# snow_ai_classify

Classify a piece of text into one of a caller-supplied list of categories, with a confidence score. Use for routing incoming cases/incidents into queues or assignment groups by content.

Agent View of the PolicyLayer registry record for `snow_ai_classify`. HTML page: https://policylayer.com/tools/serac/snow-ai-classify

## Facts

- Tool: `snow_ai_classify`
- Server: Serac (`serac-labs/serac`) — https://policylayer.com/tools/serac.md
- Homepage: https://github.com/serac-labs/serac
- Risk category: Read (Low risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Allowed

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

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

## Why snow_ai_classify is rated Low

The tool performs content analysis and categorization—a read-only operation that examines input text and returns classification results. It has no side effects on data state, does not execute code or commands, and does not delete or move money. It is purely informational/analytical in nature. Severity is low because misuse would at worst result in incorrect routing decisions, not data loss or unauthorized actions.

From the tool's own definition: "Tool description states it 'Classify a piece of text into one of a caller-supplied list of categories, with a confidence score' and is used for 'routing incoming cases/incidents into queues'."

## Use case

AI agents call snow_ai_classify to retrieve information from Serac without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Serac:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "snow_ai_classify": {}
  }
}
```

## Other tools on Serac (431)

- `snow_cleanup_test_artifacts` — Destructive — https://policylayer.com/tools/serac/snow-cleanup-test-artifacts.md
- `snow_delete_attachment` — Destructive — https://policylayer.com/tools/serac/snow-delete-attachment.md
- `snow_inbound_email_action` — Destructive — https://policylayer.com/tools/serac/snow-inbound-email-action.md
- `snow_pa_indicator_manage` — Destructive — https://policylayer.com/tools/serac/snow-pa-indicator-manage.md
- `snow_rollback_deployment` — Destructive — https://policylayer.com/tools/serac/snow-rollback-deployment.md
- `snow_workflow_transition` — Destructive — https://policylayer.com/tools/serac/snow-workflow-transition.md
- `enterprise_tool_execute` — Execute — https://policylayer.com/tools/serac/enterprise-tool-execute.md
- `snow_auto_resolve_incident` — Execute — https://policylayer.com/tools/serac/snow-auto-resolve-incident.md
- `snow_automate_threat_response` — Execute — https://policylayer.com/tools/serac/snow-automate-threat-response.md
- `snow_batch_request` — Execute — https://policylayer.com/tools/serac/snow-batch-request.md
- `snow_change_manage` — Execute — https://policylayer.com/tools/serac/snow-change-manage.md
- `snow_cicd_deploy` — Execute — https://policylayer.com/tools/serac/snow-cicd-deploy.md
- `snow_collect_metric` — Execute — https://policylayer.com/tools/serac/snow-collect-metric.md
- `snow_confirm_script_execution` — Execute — https://policylayer.com/tools/serac/snow-confirm-script-execution.md
- `snow_convert_es6_to_es5` — Execute — https://policylayer.com/tools/serac/snow-convert-es6-to-es5.md
- `snow_convert_to_es5` — Execute — https://policylayer.com/tools/serac/snow-convert-to-es5.md
- `snow_create_mobile_action` — Execute — https://policylayer.com/tools/serac/snow-create-mobile-action.md
- `snow_create_vulnerability_scan` — Execute — https://policylayer.com/tools/serac/snow-create-vulnerability-scan.md
- `snow_custom_api` — Execute — https://policylayer.com/tools/serac/snow-custom-api.md
- `snow_elevate_role` — Execute — https://policylayer.com/tools/serac/snow-elevate-role.md
- `snow_employee_offboarding` — Execute — https://policylayer.com/tools/serac/snow-employee-offboarding.md
- `snow_employee_onboarding` — Execute — https://policylayer.com/tools/serac/snow-employee-onboarding.md
- `snow_execute_atf_test` — Execute — https://policylayer.com/tools/serac/snow-execute-atf-test.md
- `snow_execute_script` — Execute — https://policylayer.com/tools/serac/snow-execute-script.md
- `snow_execute_security_playbook` — Execute — https://policylayer.com/tools/serac/snow-execute-security-playbook.md
- `snow_execute_transform` — Execute — https://policylayer.com/tools/serac/snow-execute-transform.md
- `snow_fluent_build` — Execute — https://policylayer.com/tools/serac/snow-fluent-build.md
- `snow_fluent_install` — Execute — https://policylayer.com/tools/serac/snow-fluent-install.md
- `snow_fluent_transform` — Execute — https://policylayer.com/tools/serac/snow-fluent-transform.md
- `snow_github_deploy` — Execute — https://policylayer.com/tools/serac/snow-github-deploy.md
- …and 401 more: https://policylayer.com/tools/serac.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=serac · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/serac