agent-device

Official

Overview Schema Related Servers Score Discussions

replay

Run recorded automation scripts on iOS, Android, desktop, or TV devices to repeat test flows and debug app behavior. Sessions stay active for follow-up commands, with configurable timeouts.

Instructions

Run a recorded automation script, including compatible Maestro YAML flows. A script without a terminal close leaves its session active for subsequent automation. Times out after 90s; a caller-supplied budget extends it.

Input Schema

TableJSON Schema

Name	Required	Description
`env`	No
`path`	Yes
`udid`	No	iOS device UDID selector.
`debug`	No	Enable debug diagnostics.
`force`	No
`runId`	No	Lease run identifier.
`device`	No	Device name selector.
`serial`	No	Android device or Vega VVD serial selector.
`target`	No	Alias for deviceTarget on commands without a UI target field. Interaction commands reserve target for the UI element.
`tenant`	No	Remote tenant identifier.
`update`	No
`backend`	No
`leaseId`	No	Existing lease identifier.
`maestro`	No
`session`	No	Agent-device session name.
`platform`	No	Platform selector used to resolve a device.
`bundleUrl`	No	Bundle URL hint inherited by replay-opened sessions.
`metroHost`	No	Metro/debug host hint inherited by replay-opened sessions.
`metroPort`	No	Metro/debug port hint inherited by replay-opened sessions.
`timeoutMs`	No	Maximum wall-clock duration for the replay request.
`resumeFrom`	No
`saveScript`	No
`includeCost`	No	Include per-command agent-cost (cost.wallClockMs, …) in structuredContent. Defaults to off; the default response shape is unchanged.
`keepSession`	No	Leave the session active by suppressing exactly an authored terminal close in native .ad.
`deviceTarget`	No	Device target form. Maps to the CLI --target flag.
`responseLevel`	No	Response verbosity: token-cheap digest / default (today) / full. Defaults to default; the default response shape is unchanged.
`mcpOutputFormat`	No	MCP text content format. Defaults to optimized agent-friendly text; use json for JSON text. Structured content is always returned separately.
`resumePlanDigest`	No
`androidDeviceAllowlist`	No	Android serial allowlist used for device resolution.

Output Schema

TableJSON Schema

Name	Required	Description
`healed`	Yes
`message`	Yes
`session`	Yes
`replayed`	Yes
`artifactPaths`	Yes
`sessionActive`	Yes	True iff the session is still active — the script had no terminal close.
`snapshotDiagnostics`	No

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

Changed8 schema fields changedv0.20.10Aug 26, 2026

removedInput schema / properties / cwd

Removed value: -{
-  "description": "Working directory for command execution.",
-  "type": "string"
-}

removedInput schema / properties / daemonAuthToken

Removed value: -{
-  "description": "Remote daemon auth token.",
-  "type": "string"
-}

removedInput schema / properties / daemonBaseUrl

Removed value: -{
-  "description": "Remote daemon base URL.",
-  "type": "string"
-}

removedInput schema / properties / iosSimulatorDeviceSet

Removed value: -{
-  "description": "iOS simulator device-set path used for device resolution.",
-  "type": "string"
-}

removedInput schema / properties / iosXctestDerivedDataPath

Removed value: -{
-  "description": "Derived data path for external iOS XCTest runner execution.",
-  "type": "string"
-}

removedInput schema / properties / iosXctestEnvDir

Removed value: -{
-  "description": "Writable directory for iOS XCTest runner env overlays.",
-  "type": "string"
-}

removedInput schema / properties / iosXctestrunFile

Removed value: -{
-  "description": "Externally built iOS XCTest runner .xctestrun artifact path.",
-  "type": "string"
-}

removedInput schema / properties / stateDir

Removed value: -{
-  "description": "Agent-device state directory.",
-  "type": "string"
-}

Changed1 schema field changedv0.20.9Aug 19, 2026

changedInput schema / properties / platform / enum

Previous value: -[
-  "apple",
-  "android",
-  "vega",
-  "linux",
-  "web",
-  "ios",
-  "macos"
-]New value: +[
+  "apple",
+  "android",
+  "harmonyos",
+  "vega",
+  "linux",
+  "web",
+  "ios",
+  "macos"
+]

Changed1 schema field changedv0.20.6Aug 7, 2026

addedInput schema / properties / timeoutMs

Added value: +{
+  "description": "Maximum wall-clock duration for the replay request.",
+  "type": "integer"
+}

Changed1 schema field changedv0.20.4Aug 3, 2026

addedInput schema / properties / keepSession

Added value: +{
+  "description": "Leave the session active by suppressing exactly an authored terminal close in native .ad.",
+  "type": "boolean"
+}

Changed10 schema fields changedv0.20.2Jul 30, 2026

addedInput schema / properties / bundleUrl

Added value: +{
+  "description": "Bundle URL hint inherited by replay-opened sessions.",
+  "type": "string"
+}

addedInput schema / properties / force
```
Added value: +{
+  "type": "boolean"
+}
```

addedInput schema / properties / metroHost

Added value: +{
+  "description": "Metro/debug host hint inherited by replay-opened sessions.",
+  "type": "string"
+}

addedInput schema / properties / metroPort

Added value: +{
+  "description": "Metro/debug port hint inherited by replay-opened sessions.",
+  "type": "integer"
+}

changedInput schema / properties / platform / enum

Previous value: -[
-  "apple",
-  "android",
-  "linux",
-  "web",
-  "ios",
-  "macos"
-]New value: +[
+  "apple",
+  "android",
+  "vega",
+  "linux",
+  "web",
+  "ios",
+  "macos"
+]

addedInput schema / properties / resumeFrom
```
Added value: +{
+  "type": "integer"
+}
```
addedInput schema / properties / resumePlanDigest
```
Added value: +{
+  "type": "string"
+}
```

addedInput schema / properties / saveScript

Added value: +{
+  "oneOf": [
+    {
+      "type": "boolean"
+    },
+    {
+      "type": "string"
+    }
+  ]
+}

changedInput schema / properties / serial / description

Previous value: -"Android serial selector."New value: +"Android device or Vega VVD serial selector."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "artifactPaths": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "healed": {
+      "type": "number"
+    },
+    "message": {
+      "type": "string"
+    },
+    "replayed": {
+      "type": "number"
+    },
+    "session": {
+      "type": "string"
+    },
+    "sessionActive": {
+      "description": "True iff the session is still active — the script had no terminal close.",
+      "type": "boolean"
+    },
+    "snapshotDiagnostics": {
+      "additionalProperties": true,
+      "type": "object"
+    }
+  },
+  "required": [
+    "replayed",
+    "healed",
+    "session",
+    "sessionActive",
+    "artifactPaths",
+    "message"
+  ],
+  "type": "object"
+}

Changed3 schema fields changedv0.17.11Jul 6, 2026

addedInput schema / properties / includeCost

Added value: +{
+  "description": "Include per-command agent-cost (cost.wallClockMs, …) in structuredContent. Defaults to off; the default response shape is unchanged.",
+  "type": "boolean"
+}

changedInput schema / properties / platform / enum

Previous value: -[
-  "ios",
-  "macos",
-  "android",
-  "linux",
-  "web",
-  "apple"
-]New value: +[
+  "apple",
+  "android",
+  "linux",
+  "web",
+  "ios",
+  "macos"
+]

addedInput schema / properties / responseLevel

Added value: +{
+  "description": "Response verbosity: token-cheap digest / default (today) / full. Defaults to default; the default response shape is unchanged.",
+  "enum": [
+    "digest",
+    "default",
+    "full"
+  ],
+  "type": "string"
+}

Changed1 schema field changedv0.17.7Jun 23, 2026

changedInput schema / properties / platform / enum

Previous value: -[
-  "ios",
-  "macos",
-  "android",
-  "linux",
-  "apple"
-]New value: +[
+  "ios",
+  "macos",
+  "android",
+  "linux",
+  "web",
+  "apple"
+]

Changed5 schema fields changedv0.17.6Jun 18, 2026

addedInput schema / properties / iosXctestDerivedDataPath

Added value: +{
+  "description": "Derived data path for external iOS XCTest runner execution.",
+  "type": "string"
+}

addedInput schema / properties / iosXctestEnvDir

Added value: +{
+  "description": "Writable directory for iOS XCTest runner env overlays.",
+  "type": "string"
+}

addedInput schema / properties / iosXctestrunFile

Added value: +{
+  "description": "Externally built iOS XCTest runner .xctestrun artifact path.",
+  "type": "string"
+}

addedInput schema / properties / mcpOutputFormat

Added value: +{
+  "description": "MCP text content format. Defaults to optimized agent-friendly text; use json for JSON text. Structured content is always returned separately.",
+  "enum": [
+    "optimized",
+    "json"
+  ],
+  "type": "string"
+}

changedInput schema / properties / platform / enum

Previous value: -[
-  "ios",
-  "android",
-  "macos",
-  "linux",
-  "apple"
-]New value: +[
+  "ios",
+  "macos",
+  "android",
+  "linux",
+  "apple"
+]

First observedv0.16.9Jun 3, 2026

TDQS

B3.1/5.0

Behavior3/5

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

With no annotations provided, the description carries the behavioral burden. It discloses two non-obvious behaviors: a script without a terminal close leaves the session active, and the request times out after 90 seconds unless a caller-supplied budget extends it. These are genuinely useful. Still, for a tool that executes scripts and can have side effects on devices, it does not mention reversibility, permissions, failure modes, or what execution actually changes.

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 short, front-loaded with the main verb and resource, and every sentence carries relevant behavioral information. It is not bloated. It is slightly under-sized for a 29-parameter automation tool, but that is more a completeness concern than a conciseness flaw.

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

Completeness2/5

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

Given 29 parameters, no annotations, and a complex automation/device domain, the description is incomplete. It says nothing about how to select a device or platform, how leases or sessions are established, what the required 'path' refers to, how environment variables are passed, or how the output schema relates to execution results. The timeout and session notes are helpful but far from sufficient for an agent to call this tool reliably across its many options.

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?

The schema covers 69% of parameters, so the description does not need to compensate fully, but it does add useful meaning for two parameters: the 'caller-supplied budget' clarifies timeoutMs's default behavior, and the terminal-close statement clarifies session and keepSession semantics. It does not, however, add anything for the undocumented params like path, env, force, update, backend, maestro, resumeFrom, or saveScript.

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?

The description states a specific action and resource: 'Run a recorded automation script', and further scopes it to 'compatible Maestro YAML flows'. This is clear and distinct from the sibling 'record', which creates scripts. However, it does not explicitly distinguish among other siblings like 'test' or 'batch', so it misses the top bar for sibling differentiation.

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

Usage Guidelines2/5

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

The description implies the tool is for running previously recorded or Maestro-authored automation, but it never explicitly says when to use replay versus record, test, batch, or other automation-related siblings. It provides no exclusions, prerequisites, or alternative routing guidance. The session and timeout notes are behavioral, not usage-selection guidance.

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

Install Server

Other Tools

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/callstack/agent-device'

If you have feedback or need assistance with the MCP directory API, please join our Discord server