// teleport guide · Database · community

Teleport Redis MCP — read-only, P2P, zero cloud

Redis MCP servers talk to your cache with full command power. The dangerous ones are exactly what they sound like: DEL and FLUSHALL against production. Whitelist reads and information commands, and let the firewall make everything else nonexistent to the peer. This guide maps all 10 tools of @gongrzmax/redis-mcp-server by blast radius, then gives you the exact command to share it with a remote teammate's AI agent — capability without credentials.

3SAFE to expose

3CAUTION

4KEEP LOCAL

0servers involved

host terminal — read-only share command

npx -y mcpwire share --allow "redis_keys,redis_ttl,redis_type" --redact-secrets --ttl 30m -- npx -y @gongrzmax/redis-mcp-server

Only the 3 read-only tools are exposed; the other 7 are invisible to the peer (filtered from tools/list and blocked if forced). Tunnel dies in 30 minutes. Add --confirm to approve every call, or --max-calls 20 for a hard budget.

peer config — claude_desktop_config.json / .cursor/mcp.json

{
  "mcpServers": {
    "teleported-redis": {
      "command": "npx",
      "args": [
        "-y",
        "mcpwire",
        "join",
        "wire://<TICKET_FROM_HOST_BANNER>"
      ]
    }
  }
}

🛡️ tool risk map — Redis

tool	risk	notes
`redis_get`	CAUTION	Reads keys — values may contain sessions/PII.
`redis_keys`	SAFE	Key listing.
`redis_ttl`	SAFE	TTL inspection.
`redis_type`	SAFE	Key type.
`redis_lrange`	CAUTION	List reads.
`redis_smembers`	CAUTION	Set reads.
`redis_set`	HIGH RISK	Writes keys.
`redis_del`	HIGH RISK	Deletes keys.
`redis_flushall`	HIGH RISK	Nukes the database. Never teleport.
`redis_expire`	HIGH RISK	Changes key lifetimes.

🔒 Why not just share your token?

Redis's credential would grant the full toolset to a foreign LLM — including redis_set and redis_del. With mcpwire the credential stays in your env; the peer only ever holds an expiring wire:// capability scoped to 3 tools.

🎥 Audit everything

Add --record session.wirelog and every call, block and redaction is logged locally. Drag the file into mcpwire.co/replay for a DevTools-style waterfall of what the remote agent actually did.

🔁 Works with every MCP client

Claude Desktop, Cursor, Windsurf, Cline — anything speaking MCP over stdio. Your peer pastes the snippet above; you keep the kill-switch (Ctrl+C) in your terminal.

What happens if the peer's agent tries to call a blocked Redis tool?

The request never reaches your MCP server. mcpwire answers with a JSON-RPC error (-32601 [MCPWire Firewall]) and logs the attempt — the tool doesn't exist from the agent's point of view, so well-behaved agents won't even try.

Can I expose the caution-level tools too?

Yes — just add them to --allow or run with --confirm so each call waits for your y/n in the host terminal. The risk map above tells you exactly what you'd be signing up for.

Is the traffic really serverless?

Yes. Discovery goes through the public Hyperswarm DHT; the data path is a direct Noise-encrypted socket between the two machines (UDP hole punching). If both NATs are stubborn, Hyperswarm routes through community relays — which only see ciphertext.

← all teleport guides ⚡ open the policy builder

🔒 MCPWire Enterprise & Team Mesh (Early Access)

Need persistent wire://your-company/db namespaces, SSO / GitHub identity verification before the P2P handshake, and centralized audit logs for compliance (SOC2 / ISO)?