New Your team’s decisions, in one playbook every coding agent works from. Never answer your agent twice

Ya Frida

61 tools. 39 can modify or destroy data without limits.

4 destructive tools with no built-in limits. Policy required.

Last updated:

39 can modify or destroy data
22 read-only
61 tools total

Community server · catalogue entry checked 28/09/2026

How to control Ya Frida ↓

What Ya Frida exposes to your agents

Read (22) Write / Execute (35) Destructive / Financial (4)
Critical Risk

The most dangerous Ya Frida tools

39 of Ya Frida's 61 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control Ya Frida

PolicyLayer is an MCP gateway — it sits between your AI agents and Ya Frida, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations
{
  "adb_forward_remove": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations
{
  "adb_push": {
    "limits": [
      {
        "counter": "adb_push_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "adb_devices": {
    "limits": [
      {
        "counter": "adb_devices_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

  1. Create a free account and register Ya Frida — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON YA FRIDA →

Instant setup, no code required.

All 61 Ya Frida tools

EXECUTE 31 tools
Execute adb_connect Connect to a device over TCP/IP (e.g. '192.168.1.100:5555'). Execute adb_disconnect Disconnect a TCP/IP device. Execute adb_forward Set up port forwarding (e.g. local='tcp:27042' remote='tcp:27042'). Execute adb_install Install an APK on the device. Execute adb_reboot Reboot the device. Execute adb_reverse Set up reverse port forwarding (device to host). Execute adb_root Restart adbd with root permissions. Execute adb_shell Run a shell command on the device and return its output. Execute adb_unroot Restart adbd without root permissions. Execute frida_attach frida_attach Execute frida_compile_script frida_compile_script Execute frida_detach Detach from a process session. Execute frida_disable_child_gating Disable child gating on a session. Execute frida_disable_spawn_gating Disable spawn gating on the device. Execute frida_enable_child_gating Enable child gating on a session. Execute frida_enable_spawn_gating Enable spawn gating on the device. Execute frida_eternalize_script Eternalize a script so it persists after detaching from the session. Execute frida_fix_usap frida_fix_usap Execute frida_inject frida_inject Execute frida_inject_library_blob frida_inject_library_blob Execute frida_inject_library_file frida_inject_library_file Execute frida_memory_protect Change memory protection flags. Execute frida_memory_write Write bytes to process memory. Execute frida_post_message Post a message to an injected script. Execute frida_resume Resume a suspended process. Execute frida_rpc_call frida_rpc_call Execute frida_server_start Start frida-server on the device (must already be pushed). Execute frida_server_stop Stop frida-server on the device. Execute frida_snapshot_script frida_snapshot_script Execute frida_spawn frida_spawn Execute frida_unload_script Unload a previously injected script.
READ 22 tools
Read adb_devices List all ADB-connected devices with their state and properties. Read adb_getprop Read a system property (e.g. 'ro.build.version.sdk'). Read adb_logcat Capture logcat output (dump mode). Use filters like 'ActivityManager:I :S'. Read adb_pull Pull a file or directory from the device to local machine. Read frida_enumerate_exports Enumerate exports of a specific module. Read frida_enumerate_modules frida_enumerate_modules Read frida_enumerate_pending_children List pending child processes that are waiting to be resumed. Read frida_enumerate_pending_spawn List pending spawned processes that are waiting to be resumed. Read frida_get_device Get info for a specific device. Uses default device if ID is omitted. Read frida_get_frontmost_application Get details about the frontmost application. Read frida_get_messages Retrieve and drain pending messages from an injected script. Read frida_list_exports List RPC exports available on an injected script. Read frida_list_scripts List all active script IDs. Read frida_list_sessions List all active session PIDs. Read frida_ls_apps frida_ls_apps Read frida_ls_apps_running List only currently running applications. Read frida_ls_devices List all available Frida devices (local, USB, remote). Read frida_memory_read Read bytes from process memory. Read frida_memory_scan Scan process memory for a byte pattern. Read frida_ps frida_ps Read frida_query_system_parameters Returns a dictionary of information about the host system. Read frida_server_status Check if frida-server is running on the device and whether its version matches the local Frida client.

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

Questions about Ya Frida

Can an AI agent delete data through the Ya Frida MCP server? +

Yes. The Ya Frida server exposes 4 destructive tools including adb_forward_remove, adb_reverse_remove, adb_uninstall. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Ya Frida? +

The Ya Frida server has 4 write tools including adb_push, frida_add_remote, frida_remove_remote. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Ya Frida.

How many tools does the Ya Frida MCP server expose? +

61 tools across 4 categories: Destructive, Execute, Read, Write. 22 are read-only. 39 can modify, create, or delete data.

How do I enforce a policy on Ya Frida? +

Register the Ya Frida MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Ya Frida tool call.

Deterministic rules across all 61 Ya Frida tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Instant setup, no code required.

61 Ya Frida tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from Ya Frida's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.