# start_security_scan

A execute tool on the AWS MCP server.

Agent View of the PolicyLayer registry record for `start_security_scan`. HTML page: https://policylayer.com/tools/aws/start-security-scan

## Facts

- Tool: `start_security_scan`
- Server: AWS (`@awslabs/mcp`) — https://policylayer.com/tools/aws.md
- Install: `npx -y @awslabs/mcp`
- Homepage: https://github.com/awslabs/mcp
- Risk category: Execute (High risk)
- Registry record: grade F, identity verified
- 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": "start_security_scan",
    "arguments": {}
  }
}
```

## Why start_security_scan is rated High

Security scanning is an external operation that triggers infrastructure scanning with effects dependent on configuration and scope. On AWS, security scans can examine resources, trigger API calls, and generate findings. This constitutes execution of a defined process rather than simple data retrieval. The high severity reflects that misconfigured scans could be noisy, resource-intensive, or expose sensitive findings.

From the tool's own definition: "Tool name 'start_security_scan' indicates execution of a security scanning operation. The description is empty, limiting direct evidence."

## Use case

AI agents invoke start_security_scan to trigger actions in AWS. 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 AWS:

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

## Other tools on AWS (299)

- `bulk_delete_by_criteria` — Destructive — https://policylayer.com/tools/aws/bulk-delete-by-criteria.md
- `cache_delete` — Destructive — https://policylayer.com/tools/aws/cache-delete.md
- `cache_delete_many` — Destructive — https://policylayer.com/tools/aws/cache-delete-many.md
- `cache_delete_multi` — Destructive — https://policylayer.com/tools/aws/cache-delete-multi.md
- `cache_flush_all` — Destructive — https://policylayer.com/tools/aws/cache-flush-all.md
- `delete` — Destructive — https://policylayer.com/tools/aws/delete.md
- `delete_access_key` — Destructive — https://policylayer.com/tools/aws/delete-access-key.md
- `delete_datastore` — Destructive — https://policylayer.com/tools/aws/delete-datastore.md
- `delete_group` — Destructive — https://policylayer.com/tools/aws/delete-group.md
- `delete_image_set` — Destructive — https://policylayer.com/tools/aws/delete-image-set.md
- `delete_instance_in_series` — Destructive — https://policylayer.com/tools/aws/delete-instance-in-series.md
- `delete_instance_in_study` — Destructive — https://policylayer.com/tools/aws/delete-instance-in-study.md
- `delete_patient_studies` — Destructive — https://policylayer.com/tools/aws/delete-patient-studies.md
- `delete_resource` — Destructive — https://policylayer.com/tools/aws/delete-resource.md
- `delete_role_policy` — Destructive — https://policylayer.com/tools/aws/delete-role-policy.md
- `delete_series_by_uid` — Destructive — https://policylayer.com/tools/aws/delete-series-by-uid.md
- `delete_study` — Destructive — https://policylayer.com/tools/aws/delete-study.md
- `delete_user` — Destructive — https://policylayer.com/tools/aws/delete-user.md
- `delete_user_policy` — Destructive — https://policylayer.com/tools/aws/delete-user-policy.md
- `detach_user_policy` — Destructive — https://policylayer.com/tools/aws/detach-user-policy.md
- `json_arrtrim` — Destructive — https://policylayer.com/tools/aws/json-arrtrim.md
- `json_clear` — Destructive — https://policylayer.com/tools/aws/json-clear.md
- `json_del` — Destructive — https://policylayer.com/tools/aws/json-del.md
- `list_pop_left` — Destructive — https://policylayer.com/tools/aws/list-pop-left.md
- `list_trim` — Destructive — https://policylayer.com/tools/aws/list-trim.md
- `remove_instance_from_image_set` — Destructive — https://policylayer.com/tools/aws/remove-instance-from-image-set.md
- `remove_series_from_image_set` — Destructive — https://policylayer.com/tools/aws/remove-series-from-image-set.md
- `set_pop` — Destructive — https://policylayer.com/tools/aws/set-pop.md
- `sorted_set_remove_by_lex` — Destructive — https://policylayer.com/tools/aws/sorted-set-remove-by-lex.md
- `sorted_set_remove_by_score` — Destructive — https://policylayer.com/tools/aws/sorted-set-remove-by-score.md
- …and 269 more: https://policylayer.com/tools/aws.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=aws · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/aws