# career_run_continue

仅提交最新 next_actions 中允许的动作；expected_state_version 必须来自最新状态。subject_ref_json/target_ref_json 为可选 JSON 字符串。

Agent View of the PolicyLayer registry record for `career_run_continue`. HTML page: https://policylayer.com/tools/a02-careeragent-mcp/career-run-continue

## Facts

- Tool: `career_run_continue`
- Server: A02 Careeragent (`a02-careeragent-mcp`) — https://policylayer.com/tools/a02-careeragent-mcp.md
- Install: `npx -y a02-careeragent-mcp`
- Homepage: https://www.npmjs.com/package/a02-careeragent-mcp
- Risk category: Execute (High risk)
- Registry record: grade F, 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": "career_run_continue",
    "arguments": {}
  }
}
```

## Why career_run_continue is rated High

career_run_continue triggers real processes with real consequences. An agent gone sideways doesn't fire it once. It starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.

## Use case

AI agents invoke career_run_continue to trigger actions in A02 Careeragent. 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 A02 Careeragent:

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

## Other tools on A02 Careeragent (4)

- `career_decision_confirm` — Execute — https://policylayer.com/tools/a02-careeragent-mcp/career-decision-confirm.md
- `career_run_start` — Execute — https://policylayer.com/tools/a02-careeragent-mcp/career-run-start.md
- `career_run_status` — Execute — https://policylayer.com/tools/a02-careeragent-mcp/career-run-status.md
- `artifact_get` — Read — https://policylayer.com/tools/a02-careeragent-mcp/artifact-get.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=a02-careeragent-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/a02-careeragent-mcp
