Skip to main content
Glama
appium

MCP Appium

Official
by appium
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

appium_mobile_permissions

Manage mobile app permissions: retrieve or update Android permissions, adjust iOS Simulator privacy services, and reset iOS privacy prompts for testing.

Instructions

Get/update Android app permissions or iOS Simulator privacy services; reset iOS privacy prompts. See action-specific parameters.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idNoApp ID; overrides name. Android defaults to the app under test; required for iOS get/update.
nameNoApp name resolved to an ID. Android defaults to the app under test; alternative to id for iOS get/update.
accessNoiOS update only: map of access rule → yes|no|unset|limited (Simulator + AppleSimulatorUtils). Required for iOS update.
actionYesget: list (Android) or read one privacy state (iOS Simulator). update: grant/revoke (Android) or set privacy map (iOS Simulator). reset: restore a privacy prompt for the app under test (iOS only).
targetNoAndroid update: pm (default) or appops.
serviceNoiOS get: privacy service name (e.g. camera, microphone, photos). iOS reset: service name or numeric XCUIProtectedResource id.
sessionIdNoSession ID; defaults to the active session.
permissionsNoAndroid update only: permission name(s), `all` (with pm target), or appops names. Required for Android update.
permissionFilterNoAndroid get only: which bucket to return. Defaults to requested per UiAutomator2.
permissionChangeActionNoAndroid update: for pm target grant (default) or revoke; for appops allow, deny, ignore, default.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.95.0
    • changedInput schema / properties / access / additionalProperties
      Previous value: -falseNew value: +{
+  "enum": [
+    "yes",
+    "no",
+    "unset",
+    "limited"
+  ],
+  "type": "string"
+}
    • changedInput schema / properties / sessionId / description
      Previous value: -"Session ID to target. If omitted, uses the active session."New value: +"Session ID; defaults to the active session."
  2. First observedv1.92.11

TDQS

A4.3/5.0
Behavior4/5

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

Annotations only say readOnlyHint=false and openWorldHint=false, so the description carries the burden of disclosing mutation behavior. It does disclose that 'update' grants/revokes and 'reset' restores a privacy prompt, and it notes platform-specific defaults (Android defaults to the app under test; iOS requires an ID). It does not mention side effects like whether reset clears all prompts or whether update is destructive, but the action-specific parameter hints cover the main behavioral traits.

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?

The description is a single sentence that front-loads the core purpose and then points to action-specific parameters. It is compact and avoids repeating schema details. It could be slightly more structured (e.g., bullet points per action), but it earns its place and is not bloated.

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?

Given the tool's complexity (10 parameters, nested objects, three actions, two platforms) and no output schema, the description is reasonably complete: it names the actions, platforms, and points to parameter details. It does not explain return values or error cases, but the schema covers parameter semantics and the description covers the action matrix. A short note on output shape would push it to 5.

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

Parameters4/5

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

Schema description coverage is 100%, so the baseline is 3. The description adds value by grouping parameters by action ('iOS update only', 'Android update only', 'Android get only') and by clarifying defaults (Android defaults to the app under test; pm target default). This goes beyond the schema's per-parameter descriptions and helps an agent pick the right parameters for a chosen action.

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 states a specific verb-resource pair ('Get/update Android app permissions or iOS Simulator privacy services; reset iOS privacy prompts') and clearly distinguishes the three actions. It also names the platform split (Android vs iOS Simulator), which differentiates it from sibling tools like appium_mobile_device_control or appium_driver_settings.

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?

The description gives clear context for when to use the tool (permissions/privacy services) and points to action-specific parameters, but it does not explicitly state when not to use it or name alternative tools. The sibling list contains related device-control tools, but no exclusion is stated.

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