Lets an AI client dynamically instrument Android and iOS apps to explore classes, hook methods, trace calls, scan memory and capture TLS keys.
Also known as monkeywave/frida-mobile-mcp, frida-mobile-mcp
- Stars
- 21
- Tools
- 71
- Downloads, 30 days
- 1,541
- Latest version
- 0.7.3
- Last commit
- Nov 12, 2026
- License
- MIT
What is Frida MCP?
Frida lets an AI client dynamically instrument Android and iOS apps to explore classes, hook methods, trace calls, scan memory and capture TLS keys. It exposes 71 tools, such as get_status, frida_help, explore_app.
Summary generated from the project's README
About Frida MCP server
Security researchers and mobile developers can perform dynamic instrumentation of Android and iOS applications through this MCP server. It connects to devices or emulators running frida-server 17.x to allow an AI client to explore classes, hook methods, and trace calls in real time. The server works locally via stdio and supports integration with clients like Claude Desktop, Cursor, and VS Code.
Users can perform advanced tasks such as bypassing SSL pinning, capturing TLS keys and plaintext using friTap, and scanning memory for secrets like AES keys or JWTs. The server provides 71 tools ranging from high-level automation, like driving the UI toward uncovered code, to low-level primitives for memory dumps and address resolution. It is designed to work alongside static analysis tools by using a consistent module and offset notation for results.
Setup requires Node.js and a compatible mobile device. For non-jailbroken iOS devices, the server can assist in generating configurations for the Frida Gadget to enable instrumentation. The server also includes features to validate custom scripts and run prebuilt analysis routines to ensure compatibility with the Frida 17 runtime.
Written from the project's README. Every use case is checked against a quote from it.
How to install Frida MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Frida MCP in Claude Code
$ claude mcp add --env 'FRIDA_MCP_HTTP_TOKEN=<YOUR_FRIDA_MCP_HTTP_TOKEN>' --env 'FRIDA_MCP_REMOTE_TOKEN=<YOUR_FRIDA_MCP_REMOTE_TOKEN>' frida-mobile-mcp -- npx -y frida-mobile-mcpInstall Frida MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"frida-mobile-mcp": {
"command": "npx",
"args": [
"-y",
"frida-mobile-mcp"
],
"env": {
"FRIDA_MCP_HTTP_TOKEN": "<YOUR_FRIDA_MCP_HTTP_TOKEN>",
"FRIDA_MCP_REMOTE_TOKEN": "<YOUR_FRIDA_MCP_REMOTE_TOKEN>"
}
}
}
}Install Frida MCP in VS Code
.vscode/mcp.json
{
"servers": {
"frida-mobile-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"frida-mobile-mcp"
],
"env": {
"FRIDA_MCP_HTTP_TOKEN": "<YOUR_FRIDA_MCP_HTTP_TOKEN>",
"FRIDA_MCP_REMOTE_TOKEN": "<YOUR_FRIDA_MCP_REMOTE_TOKEN>"
}
}
}
}Install Frida MCP in VS Code CLI
$ code --add-mcp '{"name":"frida-mobile-mcp","type":"stdio","command":"npx","args":["-y","frida-mobile-mcp"],"env":{"FRIDA_MCP_HTTP_TOKEN":"<YOUR_FRIDA_MCP_HTTP_TOKEN>","FRIDA_MCP_REMOTE_TOKEN":"<YOUR_FRIDA_MCP_REMOTE_TOKEN>"}}'Install Frida MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"frida-mobile-mcp": {
"command": "npx",
"args": [
"-y",
"frida-mobile-mcp"
],
"env": {
"FRIDA_MCP_HTTP_TOKEN": "<YOUR_FRIDA_MCP_HTTP_TOKEN>",
"FRIDA_MCP_REMOTE_TOKEN": "<YOUR_FRIDA_MCP_REMOTE_TOKEN>"
}
}
}
}Install Frida MCP in Codex
$ codex mcp add frida-mobile-mcp --env 'FRIDA_MCP_HTTP_TOKEN=<YOUR_FRIDA_MCP_HTTP_TOKEN>' --env 'FRIDA_MCP_REMOTE_TOKEN=<YOUR_FRIDA_MCP_REMOTE_TOKEN>' -- npx -y frida-mobile-mcpInstall Frida MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.frida-mobile-mcp] command = "npx" args = ["-y", "frida-mobile-mcp"] [mcp_servers.frida-mobile-mcp.env] FRIDA_MCP_HTTP_TOKEN = "<YOUR_FRIDA_MCP_HTTP_TOKEN>" FRIDA_MCP_REMOTE_TOKEN = "<YOUR_FRIDA_MCP_REMOTE_TOKEN>"
Install Frida MCP in Gemini CLI
$ gemini mcp add -s user -e 'FRIDA_MCP_HTTP_TOKEN=<YOUR_FRIDA_MCP_HTTP_TOKEN>' -e 'FRIDA_MCP_REMOTE_TOKEN=<YOUR_FRIDA_MCP_REMOTE_TOKEN>' frida-mobile-mcp npx -- -y frida-mobile-mcpInstall Frida MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"frida-mobile-mcp": {
"command": "npx",
"args": [
"-y",
"frida-mobile-mcp"
],
"env": {
"FRIDA_MCP_HTTP_TOKEN": "<YOUR_FRIDA_MCP_HTTP_TOKEN>",
"FRIDA_MCP_REMOTE_TOKEN": "<YOUR_FRIDA_MCP_REMOTE_TOKEN>"
}
}
}
}Started by HostedMCP on 16 Nov 2026
We ran this command for frida-mobile-mcp 0.7.3 in an isolated container with no network and no keys. It answered and listed 71 tools.
Frida MCP tools 71
Read from the server with tools/listget_statusRead-onlyGet an overview of connected devices, active sessions (with platform, script count and last activity), hooks, traces, and the most recent session detaches / process crashes (recent_detaches). Use this first to understand what is available before starting any instrumentation work, and after a session is lost to see why.
frida_helpRead-onlyGet help on how to use frida-mobile-mcp tools. Use this to learn about available capabilities, method hooking patterns, address notation, script kinds (classic/esm/bundle), TLS capture and example workflows. Topics: overview, hooking, tracing, memory, scripts, native, tls, mobile, examples, advanced, evasion, script_catalog, script_api, recipes, interop.
explore_appActionLaunch a mobile app and gather comprehensive initial context including loaded classes, modules, and libraries. This is the recommended starting point for any app analysis. The app will be spawned in suspended mode, instrumented, then resumed. Returns: pid, platform, loaded modules, and filtered class list.
hook_methodActionHook a method to intercept calls with auto device/session management. Provide the app target (or a session_id of an existing session) and method pattern. Supports Java methods (Android: "com.example.Class.method"), Objective-C methods (iOS: "-[NSURLSession dataTaskWithRequest:]"), and native functions in any notation: "libssl.so!SSL_read" (module export), "libfoo.so+0x1234" or "libfoo.so+4660" (module-relative offset, as shown by Ghidra/IDA), "0x7f1234567890" (absolute address), or "!open" (global export searched across all modules). Native backtraces are reported as "module+0xoff (symbol)". Java overloads: append a signature to hook ONE overload, e.g. "com.pkg.Class.encrypt(byte[], java.lang.String)" (without one, every overload is hooked). Static-analysis findings can be passed as "evidence" instead of "method": {module, offset} (image-base-relative offset from Ghidra/IDA) or {module, address, image_base}, or {class, signature} for Java (jadx/describe_class/JVM descriptor). After hooking, use get_messages to retrieve intercepted calls.
trace_methodActionTrace function calls matching a pattern for a specified duration. Simplified frida-trace equivalent. Supports glob patterns like "com.example.network.*" for Java, "-[NSURL*]" for ObjC, and "libssl.so!SSL_*" for native. Returns all captured invocations after the duration expires.
execute_scriptActionExecute a custom Frida JavaScript/TypeScript script in a target process (Frida 17 agent). Provide either inline source code or a file path. Three source kinds are supported and detected automatically (override with `source_kind`): classic (non-module) JavaScript, where the `Java` and `ObjC` globals are auto-injected by platform (Java on Android, ObjC on iOS/macOS; override with `bridges`) so legacy Java.perform()/ObjC scripts keep working with their own line numbers; ES modules (import/export, JS or TS) such as `import Java from "frida-java-bridge"`, which are compiled on the host with the Frida Compiler (bridges are bundled by the imports, so `bridges` is ignored); and frida-compile bundles (source starting with the 📦 marker), which are loaded as-is. The full Frida API (Interceptor, Memory, Module, Process, NativePointer, ...) is available everywhere. Results are sent via send() and retrieved with get_messages. `timeout_ms` bounds the script's initial run (default 30000 for one-shot scripts, 0 for persistent ones); a script that overruns is interrupted, then terminated, and the call fails with SCRIPT_TIMEOUT including the partial messages. Use validate_script to check syntax/types without a device. Note: custom scripts must be explicitly enabled in config (allowCustomScripts: true).
search_classes_and_methodsRead-onlySearch for classes and their methods by pattern in a running app. Combines class enumeration and method listing. Use regex patterns like "Login", "com\.example\.auth.*", or "NSURLSession". Returns matching classes with their methods when include_methods is true.
describe_classRead-onlyReturn the full shape of ONE loaded app class so you can pick an exact method overload before hooking. Android: every declared method with parameter types, return type, modifiers and a ready-to-use `signature` (e.g. "encrypt(byte[], java.lang.String)"), constructors (as "$init(...)"), fields, superclass and interfaces; searches all class loaders. iOS: selectors with Objective-C type encodings, superclass and protocols. Pass a returned signature verbatim to hook_method as evidence: {class, signature} to hook exactly that overload. The class must already be loaded; if it is not, use watch_loads or search_classes_and_methods.
discover_cryptoRead-onlyFind where an app actually performs cryptography (or any API family), without assuming javax.crypto. In one pass it enumerates: Java/ObjC classes whose name matches a pattern (across all class loaders), and native export symbols matching the pattern or a known crypto/TLS symbol (EVP_*, SSL_read/write, CCCrypt, RC4, AES_, mbedtls_, ...). Returns ranked candidates — app-owned classes first, then framework classes, then native symbols. Native candidates hook as-is ("module!symbol"); Java/ObjC candidates are CLASSES — pass "Class.method" to hook_method (method names are in the `java` list), or trace "Class.*". Use this before guessing a hook when the goal is "capture the key", "trace the cipher", etc.
find_secrets_in_memoryRead-onlyScan live process memory for the STRUCTURE of secrets, not just names or byte patterns. Finds keys even when you never reached the code that uses them: an RC4 key schedule (256-byte permutation of 0..255, byte[] or Java int[256] — the rc4demo case), an AES key schedule (aeskeyfind-style verification, AES-128/192/256, both encryption AND decryption schedules — and it is MODE-INDEPENDENT: the same expanded key backs CBC/CTR/GCM/XTS), a ChaCha20/XChaCha20 key (located by the exact "expand 32-byte k" sigma constant, key at +16) and Salsa20 state, high-entropy 16/24/32-byte buffers (candidate symmetric keys), PEM/DER private-key headers, and JWT tokens. Raw-key-only ciphers (AES-NI with no in-memory schedule) fall back to high_entropy_key + monitor_crypto at the API boundary. Defaults to writable (heap) ranges where live keys sit. Returns candidates with a module+offset address and a hex/text preview; read the full bytes with read_memory, or hand one to generate_memory_pattern. Complements discover_crypto (name-only) and scan_memory (fixed byte-pattern only).
trace_coverageActionArm a broad set of cheap entry-hooks over a target set and track which have been REACHED (covered) vs which are still COLD — the reachability signal for a drive loop. Unlike trace_method (time-boxed, logs every call), this is persistent and entry-only: it answers "what code have I NOT exercised yet, so where should I keep driving?". Scope can be a single class (all its methods), a class/package glob ("com.example.*"), a native module glob ("libfoo.so!*"), or an ObjC pattern ("-[MyClass *]"). Workflow: arm it, then alternate trigger_and_wait (drive the UI) with trace_coverage {report_only:true} to watch the cold set shrink. Each target fires at most once (first-seen), so hot methods do not flood output. Set engine="stalker" with `module` for a time-boxed basic-block map of one native module (Stalker; CPU heavy) returned as module+0xoffset blocks.
monitor_cryptoActionCast a wide net over cryptography instead of hooking one method at a time. In a single persistent script it discovers and hooks ALL likely crypto sinks at once — app-owned Java classes whose name matches a crypto pattern (every overload of every declared method), plus the framework sinks that almost every app funnels through: javax.crypto Cipher (doFinal/init/getInstance), Mac, MessageDigest and SecretKeySpec on Android; CommonCrypto (CCCrypt, CCCryptorCreate, CC_SHA256, CC_MD5) on iOS; and native OpenSSL/BoringSSL (EVP_*Update, RC4, AES_set_encrypt_key). Every call dumps its byte[]/String key, input and output as hex, so you capture the key and plaintext WITHOUT knowing the exact method. This is persistent instrumentation (like hook_method): it returns immediately, then you drive the app and read the captured events with get_messages. Use when the goal is "grab the key / see the plaintext" and discover_crypto gave too many candidates to hook by hand.
Show all 71 toolsShow fewer tools
generate_memory_patternRead-onlyTurn a secret you already located (e.g. from find_secrets_in_memory) into a reusable anchor pattern: a stable byte signature near the key plus the offset from it to the key. Reads a small window around the address, then derives a recognizer-aware anchor (ChaCha sigma constant, PEM/DER/JWT header, or the longest stable run adjacent to the key). Returns a scan_memory pattern to re-locate the secret by shape across restarts, plus a friTap offsets entry and an ms_agent anchor to hand to capture_tls. This finds no new secret — give it one you have.
watch_loadsActionInstall a persistent watcher that reports what the app does AFTER attach, straight into the session message buffer. Three signal families, each toggleable: (1) native libraries (.so) loaded late (dlopen/android_dlopen_ext), observed via Frida's loader module-load notifications — no dlopen hook, so it will not destabilize the target — meaning a library that only appears after a UI action is still seen; (2) Java classes loaded late via ClassLoader.loadClass (Android only; the Java.available guard makes it a no-op elsewhere); (3) anti-instrumentation / anti-debug reads of canonical /proc locations (maps, status, task) via open/fopen. The watcher stays loaded and keeps emitting: drive the app (e.g. mobile_action), then call get_messages to read the watch_event entries. Pair with discover_crypto / hook_method once a late-loaded target shows up. Set spoof=true (needs memoryWriteEnabled) to go beyond reporting and actively scrub Frida signatures / zero TracerPid from those /proc reads; for a fuller stealth set use the anti_frida_evasion prebuilt script.
read_memoryRead-onlyRead raw memory from a target process. Requires an active session. Address in any notation: "0x7fff12345678" (absolute), "libfoo.so+0x1234" or "libfoo.so+4660" (module-relative offset), "libssl.so!SSL_read" (module export), or "!open" / "open" (global export). Max 4MB per read. Returns hex-encoded bytes plus the resolved absolute address and module+offset (rva).
write_memoryActionWrite raw bytes to process memory. DISABLED by default for safety - enable via config (memoryWriteEnabled: true). Provide hex-encoded data. Address in any notation: "0x7fff12345678" (absolute), "libfoo.so+0x1234" or "libfoo.so+4660" (module-relative offset), "libssl.so!SSL_read" (module export), or "!open" / "open" (global export).
scan_memoryRead-onlyScan process memory for a byte pattern. Pattern format: "48 89 5c 24 ?? 57" where ?? is a wildcard. Optionally limit scan to a specific module.
get_messagesRead-onlyRetrieve buffered messages from active scripts and hooks. Messages include hook invocations, trace hits, script output (send() calls), and errors. Use "since" for pagination to get only new messages.
stop_instrumentationActionClean up all hooks, scripts, and traces on a target. The "undo everything" tool. Detaches the Frida session and frees all resources. Use when you are done analyzing an app or want to start fresh.
unload_scriptActionUnload a single script (hook, trace or custom script) from a session while keeping the session attached. Use the script_id returned by hook_method, trace_method, execute_script or run_prebuilt_script. Hooks and traces that belong to the script are removed from the server state. Use stop_instrumentation to tear down a whole session instead. Java-bridge scripts must be unloaded newest-first (unloading an older one first can crash the app): if newer Java-bridge scripts are loaded, the call fails with UNLOAD_ORDER_UNSAFE listing them, unless cascade=true, which unloads those newer scripts first and reports them in cascaded_scripts.
trigger_and_waitActionCorrelate a UI action with instrumentation output in one round-trip: optionally perform a mobile_action (tap/launch/type) on the session's device, then block until at least `expect_messages` new messages/hook hits arrive (or timeout). Returns exactly the messages the trigger produced and which hooks fired. This is how you confirm "this tap ran the hooked code" — or learn "nothing fired, the hypothesis is wrong" — instead of tapping blindly and polling get_messages. Install hooks first (hook_method / discover_crypto → hook_method), then trigger_and_wait.
validate_scriptRead-onlyCheck a Frida script for syntax, type and Frida 17 API problems without a device. Use it before execute_script. Classic (non-module) scripts get a JavaScript syntax check plus a lint for APIs removed in Frida 17 (static Module/Memory helpers, *Sync enumerators); referencing them throws at runtime, so they make the result not ok. ES module scripts (import/export) are compiled with the Frida Compiler: strict (default) runs a full TypeScript type check; plain JavaScript is only syntax-checked unless language is "ts". frida-compile bundles (source starting with the 📦 marker) are accepted as-is. Provide either inline source or a file path.
save_scriptActionSave a Frida script to the local library (~/.config/frida-mobile-mcp/scripts/) so it can be re-run later with run_saved_script or shared with export_script. Stores the raw source as <name>.js plus a <name>.json metadata file (sha256, size, created timestamp, description). Names are restricted to letters, digits, underscores and hyphens. Refuses to overwrite an existing script unless overwrite is true. Requires allowCustomScripts to be enabled in config.
list_saved_scriptsRead-onlyList the Frida scripts saved in the local library (~/.config/frida-mobile-mcp/scripts/) with their description, creation time and size. Returns an empty list when nothing has been saved yet. No device is required.
run_saved_scriptActionLoad a script previously saved with save_script into a target process. Resolves (or reuses) a session the same way execute_script does and runs the stored source as a custom agent: classic JavaScript gets the Java/ObjC bridges injected by platform, ES modules are compiled with the Frida Compiler, and frida-compile bundles are loaded as-is. Provide a target (app id, process name or PID) or an existing session_id. Requires allowCustomScripts to be enabled in config.
export_scriptActionTurn a Frida script into a STANDALONE classic .js file that the plain frida / frida-tools 17 CLI can run with `frida -U -f <package> -l file.js`, without this MCP server. The output is a header comment + the frida-mobile-mcp preamble helpers + the script body. Provide exactly one of source (inline) or name (a saved script). It does NOT bundle the Java/ObjC bridges (the Frida 17 CLI injects those) and does NOT emit TypeScript. With out_path the file is written and its path returned; otherwise the text is returned inline. This tool only transforms text, so it does not require allowCustomScripts.
get_evidenceRead-onlyReturn the persisted record of an earlier tool call by its evidence_id (from the result envelope or `_meta.evidence_id`): tool, redacted parameters, status, session, device, duration, script SHA-256 and the full structured result or error body. Records survive server restarts until evicted by the evidence size limits.
export_evidence_bundleActionExport persisted tool results as one JSON or Markdown report for a write-up or for a static-analysis tool. Select records by explicit evidence_ids, or by session_id and/or since (newest `limit` matches, exported oldest first). With out_path (absolute, under the current directory, the OS temp directory, ~/.config/frida-mobile-mcp/dumps or the evidence directory) the bundle is written to that file (mode 0600); otherwise it is returned inline.
list_devicesRead-onlyEnumerate all Frida-visible devices including local, USB, and remote devices. Equivalent to frida-ls-devices CLI command.
select_deviceActionExplicitly select the active Frida device for subsequent operations.
get_device_infoRead-onlyGet detailed information about a device including OS version, architecture, and system parameters.
list_processesRead-onlyList running processes on the target device. Equivalent to frida-ps CLI command.
list_applicationsRead-onlyList installed and running applications on the target device.
get_frontmost_applicationRead-onlyGet the currently foreground application on the device.
spawn_processActionSpawn a new process in suspended state for early instrumentation. The process will be paused until resume_process is called. Set realm="emulated" to hook ARM libraries of an app running under native-bridge translation (Houdini/libndk) on an x86/x86_64 Android emulator (requires Frida >= 17.26 on device).
attach_processActionAttach to an already running process by PID or name. Set realm="emulated" to hook ARM libraries of an app running under native-bridge translation (Houdini/libndk) on an x86/x86_64 Android emulator (requires Frida >= 17.26 on device).
resume_processActionResume a suspended process (after spawn_process).
kill_processActionKill a process on the target device.
detach_sessionActionDetach from a specific Frida session, unloading all scripts.
spawn_gatingActionEnable, disable, or list device-wide spawn gating. When enabled, every newly spawned process (including app-launched child/isolated processes that often run RASP/anti-Frida checks) is held suspended until released. Use "list" to see pending spawns and children, then attach_process + hook_method, and resume_process to release each by PID.
child_gatingActionEnable or disable child gating on an existing session. When enabled, processes forked/exec'd by the instrumented process are held so they can be instrumented too (e.g. an app that moves detection into a child process). Requires device-wide spawn gating to catch the held children; list them with spawn_gating action="list".
eternalize_scriptActionMake a loaded script survive session detach: frida pins it in the target so it keeps running after we detach (or the host exits). Trade-off — once eternalized the script can no longer send messages back, be unloaded, or be inspected; it is fire-and-forget persistence. Use it to leave a bypass/monitor running while you free the session. Give the session_id and the script_id returned by hook_method / execute_script / watch_loads.
list_sessionsRead-onlyList all active Frida sessions managed by this server.
enumerate_modulesRead-onlyList loaded modules (shared libraries) in the target process with name, base, end (base+size), size and path. Optional case-insensitive regex `filter` matches against name or path. Use base/end to rebase a Ghidra/IDA project; Addresses are absolute runtime pointers; subtract the module base to get the Ghidra/IDA offset (or use resolve_address with a "module+0xoff" target).
enumerate_exportsRead-onlyList exports (functions and variables) of a specific module, paginated with offset/limit. Hook results with hook_method using "module!name". Addresses are absolute runtime pointers; subtract the module base to get the Ghidra/IDA offset (or use resolve_address with a "module+0xoff" target).
enumerate_importsRead-onlyList imports of a specific module (functions it calls in other libraries), paginated with offset/limit. Each entry carries the providing `module` when known, so "module!name" can be hooked directly. Addresses are absolute runtime pointers; subtract the module base to get the Ghidra/IDA offset (or use resolve_address with a "module+0xoff" target).
enumerate_symbolsRead-onlyList symbols (including non-exported/debug symbols) of a specific module. Only available on Linux, Android, iOS and macOS. Filtering (case-insensitive regex on the symbol name) and offset/limit paging happen inside the agent, so large symbol tables stay cheap. Addresses are absolute runtime pointers; subtract the module base to get the Ghidra/IDA offset (or use resolve_address with a "module+0xoff" target).
hook_functionActionLow-level hook with custom onEnter/onLeave JavaScript handlers. For advanced use when hook_method does not provide enough control. Custom handler bodies require allowCustomScripts: true in config; without them the hook sends default enter/leave events. Handler bodies are compiled as functions (new Function) inside the agent: `this` is the Interceptor invocation context (this.context, this.returnAddress, this.threadId, and any fields you set in on_enter are visible in on_leave). Java/ObjC globals are available (auto-injected by platform). A static-analysis finding can be passed as evidence {module, offset} or {module, address, image_base} instead of target.
unhook_functionActionRemove a specific hook by its hook ID.
resolve_addressRead-onlyTranslate between absolute process addresses and static-analysis coordinates. Give "0x7f..." to get module+0xoffset (+ nearest symbol); give "libfoo.so+0x1234" or "libfoo.so!func" to get the absolute runtime address. Use it to hand addresses between Frida and Ghidra/IDA.
analyze_native_functionRead-onlyStatic-style analysis of a native function at runtime: function range (Process.findFunctionRange), basic blocks and edges (Frida 17.12+ ControlFlowGraph; falls back to linear disassembly until the first return and says so in `limitations`), and the first instructions. All addresses are reported as absolute and as module+0xoffset for cross-referencing with Ghidra/IDA.
dump_module_memoryActionDump a loaded module from process memory to a file on the host (e.g. an unpacked/decrypted library). The file is laid out base-relative: file offset 0 is the module base, readable ranges are copied in 1 MiB chunks, unreadable gaps are zero-filled, so it can be imported into Ghidra/IDA as a raw binary at the returned `base`. out_path must be absolute and inside the current directory, the OS temp directory or ~/.config/frida-mobile-mcp/dumps.
list_threadsRead-onlyList the threads of the target process (id, name, state, current pc as module+0xoffset). With backtraces: true each thread also gets a symbolised backtrace (up to 8 frames) captured from its register context.
inject_libraryActionInject a native agent library (.so/.dylib) from the host into a target process via Frida's injector, independent of the JS engine — the parity path for a prebuilt Frida gadget/agent or a custom .so. Runs arbitrary native code in the target, so it needs allowNativeInjection (a capability separate from allowCustomScripts). The library must match the device architecture (arm64-v8a etc.); its optional exported entrypoint is called with the data string. Returns the frida injectee id.
get_app_infoActionIdentify the exact installed artifact of an app: version, SDK levels, debuggable flag, installer, data/native-lib dirs and every APK (base + splits) with on-device sha256 and size (Android via fixed adb queries: pm path, dumpsys package, sha256sum, stat). With pull_to, pulls the APKs to the host and verifies their sha256 against the device. Use it to hand the same APK that runs to a static tool (REA inspect_android_package, jadx) and to record in a report which artifact was analysed. iOS returns the Frida application parameters without hashes.
run_prebuilt_scriptActionRun a pre-built Frida script from the built-in library. Call without script_name to list all available scripts. Available scripts include: ssl_pinning_bypass, root_jailbreak_bypass, class_enumeration, method_hook, crypto_monitor, network_inspector, keychain_prefs, filesystem_monitor, anti_frida_evasion.
drive_coverageActionAutonomously drive the UI of an already-instrumented session toward uncovered code and stop the moment a signal fires. This arms NOTHING — first arm monitor_crypto and/or trace_coverage, then call drive_coverage to tap through on-screen elements breadth-first, correlating each tap with new hook output (snapshot → tap → wait → delta, like trigger_and_wait in a loop). It stops on the first delta message that matches `stop_on` (default "crypto_event") or looks like a captured key/secret, when coverage stalls for several steps, when no untried elements remain, or at max_steps / the wall-clock cap. Supply `coverage_id` to measure the covered delta the drive produced. Use it to reach a crypto path hands-free instead of tapping manually; read the full output afterwards with get_messages.
bypass_ssl_pinningActionOne-click SSL certificate pinning bypass for the target app. Auto-detects platform (Android/iOS) and applies the appropriate bypass techniques. On Android: hooks TrustManager, OkHttp CertificatePinner, and Conscrypt. On iOS: hooks SecTrust, ATS, and BoringSSL verification. Returns which bypass methods were successfully installed.
mobile_actionActionGateway to mobile-mcp UI automation tools. Perform screenshots, taps, swipes, text input, app management and more. Common actions: mobile_take_screenshot, mobile_list_elements_on_screen, mobile_click_on_screen_at_coordinates (params: {x, y}), mobile_swipe_on_screen (params: {direction}), mobile_type_keys (params: {text}), mobile_launch_app (params: {appId}), mobile_list_apps. Call without action to see all available actions.
detect_app_technologiesRead-onlyDetect what libraries, frameworks, and security mechanisms an app uses. Returns structured results with recommended script targets. Run this before choosing which pre-built scripts to use.
search_recipesRead-onlySearch the purpose-indexed library of ready-to-run classic-JS Frida recipes (custom Java crypto-key capture, standard javax.crypto key/IV, native export hook, JNI RegisterNatives discovery, custom-classloader enumeration, intent/deeplink trace, WebView bridge, iOS Keychain). Returns ranked recipes with their classic-JS source and usage notes; adapt the source and run it with execute_script. An empty query lists the whole library.
frida_server_statusRead-onlyReport whether frida-server is running on an Android device (via adb): its PIDs, the device CPU ABI, the matching frida release arch, and the exact GitHub .xz asset URL to download for the installed frida-node version.
frida_server_installActionPush a local frida-server binary to an Android device and make it executable (adb push + chmod 755). Download and decompress the correct .xz for the device ABI first (frida_server_status gives the asset URL).
frida_server_startActionStart frida-server detached on an Android device (adb shell, daemonized with -D), optionally via su. Supports a custom listen address/port and a renamed binary path for stealth setups, then confirms the server came up.
frida_server_stopActionStop frida-server on an Android device by sending a signal to the matching process (adb shell pkill, optionally via su), then report any remaining PIDs.
adb_shellActionRun an arbitrary shell command on an Android device via `adb shell`. DISABLED by default: arbitrary command execution must be enabled with allowAdbShell (config) or FRIDA_MCP_ALLOW_ADB_SHELL=1. Enforces allowedDevices.
adb_logcatActionDump the last N lines of the Android logcat (one-shot, `adb logcat -t N`), optionally filtered by tag:priority specs, or clear the buffer. Useful for correlating app log output with instrumentation events.
adb_pullActionPull a file from an Android device to the host (`adb pull`). Enforces allowedDevices.
adb_pushActionPush a file from the host to an Android device (`adb push`). Enforces allowedDevices.
adb_forwardActionManage adb port forwards (`adb forward`): add a local->remote forward, remove one, or list them. Use it to reach a frida-server on a non-default device port (e.g. local "tcp:27042" -> remote "tcp:12345").
capture_tlsActionCapture TLS session keys (NSS key log format) and decrypted plaintext from the target using the friTap agent (OpenSSL/BoringSSL, Conscrypt, NSS, GnuTLS, wolfSSL, mbedTLS, Secure Transport, ...). By default the app is spawned suspended, friTap is loaded, then the app is resumed so early handshakes are caught (retried once with spawn_mode=early_resume when Android kills the suspended app for a start timeout). Key log lines are written to keylog_path (usable with Wireshark tls.keylog_file) and plaintext records are buffered as fritap_datalog messages for get_messages (requires full_capture). protocols widens hooking beyond TLS (e.g. rc4); probe, pairip_safe and no_loader_hook help when instrumentation crashes anti-tamper apps; attribute_sdk adds per-connection caller stacks. Needs the friTap agent bundle: pip install friTap, FRITAP_AGENT_PATH, or allow_download.
Configuration
FRIDA_MCP_HTTP_TOKENSecretBearer token required by HTTP clients. Only used with --transport http (required when --host is not loopback); unused for the default stdio transport.
FRIDA_MCP_REMOTE_TOKENSecretAuth token of the remote frida-server in FRIDA_MCP_REMOTE (frida-server --token).
FRIDA_DEVICE_IDFRIDA_DEVICE_IDDefault Frida device ID to use (e.g. emulator-5554 or a USB serial). Can also be set with --device.
FRIDA_MCP_ALLOW_ADB_SHELLSet to "1" to enable the adb_shell tool (arbitrary shell commands on an Android device via adb). Disabled by default.
FRIDA_MCP_ALLOW_CUSTOM_SCRIPTSSet to "1" to enable execution of custom Frida scripts (execute_script and custom hook_function handlers). Disabled by default.
FRIDA_MCP_ALLOW_NATIVE_INJECTIONSet to "1" to enable the inject_library tool (loads a native .so/.dylib into the target via Frida's injector). Disabled by default.
FRIDA_MCP_BRIDGES_DIRDirectory with prebuilt Java/ObjC bridge bundles (defaults to dist/bridges inside the package)
FRIDA_MCP_COMPILER_PROJECT_DIRCache directory for the frida.Compiler project used to compile ES module scripts
FRIDA_MCP_DEBUGSet to "1" to enable debug logging on stderr. Can also be set with --debug.
FRIDA_MCP_E2E_DEVICEFRIDA_MCP_EVIDENCESet to "0" to stop persisting every tool result (params, status, structured result) to the evidence store; "1" forces it on. Enabled by default.
FRIDA_MCP_EVIDENCE_MAX_MBSize cap of the evidence store in MB; oldest records are pruned beyond it. Defaults to 200.
FRIDA_MCP_EVIDENCE_PATHDirectory of the evidence store (records at <path>/YYYY-MM-DD/<evidence_id>.json plus index.jsonl, mode 0600). Defaults to ~/.config/frida-mobile-mcp/evidence.
FRIDA_MCP_HTTP_TOKENFRIDA_MCP_MAX_RESPONSE_CHARSMaximum number of characters in a single tool response; longer output is truncated.
FRIDA_MCP_MEMORY_WRITESet to "1" to enable the write_memory tool. Disabled by default for safety.
FRIDA_MCP_REMOTEhost[:port] of a remote frida-server to add as a remote device at startup (port defaults to 27042).
FRIDA_MCP_REMOTE_CERTPath to the PEM certificate of a TLS remote frida-server in FRIDA_MCP_REMOTE (frida-server --certificate).
FRIDA_MCP_RUNTIMEFrida script runtime to use for injected agents.
FRIDA_MCP_SCHEMA_PROFILETool schema profile. "compact" shortens tool schemas and descriptions for clients with small context windows.
FRIDA_MCP_SNAPSHOTSSet to "1" to use V8 script-runtime snapshots to speed up repeated script loads (requires FRIDA_MCP_RUNTIME=v8). Disabled by default.
FRIDA_MCP_TOOLS_EXCLUDEComma-separated tool-name globs that are never registered, e.g. "adb_*,frida_server_*".
FRIDA_MCP_TOOL_PROFILETool exposure profile. "core" registers only 32 core tools to keep the tool catalog small next to other MCP servers.
FRITAP_AGENT_PATHPath to a friTap fritap_agent.js bundle for capture_tls (otherwise the installed friTap Python package or a pinned download is used)
FRITAP_AGENT_SHA256Bare sha256 of the downloaded friTap agent for the selected FRITAP_VERSION tag. v2.6.5 is pinned in the package; set this for other tags.
FRITAP_VERSIONfriTap release tag to download when no local agent is found (default v2.6.5)
Automated checks
Ran Nov 16, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablemonkeywave/frida-mobile-mcp is public and reachablegithub.com/monkeywave/frida-mobile-mcp ↗Pass
- Package names this repository as its sourcefrida-mobile-mcp names monkeywave/frida-mobile-mcp as sourcenpmjs.com/package/frida-mobile-mcp ↗Pass
- Build provenance (Sigstore attestation)Sigstore attestation for frida-mobile-mcpnpmjs.com/package/frida-mobile-mcp/v/0.7.3#provenance ↗Pass
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-12github.com/monkeywave/frida-mobile-mcp ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from frida-mobile-mcpPass
- No critical advisory in the package or its dependenciesthe package checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model71 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledDestructive tools carry destructiveHintPass
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubfrida-mobile-mcp
An MCP server that gives AI agents dynamic instrumentation of Android and iOS apps through Frida 17, and runs next to REA, ReVa (Ghidra) and IDA MCP servers. It exposes 71 tools: high-level ones that manage devices, sessions and scripts for you (explore an app, hook a Java/ObjC/native method, trace calls, map reachability coverage and autonomously drive the UI toward it, find secrets in memory and turn them into reusable friTap patterns, cast a wide net over crypto, bypass SSL pinning, capture TLS keys and plaintext with friTap, run prebuilt analysis scripts, validate custom scripts) and low-level primitives (spawn/attach, module and symbol enumeration, address resolution, control-flow analysis, memory dumps). Addresses use the same module+0xoffset notation as Ghidra/IDA so results move between static and dynamic tools without conversion, and every result carries an evidence envelope (evidence_id, limitations, coverage). Optional UI automation goes through mobile-mcp.
Quick start
npx frida-mobile-mcp # stdio MCP server (default `serve` command)
frida-mobile-mcp doctor # check Node, frida-node, adb, devices, frida-server, bridge bundles
frida-mobile-mcp setup --client cursor # write the server into a client config (claude-code, claude-desktop, cursor, vscode, windsurf, codex)
frida-mobile-mcp gadget --platform android --print # generate a frida-gadget config.json + APK/IPA repackaging guidance
The gadget command generates a frida-gadget config.json (--interaction listen or --interaction script) and prints the APK/IPA repackaging steps. Embedding the gadget is the only way to instrument native detection that runs in .init_array / JNI_OnLoad before an attach-time script can load, and it removes the frida-server :27042 port as a fingerprint — see frida_help({ topic: "evasion" }).
Claude Code:
claude mcp add frida -- npx -y frida-mobile-mcp
Claude Desktop (claude_desktop_config.json):
{
"mcpServers": {
"frida": {
"command": "npx",
"args": ["-y", "frida-mobile-mcp"],
"env": { "FRIDA_DEVICE_ID": "emulator-5554" }
}
}
}
Per-client instructions, HTTP mode and remote frida-server setup are in docs/clients.md. A Claude Desktop extension manifest (manifest.json, MCPB) and an MCP registry entry (server.json) ship in the repo.
Requirements
-
Node.js >= 22.12 (CI runs 22 and 24 on Linux, macOS and Windows).
npm installruns thefridapackage's install script, which downloads the native frida-node prebuild. -
A device or emulator running frida-server 17.x. This package depends on frida-node
^17.26.2; frida-server on the device should be 17.26.x (same major is required, same minor is recommended;realm: 'emulated'needs >= 17.26).frida-mobile-mcp doctorprints both versions and flags mismatches. -
Android: download the matching
frida-server-17.x.y-android-<arch>.xzfrom https://github.com/frida/frida/releases, thenxz -d frida-server-17.26.2-android-arm64.xz adb push frida-server-17.26.2-android-arm64 /data/local/tmp/frida-server adb shell "chmod 755 /data/local/tmp/frida-server" adb shell "su -c '/data/local/tmp/frida-server &'" -
iOS: a jailbroken device with the matching Frida package from the Frida Cydia/Sileo repository. Non-jailbroken devices need the app repackaged with the Frida Gadget; the server then attaches to the gadget-enabled process like any other.
-
Optional:
pip install friTapforcapture_tls(otherwise the pinned agent is downloaded on first use), and network access fornpx -y @mobilenext/mobile-mcp@lateston firstmobile_action.
What is new for Frida 17
- Bridges are bundled. Frida 17 no longer ships the Java/ObjC bridges in the GumJS runtime.
npm run build:bridgesbundlesfrida-java-bridgeandfrida-objc-bridgeintodist/bridges/{java,objc}.js; the server injects the right one by platform (Java on Android, ObjC on iOS/macOS) ahead of every script. - Legacy scripts still work.
execute_scriptruns classic (non-module) scripts throughScript.evaluate, so aJava.perform(...)script written for Frida 16 runs unchanged and keeps its own line numbers in errors. ES modules (import Java from "frida-java-bridge", JS or TS) are compiled on the host with the Frida Compiler; frida-compile bundles (starting with the📦marker) are loaded as-is. - Removed APIs are linted.
validate_scriptflags the staticModule.findExportByName/findBaseAddress/enumerateExports,Memory.readX/writeXand*Syncenumerators that throw on Frida 17 and suggests the Module-instance /NativePointerreplacements. Generated scripts getfindExport(lib, name)andhookNative(lib, name, callbacks)helpers from the agent preamble, and template options as__FRIDA_MCP__.options. analyze_native_functionusesProcess.findFunctionRangeand the Frida 17.12+ControlFlowGraph(with a linear-disassembly fallback reported inlimitations).
Tool reference
Tier 1: high-level tools
| Tool | Description |
|---|---|
get_status |
Connected devices, active sessions (platform, script count, last activity), hooks, traces and recent detaches/crashes. Run first and after a session is lost. |
frida_help |
Topic help: overview, hooking, tracing, memory, scripts, native, tls, mobile, examples, advanced, evasion, script_catalog, script_api, recipes, interop. |
detect_app_technologies |
Fingerprint libraries, frameworks and security mechanisms; returns recommended script targets. |
explore_app |
Spawn an app suspended, instrument, resume; returns pid, platform, modules and a filtered class list. |
get_app_info |
Identify the installed artifact: version, SDK levels, debuggable, installer and every APK (base + splits) with on-device sha256/size; pull_to pulls and hash-verifies them for a static tool such as REA inspect_android_package. iOS: Frida app parameters only. |
search_classes_and_methods |
Regex search over classes (and methods with include_methods) in a running app. |
describe_class |
Full shape of one loaded class: every method overload with parameter/return types and a hook-ready signature, constructors, fields, superclass/interfaces (ObjC: selectors with type encodings). Feed a signature to hook_method evidence: {class, signature}. |
discover_crypto |
Find where an app does crypto (or any API family) without assuming javax.crypto: ranked candidate hook targets across Java/ObjC classes and native symbols. |
find_secrets_in_memory |
Content-aware memory scan for the structure of secrets: RC4 S-box (byte[] or Java int[256]), AES key schedule (aeskeyfind — encryption and decryption, mode-independent), ChaCha20/Salsa20 keys (sigma constant), high-entropy 16/24/32-byte keys, PEM/DER private keys, JWTs. Finds keys without reaching the code that uses them. |
generate_memory_pattern |
Turn a located secret into a reusable anchor pattern (stable byte signature near the key + offset): re-locate it with scan_memory, or hand it to friTap via capture_tls (patterns/offsets). |
monitor_crypto |
Crypto-oracle wide net: discover and hook all likely crypto sinks at once (app-owned classes + javax.crypto/Mac/MessageDigest, iOS CommonCrypto, native OpenSSL/BoringSSL) and dump every key, input and output as hex. |
trace_coverage |
Reachability map: arm cheap persistent entry-hooks over a class/package/module scope and track covered vs cold targets across trigger_and_wait drives, so you know what code you have not yet exercised. |
drive_coverage |
Autonomously drive an instrumented session's UI toward uncovered code — taps on-screen elements breadth-first and stops the instant a crypto/secret signal fires (or coverage stalls / max_steps). Pair with monitor_crypto / trace_coverage. |
watch_loads |
Watch for late-loaded .so libraries and Java classes, plus anti-Frida probes; emits watch_event messages as the app runs. |
trigger_and_wait |
Perform a UI action and block until the resulting hook/message output arrives, so you learn which hook a tap fired (or that none did). |
hook_method |
Hook Java (com.example.Class.method), ObjC (-[Class sel:]) or native targets (libssl.so!SSL_read, libfoo.so+0x1234, 0x7f..., !open) with auto session management; backtraces as module+0xoff (symbol). |
trace_method |
frida-trace style tracing of glob patterns (com.example.net.*, -[NSURL*], libssl.so!SSL_*) for a duration. |
execute_script |
Run a custom script: classic JS (bridges injected), ES module JS/TS (compiled with the Frida Compiler) or a frida-compile bundle. timeout_ms bounds the initial run. Requires allowCustomScripts. |
validate_script |
Syntax, type and Frida 17 removed-API check without a device. Use before execute_script. |
run_prebuilt_script |
Run one of the 9 prebuilt scripts below; call without script_name to list them. |
bypass_ssl_pinning |
One-click pinning bypass (Android: TrustManager, OkHttp CertificatePinner, Conscrypt; iOS: SecTrust, ATS, BoringSSL). |
capture_tls |
friTap: TLS session keys (NSS key log) and optional decrypted plaintext / synthetic pcap for OpenSSL/BoringSSL, Conscrypt, NSS, GnuTLS, wolfSSL, mbedTLS, Secure Transport and more. Accepts friTap patterns/offsets (e.g. from generate_memory_pattern or BoringSecretHunter) for stripped libraries. Options: protocols (tls/rc4/auto/all), pairip_safe, no_loader_hook, probe, attribute_sdk (per-connection fritap_caller_stack), default_fd, library_scan, experimental; stats include per_library. friTap v2.6.5, agent ABI 2 and 3. Use the tls_traffic_audit prompt for a guided flow; fritap mcp can analyse the resulting key log/pcap (see docs/interop.md). |
read_memory |
Read up to 4 MB at any address notation; returns hex plus absolute address and module+offset. |
write_memory |
Write hex bytes to memory. Disabled unless memoryWriteEnabled. |
scan_memory |
Byte-pattern scan (48 89 5c 24 ?? 57), optionally limited to a module. |
get_messages |
Buffered hook invocations, trace hits, send() output and errors; since paginates; the cursor (last_index) points after the last returned message, with truncated and remaining. |
get_evidence |
Re-read a persisted tool result (params, status, structured result) by evidence_id. |
export_evidence_bundle |
Export persisted results as a JSON or Markdown bundle, inline or to a file. |
stop_instrumentation |
Remove all hooks, scripts and traces on a target and detach (newest script first; eternalized scripts are skipped). Returns fritap_captures[] with final friTap stats. |
unload_script |
Unload a single script (hook, trace or custom) from a session while keeping it attached. Fails with UNLOAD_ORDER_UNSAFE if newer Java-bridge scripts are loaded; cascade: true unloads them first (cascaded_scripts). |
mobile_action |
Gateway to mobile-mcp UI automation (screenshot, elements, tap, swipe, type, launch app, list apps). |
search_recipes |
Search the purpose-indexed library of ready-to-run classic-JS recipes (custom crypto-key capture, native/JNI hooks, classloader/intent/WebView, iOS Keychain); returns ranked recipes with source to adapt and run via execute_script. |
save_script |
Save a script under ~/.config/frida-mobile-mcp/scripts for reuse. Requires allowCustomScripts. |
list_saved_scripts |
List scripts saved with save_script. |
run_saved_script |
Run a saved script by name against a target. Requires allowCustomScripts. |
export_script |
Export a script as a standalone classic .js that runs under the plain frida -U -f <pkg> -l file.js CLI (preamble + source; bridges provided by the frida-tools CLI, not bundled). |
Tier 2: advanced primitives
| Tool | Description |
|---|---|
list_devices |
Local, USB and remote Frida devices (frida-ls-devices). |
select_device |
Select the active device by ID, type or remote host. |
get_device_info |
OS version, architecture and system parameters. |
list_processes |
Running processes (frida-ps). |
list_applications |
Installed and running applications. |
get_frontmost_application |
Foreground application. |
spawn_process |
Spawn suspended for early instrumentation; resume with resume_process. |
attach_process |
Attach to a running process by PID or name. |
resume_process |
Resume a suspended process. |
kill_process |
Kill a process. |
detach_session |
Detach a session and unload its scripts. |
list_sessions |
Sessions managed by this server. |
spawn_gating |
Enable / disable / list device-wide spawn gating — hold newly spawned (incl. child/isolated) processes suspended for early instrumentation; release with resume_process. |
child_gating |
Enable / disable child gating on a session so forked/exec'd child processes are held for instrumentation. |
eternalize_script |
Pin a loaded script in the target so it survives detach (fire-and-forget: no more messages/unload) — leave a bypass/monitor running while you free the session. |
enumerate_modules |
Loaded modules with name, base, end, size, path; regex filter. |
enumerate_exports |
Exports of a module, paginated. |
enumerate_imports |
Imports of a module with the providing module, paginated. |
enumerate_symbols |
Symbols including non-exported/debug symbols; regex filter and paging inside the agent (Linux, Android, iOS, macOS). |
resolve_address |
Translate 0x7f... to module+0xoffset (+ nearest symbol) and module+0xoff / module!sym to an absolute address. |
analyze_native_function |
Function range, basic blocks and edges, first instructions; addresses as absolute and module+0xoffset. |
dump_module_memory |
Dump a module base-relative to a host file (under cwd, the temp dir or ~/.config/frida-mobile-mcp/dumps) for raw import into Ghidra/IDA. |
list_threads |
Threads with id, name, state, current pc as module+0xoffset; optional 8-frame backtraces. |
hook_function |
Low-level Interceptor hook on a session_id with optional custom on_enter/on_leave bodies (custom bodies need allowCustomScripts). |
unhook_function |
Remove a hook by ID. |
frida_server_status |
Android (adb): report frida-server PIDs, device CPU ABI, matching frida release arch, and the GitHub .xz asset URL for the installed frida-node version. |
frida_server_install |
Android (adb): push a local (decompressed) frida-server binary to the device and chmod 755 it. |
frida_server_start |
Android (adb): start frida-server daemonized (optionally via su) with a custom listen address/port and binary name — a non-default port/name evades :27042/frida-server scans. Enforces allowedDevices. |
frida_server_stop |
Android (adb): signal the matching frida-server process to stop (pkill, optionally via su). |
adb_shell |
Android (adb): run an arbitrary device shell command. Disabled by default — requires allowAdbShell (config) or FRIDA_MCP_ALLOW_ADB_SHELL=1. |
adb_logcat |
Android (adb): dump the last N logcat lines (one-shot), optional tag:priority filters, or clear the buffer. |
adb_pull / adb_push |
Android (adb): move files between host and device. |
adb_forward |
Android (adb): add / remove / list port forwards (reach a frida-server on a non-default device port). |
inject_library |
Inject a native library (.so/.dylib) from the host into a process via Frida's injector, independent of the JS engine — the parity path for a prebuilt gadget/agent or custom .so. Disabled by default — needs allowNativeInjection (config) or FRIDA_MCP_ALLOW_NATIVE_INJECTION=1 (a capability separate from allowCustomScripts) and an architecture-matched library. |
mobile_action gateway
mobile_action({ action, params }) forwards to a lazily spawned mobile-mcp process (npx -y @mobilenext/mobile-mcp@latest by default, configurable via mobileMcp, disabled with --no-mobile-mcp). Call it without action to list the available actions. All Frida tools work without it; when it cannot start the error is MOBILE_MCP_UNAVAILABLE.
The server also exposes frida:// resources (version, devices, processes, apps, sessions, messages, script catalog, persisted evidence via frida://evidence and frida://evidence/{id}) and five workflow prompts (explore_app, security_audit, trace_functionality, write_frida_script, hunt_secrets).
Prebuilt scripts
| Script | Purpose |
|---|---|
ssl_pinning_bypass |
Bypass certificate pinning (TrustManager, OkHttp, Conscrypt, WebView; SecTrust, ATS, BoringSSL, AFNetworking) |
root_jailbreak_bypass |
Bypass root/jailbreak detection (Java, SystemProperties, native fopen/access/stat, canOpenURL, sysctl) |
class_enumeration |
List loaded Java/ObjC classes with a regex filter, optionally with methods |
method_hook |
Generic method hook (Java/ObjC methods or a native target) with argument and return value logging |
crypto_monitor |
javax.crypto, CommonCrypto and OpenSSL calls |
network_inspector |
Sockets, DNS, UDP and TLS SSL_read/SSL_write (plaintext bytes with log_data) |
keychain_prefs |
iOS Keychain and Android SharedPreferences access |
filesystem_monitor |
File I/O and SQLite |
anti_frida_evasion |
Observe (mode=report, default) or neutralize (mode=spoof, needs memoryWriteEnabled) the native primitives RASP uses to detect Frida: /proc/self/{maps,status,task} reads, strstr "frida" greps, thread-name / dlopen probes, and iOS dyld image scans |
Address notation and evidence envelope
Every tool that takes or returns a native address uses one vocabulary:
| Form | Meaning | Example |
|---|---|---|
module!symbol |
export or ELF/Mach-O symbol | libssl.so!SSL_write |
module+0xOFFSET |
offset from the module base (Ghidra/IDA RVA); decimal libfoo.so+4660 also accepted |
libfoo.so+0x1a2b0 |
0xADDRESS |
absolute runtime address | 0x7f3a1c2b1234 |
symbol / !symbol |
global export searched across all modules | !open |
Results prefer module+0xoffset so a static tool can decompile at image base + offset; absolute addresses appear only outside known modules and come with a limitations entry.
Every successful call returns result, evidence_id (UUID, also written to the audit log), limitations[], coverage (complete | unknown), session_context and suggested_next. Errors carry code, category, retryable, remediation and recovery_actions. Every result, errors included, is also persisted to the evidence store and retrievable by its evidence_id via get_evidence, export_evidence_bundle and the frida://evidence/{id} resource (frida://evidence lists the latest 100). Field semantics and the error-code table are in docs/interop.md; the agent workflow around them is in skills/mobile-dynamic-analysis/SKILL.md.
Working with REA, ReVa and IDA
frida-mobile-mcp is built to run next to ReVa (Ghidra), ida-pro-mcp (IDA Pro) and REA: the static side answers what the code says, this server answers what it does at runtime. A static tool finds libfoo.so+0x1234; hook_method or analyze_native_function take that string as-is; backtraces and resolve_address give offsets back in the same form for decompilation. enumerate_modules returns base/end for rebasing a Ghidra/IDA project, dump_module_memory writes a base-relative image of an unpacked library for raw import, and capture_tls shows the bytes a statically found wrapper actually puts on the wire. A three-server client configuration and a full static -> dynamic -> static walkthrough are in docs/interop.md.
REA covers static Android analysis (inspect_android_package, inspect_android_method), ADB housekeeping and a generic Frida lane for desktop binaries; this server covers the mobile runtime (Java/ObjC bridges, prebuilt scripts, TLS keys, memory, UI driving). Register both in the same client, start with get_app_info so both servers analyse the same APK hash, and keep the combined catalog small with FRIDA_MCP_TOOL_PROFILE=core and FRIDA_MCP_TOOLS_EXCLUDE=adb_*,frida_server_*. Both servers return an evidence envelope with citable evidence_ids and an export_evidence_bundle tool, so one finding ledger can cite both. Routing rules, install lines, the field and error-code mapping and an APK -> static -> hook -> report walkthrough are in docs/rea.md.
HTTP transport
frida-mobile-mcp --transport http --port 3000 # loopback (127.0.0.1), token optional
FRIDA_MCP_HTTP_TOKEN=<token> frida-mobile-mcp --transport http --host 0.0.0.0 --port 3000
Streamable HTTP endpoint at /mcp with one MCP session per client (Mcp-Session-Id); DELETE /mcp with that header ends the session. The server binds to loopback by default; a Bearer token (--http-token or FRIDA_MCP_HTTP_TOKEN) is mandatory when --host is not a loopback address and the server refuses to start without one. Host and Origin headers are validated against the bound host (DNS-rebinding protection). There is no TLS; use a reverse proxy or SSH tunnel across networks. --port 0 picks a free port; the bound URL is printed as a JSON line on stderr. Full curl examples: docs/clients.md.
Library usage
import { McpServer } from '@modelcontextprotocol/server';
import { createServer, registerFridaTools, createSessionServer } from 'frida-mobile-mcp';
const server = createServer({ allowCustomScripts: false }); // ready-made McpServer with every tool
// or add the tools to your own server:
const mine = new McpServer({ name: 'my-agent', version: '1.0.0' });
const deviceManager = registerFridaTools(mine, { resources: true, prompts: false });
// or one server per HTTP session:
const perSession = createSessionServer();
Also exported: scriptRegistry, DeviceManager, composeAgentSource/createAgentScript, findRemovedApis, loadBridgeSource, startHttpServer, createStdioTransport, loadConfig, ensureState and the types (dist/lib.d.ts).
Frida MCP questions
How do I add Frida MCP to Claude Code?
Run claude mcp add --env 'FRIDA_MCP_HTTP_TOKEN=<YOUR_FRIDA_MCP_HTTP_TOKEN>' --env 'FRIDA_MCP_REMOTE_TOKEN=<YOUR_FRIDA_MCP_REMOTE_TOKEN>' frida-mobile-mcp -- npx -y frida-mobile-mcp in your terminal. Add --scope user to make it available in every project.
How do I add Frida MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does Frida MCP provide?
It exposes 71 tools, including get_status, frida_help, explore_app, hook_method, trace_method.
What does frida-mobile-mcp do?
It is an MCP server that gives AI agents dynamic instrumentation of Android and iOS apps through Frida 17, exposing 71 tools for hooking, tracing, memory scanning and TLS capture.
How do I add it to Claude Code?
Run the claude mcp add command with npx to register the server.
What are the runtime requirements?
You need Node.js 22.12 or newer and a device or emulator running frida-server 17.x with the same major version.
Can it bypass SSL pinning?
Yes, it provides a one-click pinning bypass covering Android TrustManager, OkHttp and Conscrypt, and iOS SecTrust, ATS and BoringSSL.
Does it work on non-jailbroken iOS devices?
Yes, if the app is repackaged with the Frida Gadget, which the server then attaches to like any other process.