workflows, but the impact is limited to agent metadata rather than financial or destructive system changes.

From the tool's own definition: "Tool name 'create_agent' indicates creating new agent records in a long-term memory system. The server description mentions 'cross-CLI, cross-project, cross-session' persistence, and sibling tools like 'delete_agent', 'list_agents', and 'wiki_write_concept'…"

## Use case

AI agents use create_agent to create or update resources in A2a Cloud, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your A2a Cloud environment.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches A2a Cloud:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_agent": {
      "limits": [
        {
          "counter": "create_agent_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on A2a Cloud (9)

- `build` — Execute — https://policylayer.com/tools/a2a-cloud/build.md
- `echo` — Other — https://policylayer.com/tools/a2a-cloud/echo.md
- `chat` — Read — https://policylayer.com/tools/a2a-cloud/chat.md
- `status` — Read — https://policylayer.com/tools/a2a-cloud/status.md
- `auto` — Write — https://policylayer.com/tools/a2a-cloud/auto.md
- `chat_result` — Write — https://policylayer.com/tools/a2a-cloud/chat-result.md
- `resume_interaction` — Write — https://policylayer.com/tools/a2a-cloud/resume-interaction.md
- `turn` — Write — https://policylayer.com/tools/a2a-cloud/turn.md
- `upgrade_agent` — Write — https://policylayer.com/tools/a2a-cloud/upgrade-agent.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=a2a-cloud · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/a2a-cloud