# adb_reverse

Set up reverse port forwarding (device to host).

Agent View of the PolicyLayer registry record for `adb_reverse`. HTML page: https://policylayer.com/tools/1shin-7-ya-frida-mcp/adb-reverse

## Facts

- Tool: `adb_reverse`
- Server: Ya Frida (`1shin-7/ya-frida-mcp`) — https://policylayer.com/tools/1shin-7-ya-frida-mcp.md
- Homepage: https://github.com/1shin-7/ya-frida-mcp
- Risk category: Execute (High risk)
- Registry record: grade F, identity unverified
- 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": "adb_reverse",
    "arguments": {}
  }
}
```

## Why adb_reverse is rated High

This tool configures reverse port forwarding from a device to the host, which establishes a network tunnel/socket binding. This is an active network configuration operation that triggers external operations with side effects (binding ports, routing traffic), placing it in the Execute category. Misuse could expose host services to a connected device or be used to exfiltrate data.

From the tool's own definition: "Set up reverse port forwarding (device to host)"

## Use case

AI agents invoke adb_reverse to trigger actions in Ya Frida. 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 Ya Frida:

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

## Other tools on Ya Frida (60)

- `adb_forward_remove` — Destructive — https://policylayer.com/tools/1shin-7-ya-frida-mcp/adb-forward-remove.md
- `adb_reverse_remove` — Destructive — https://policylayer.com/tools/1shin-7-ya-frida-mcp/adb-reverse-remove.md
- `adb_uninstall` — Destructive — https://policylayer.com/tools/1shin-7-ya-frida-mcp/adb-uninstall.md
- `frida_kill` — Destructive — https://policylayer.com/tools/1shin-7-ya-frida-mcp/frida-kill.md
- `adb_connect` — Execute — https://policylayer.com/tools/1shin-7-ya-frida-mcp/adb-connect.md
- `adb_disconnect` — Execute — https://policylayer.com/tools/1shin-7-ya-frida-mcp/adb-disconnect.md
- `adb_forward` — Execute — https://policylayer.com/tools/1shin-7-ya-frida-mcp/adb-forward.md
- `adb_install` — Execute — https://policylayer.com/tools/1shin-7-ya-frida-mcp/adb-install.md
- `adb_reboot` — Execute — https://policylayer.com/tools/1shin-7-ya-frida-mcp/adb-reboot.md
- `adb_root` — Execute — https://policylayer.com/tools/1shin-7-ya-frida-mcp/adb-root.md
- `adb_shell` — Execute — https://policylayer.com/tools/1shin-7-ya-frida-mcp/adb-shell.md
- `adb_unroot` — Execute — https://policylayer.com/tools/1shin-7-ya-frida-mcp/adb-unroot.md
- `frida_attach` — Execute — https://policylayer.com/tools/1shin-7-ya-frida-mcp/frida-attach.md
- `frida_compile_script` — Execute — https://policylayer.com/tools/1shin-7-ya-frida-mcp/frida-compile-script.md
- `frida_detach` — Execute — https://policylayer.com/tools/1shin-7-ya-frida-mcp/frida-detach.md
- `frida_disable_child_gating` — Execute — https://policylayer.com/tools/1shin-7-ya-frida-mcp/frida-disable-child-gating.md
- `frida_disable_spawn_gating` — Execute — https://policylayer.com/tools/1shin-7-ya-frida-mcp/frida-disable-spawn-gating.md
- `frida_enable_child_gating` — Execute — https://policylayer.com/tools/1shin-7-ya-frida-mcp/frida-enable-child-gating.md
- `frida_enable_spawn_gating` — Execute — https://policylayer.com/tools/1shin-7-ya-frida-mcp/frida-enable-spawn-gating.md
- `frida_eternalize_script` — Execute — https://policylayer.com/tools/1shin-7-ya-frida-mcp/frida-eternalize-script.md
- `frida_fix_usap` — Execute — https://policylayer.com/tools/1shin-7-ya-frida-mcp/frida-fix-usap.md
- `frida_inject` — Execute — https://policylayer.com/tools/1shin-7-ya-frida-mcp/frida-inject.md
- `frida_inject_library_blob` — Execute — https://policylayer.com/tools/1shin-7-ya-frida-mcp/frida-inject-library-blob.md
- `frida_inject_library_file` — Execute — https://policylayer.com/tools/1shin-7-ya-frida-mcp/frida-inject-library-file.md
- `frida_memory_protect` — Execute — https://policylayer.com/tools/1shin-7-ya-frida-mcp/frida-memory-protect.md
- `frida_memory_write` — Execute — https://policylayer.com/tools/1shin-7-ya-frida-mcp/frida-memory-write.md
- `frida_post_message` — Execute — https://policylayer.com/tools/1shin-7-ya-frida-mcp/frida-post-message.md
- `frida_resume` — Execute — https://policylayer.com/tools/1shin-7-ya-frida-mcp/frida-resume.md
- `frida_rpc_call` — Execute — https://policylayer.com/tools/1shin-7-ya-frida-mcp/frida-rpc-call.md
- `frida_server_start` — Execute — https://policylayer.com/tools/1shin-7-ya-frida-mcp/frida-server-start.md
- …and 30 more: https://policylayer.com/tools/1shin-7-ya-frida-mcp.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=1shin-7-ya-frida-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/1shin-7-ya-frida-mcp