# search_cve

Search the NVD CVE database.

Agent View of the PolicyLayer registry record for `search_cve`. HTML page: https://policylayer.com/tools/creativelead-unclick/search-cve

## Facts

- Tool: `search_cve`
- Server: UnClick (`creativelead/unclick`) — https://policylayer.com/tools/creativelead-unclick.md
- Homepage: https://github.com/creativelead/unclick
- Risk category: Read (Low risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 4
- Recommended policy verdict: Allowed

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `keyword` | string | no |  |
| `startIndex` | number | no |  |
| `cvssV3Severity` | string | no | LOW, MEDIUM, HIGH, CRITICAL |
| `resultsPerPage` | number | no |  |

Parameters from the server's own tool schema.

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

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

## Why search_cve is rated Low

The tool performs a search/query operation (a classic Read action) against the National Vulnerability Database. While CVE information pertains to security vulnerabilities, the tool itself only retrieves and surfaces existing public data with no side effects, no code execution, no data modification, and no destructive capability.

From the tool's own definition: "Tool description states 'Search the NVD CVE database' — this is a read-only query operation that retrieves information from a publicly available vulnerability database without modifying, executing, or deleting any data."

## Use case

AI agents call search_cve to retrieve information from UnClick 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 UnClick:

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

## Other tools on UnClick (450)

- `email_delete` — Destructive — https://policylayer.com/tools/creativelead-unclick/email-delete.md
- `instapaper_action` — Destructive — https://policylayer.com/tools/creativelead-unclick/instapaper-action.md
- `raindrop_action` — Destructive — https://policylayer.com/tools/creativelead-unclick/raindrop-action.md
- `telegram_manage_chat` — Destructive — https://policylayer.com/tools/creativelead-unclick/telegram-manage-chat.md
- `vault_action` — Destructive — https://policylayer.com/tools/creativelead-unclick/vault-action.md
- `csuite_analyze` — Execute — https://policylayer.com/tools/creativelead-unclick/csuite-analyze.md
- `mastodon_action` — Execute — https://policylayer.com/tools/creativelead-unclick/mastodon-action.md
- `slack_action` — Execute — https://policylayer.com/tools/creativelead-unclick/slack-action.md
- `text_transform` — Execute — https://policylayer.com/tools/creativelead-unclick/text-transform.md
- `unclick_call` — Execute — https://policylayer.com/tools/creativelead-unclick/unclick-call.md
- `unclick_generate_qr` — Execute — https://policylayer.com/tools/creativelead-unclick/unclick-generate-qr.md
- `unclick_hash` — Execute — https://policylayer.com/tools/creativelead-unclick/unclick-hash.md
- `unclick_parse_csv` — Execute — https://policylayer.com/tools/creativelead-unclick/unclick-parse-csv.md
- `unclick_transform_text` — Execute — https://policylayer.com/tools/creativelead-unclick/unclick-transform-text.md
- `urlscan_scan` — Execute — https://policylayer.com/tools/creativelead-unclick/urlscan-scan.md
- `virustotal_scan_url` — Execute — https://policylayer.com/tools/creativelead-unclick/virustotal-scan-url.md
- `wise_create_quote` — Financial — https://policylayer.com/tools/creativelead-unclick/wise-create-quote.md
- `calc_compound_interest` — Other — https://policylayer.com/tools/creativelead-unclick/calc-compound-interest.md
- `color_convert` — Other — https://policylayer.com/tools/creativelead-unclick/color-convert.md
- `convert_area` — Other — https://policylayer.com/tools/creativelead-unclick/convert-area.md
- `convert_data_storage` — Other — https://policylayer.com/tools/creativelead-unclick/convert-data-storage.md
- `convert_length` — Other — https://policylayer.com/tools/creativelead-unclick/convert-length.md
- `convert_speed` — Other — https://policylayer.com/tools/creativelead-unclick/convert-speed.md
- `convert_temperature` — Other — https://policylayer.com/tools/creativelead-unclick/convert-temperature.md
- `convert_volume` — Other — https://policylayer.com/tools/creativelead-unclick/convert-volume.md
- `convert_weight` — Other — https://policylayer.com/tools/creativelead-unclick/convert-weight.md
- `datetime_add_to_date` — Other — https://policylayer.com/tools/creativelead-unclick/datetime-add-to-date.md
- `datetime_convert_timezone` — Other — https://policylayer.com/tools/creativelead-unclick/datetime-convert-timezone.md
- `random_flip_coin` — Other — https://policylayer.com/tools/creativelead-unclick/random-flip-coin.md
- `random_roll_dice` — Other — https://policylayer.com/tools/creativelead-unclick/random-roll-dice.md
- …and 420 more: https://policylayer.com/tools/creativelead-unclick.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=creativelead-unclick · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/creativelead-unclick