Skip to main content
Glama
Sign In
mobile-debug-mcp

mobile-debug-mcp

by clivejefferies
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

attach_debugger

Attach a debugger to an owned Android JDI or iOS simulator LLDB session to pause app threads for inspection; requires device and app ID, plus process ID if ambiguous.

Instructions

Attach an owned Android JDI or iOS simulator LLDB session. Requires an explicit device and debuggable app; choose processId when ambiguous. Stops suspend all app threads. Auto-detach: 60s paused, 5m idle, 30m total.

Input Schema

NameRequiredDescriptionDefault
appIdYes
deviceIdYes
platformYes
processIdNo
timeoutMsNo
responseModeNodebug

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.35.0
    • changedInput schema / allOf
      Previous value: -[
-  {
-    "not": {
-      "required": [
-        "expectedState"
-      ]
-    }
-  }
-]New value: +[
+  {
+    "if": {
+      "properties": {
+        "platform": {
+          "const": "ios"
+        }
+      }
+    },
+    "then": {
+      "properties": {
+        "deviceId": {
+          "pattern": "^[A-Fa-f0-9]{8}(?:-[A-Fa-f0-9]{4}){3}-[A-Fa-f0-9]{12}$"
+        }
+      }
+    }
+  },
+  {
+    "not": {
+      "required": [
+        "expectedState"
+      ]
+    }
+  }
+]
    • changedInput schema / properties / appId / pattern
      Previous value: -"^[A-Za-z][\\w]*(?:\\.[A-Za-z][\\w]*)+$"New value: +"^[A-Za-z][\\w-]*(?:\\.[A-Za-z][\\w-]*)+$"
    • changedInput schema / properties / platform / enum
      Previous value: -[
-  "android"
-]New value: +[
+  "android",
+  "ios"
+]
    • addedInput schema / properties / responseMode
      Added value: +{
+  "default": "debug",
+  "enum": [
+    "compact",
+    "debug"
+  ],
+  "type": "string"
+}
  2. Addedv0.34.0

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does disclose the biggest side effect: attaching suspends all app threads, plus a three-tier auto-detach policy (60s paused, 5m idle, 30m total) that materially changes how the agent must sequence calls. It omits session exclusivity (can a second attach succeed?) and what the call returns.

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

Conciseness5/5

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

Three short sentences, front-loaded with the action, then preconditions, then the most consequential behavior (thread suspension) and lifecycle limits. No filler or restated field names.

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

Completeness3/5

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

For a six-parameter, unannotated, output-schema-less tool, the definition covers the critical attach semantics well but leaves the timeoutMs and responseMode knobs and the shape of the attach result unexplained. An agent can call it correctly in the common case but must guess at timeout/verbosity behavior.

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

Parameters3/5

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

Schema description coverage is 0%, so the description must compensate. It adds meaning for platform (Android JDI vs iOS simulator), deviceId, appId (must be debuggable), and processId (use when the target is ambiguous), but says nothing about timeoutMs or responseMode, leaving two of six parameters undocumented anywhere.

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

Purpose4/5

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

States a specific verb and resource: attach an owned Android JDI or iOS simulator LLDB session, including the two supported platform backends. It is clearly distinguishable from siblings like detach_debugger or get_debugger_state, though it never names those siblings explicitly.

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

Usage Guidelines4/5

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

Gives real preconditions ('Requires an explicit device and debuggable app') and a disambiguation rule ('choose processId when ambiguous'), which tells the agent how to pick the target. It stops short of stating when not to use it or which sibling to call instead (e.g., get_debugger_capabilities first).

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