Skip to main content
Glama
Sign In
frida-ios-mcp

frida-ios-mcp

by YPYT1
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript

session_open

Spawns an iOS app via Frida, injecting agent and resuming execution. Optionally enables network capture (NSURLSession/TTNet) and attaches SpringBoard in parallel.

Instructions

Open long-lived Frida session (spawn-only on this stack). ALWAYS uses mode=spawn: kill → spawn suspended → inject agent → resume. mode=attach is ignored/forced to spawn unless FRIDA_MCP_ALLOW_ATTACH=1 (unreliable: touch/net). TikTok: after open, wait 3–5s before screen_snapshot. Never dump_tree/find_view. spawn restarts the process (login UI state may reset). captureNet=true installs NSURLSession + TTNet hooks before resume (launch traffic). withSpringBoard=true attaches SpringBoard in parallel (dual inject; App+SB concurrent RPCs).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "bundleId": "<bundleId>"
    },
    "name": "session_open"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNoIgnored: always spawn unless FRIDA_MCP_ALLOW_ATTACH=1
udidNo
bundleIdYesApp bundle id, e.g. com.ss.iphone.ugc.Ame
captureNetNoIf true, enable NSURLSession+TTNet capture before resume (spawn)
netOptionsNo
withSpringBoardNoAttach SpringBoard in parallel with app open (dual session)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.8/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description fully discloses behaviors: spawn lifecycle (kill→spawn suspended→inject→resume), mode override, net capture hooks, SpringBoard dual injection, process restart, and login UI reset. Also notes unreliability of attach mode.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with core purpose and every sentence adds value. Minor redundancy in repeating spawn mechanism, but overall efficient and well-structured for a complex tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers key aspects: spawn behavior, network capture, SpringBoard injection, timing for TikTok, and sibling differentiation. Lacks explanation of return value (e.g., session handle), but practical completeness is high given no output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Adds significant meaning beyond schema: explains mode is ignored unless env var, captureNet installs specific hooks, withSpringBoard attaches in parallel, and netOptions details. Schema coverage is 67%, but description compensates fully for gaps.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Open long-lived Frida session (spawn-only on this stack)', specifying the action and resource. It distinguishes from sibling tools like session_respawn and session_close by detailing the spawn mechanism and constraints.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit guidance: always uses spawn mode, attach only with env var, TikTok-specific instructions (wait, avoid dump_tree/find_view), and explains spawn restarts process resetting login UI. Offers clear when-to-use and when-not-to-use.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools