# delete

Delete one or more keys from Redis

Agent View of the PolicyLayer registry record for `delete`. HTML page: https://policylayer.com/tools/redis/delete

## Facts

- Tool: `delete`
- Server: Redis (`@@modelcontextprotocol/server-redis`) — https://policylayer.com/tools/redis.md
- Install: `npx -y @@modelcontextprotocol/server-redis`
- Homepage: https://www.npmjs.com/package/@@modelcontextprotocol/server-redis
- Risk category: Destructive (Critical risk)
- Registry record: grade F, identity verified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Hidden

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

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

## Why delete is rated Critical

The delete operation permanently removes keys and their associated data from Redis. This action cannot be undone and results in data loss. While severity is 'high' rather than 'critical' because impact is scoped to the Redis instance itself (not system-wide or financial), it is clearly Destructive as it irreversibly deletes data.

From the tool's own definition: "Tool name 'delete' combined with description 'Delete one or more keys from Redis' explicitly indicates irreversible removal of data from a Redis store."

Risk signals: Permanently removes data entries

## Use case

AI agents call delete to permanently remove resources in Redis, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

## Recommended policy (PolicyLayer)

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

```json
{
  "version": "1",
  "default": "deny",
  "hide": [
    "delete"
  ]
}
```

## Other tools on Redis (3)

- `get` — Read — https://policylayer.com/tools/redis/get.md
- `list` — Read — https://policylayer.com/tools/redis/list.md
- `set` — Write — https://policylayer.com/tools/redis/set.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=redis · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/redis