replicant-mcp

adb-shell

Destructive

Execute ADB shell commands on Android devices with safety guards including timeout, output truncation, and summary previews.

Instructions

Execute shell commands with safety guards.

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": {
      "command": "<command>"
    },
    "name": "adb-shell"
  }
}

Input Schema

Name	Required	Description
`command`	Yes
`timeout`	No	ms, default: 30000, max: 120000
`maxChars`	No	Truncate output to N chars
`summaryOnly`	No	Compact preview only
`previewChars`	No	Preview length (default: 200)

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv1.6.7May 13, 2026
- addedInput schema / properties / maxChars / minimum
```
Added value: +1
```
- addedInput schema / properties / previewChars / minimum
```
Added value: +1
```

Changed5 schema fields changedv1.0.1Apr 2, 2026

removedInput schema / properties / command / description
```
Removed value: -"Shell command to execute"
```

addedInput schema / properties / maxChars

Added value: +{
+  "description": "Truncate output to N chars",
+  "type": "number"
+}

addedInput schema / properties / previewChars

Added value: +{
+  "description": "Preview length (default: 200)",
+  "type": "number"
+}

addedInput schema / properties / summaryOnly

Added value: +{
+  "description": "Compact preview only",
+  "type": "boolean"
+}

changedInput schema / properties / timeout / description

Previous value: -"Timeout in ms (default: 30s, max: 120s)"New value: +"ms, default: 30000, max: 120000"

First observedv1.0.0Jan 21, 2026

TDQS

C2.9/5.0

Behavior3/5

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

Annotations already indicate destructiveHint=true and readOnlyHint=false. The description adds 'with safety guards', hinting at restrictions, but does not specify what those guards are (e.g., command whitelisting, output limits). Adds marginal context beyond annotations.

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 concise (single phrase) and front-loaded with the verb. However, it might be too terse for a tool that requires careful usage.

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 5 parameters, no output schema, and destructive behavior, the description is insufficient. It lacks examples, return format, and details on safety guards. More information is needed for appropriate agent usage.

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

Parameters2/5

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

Schema coverage is 80% with descriptions for most parameters except 'command'. The description does not add meaning for the undocumented 'command' parameter, which is required. It simply restates the tool's purpose without clarifying acceptable values or formats.

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 clearly states the action (execute) and resource (shell commands), and adds a hint about safety guards. It is distinct from sibling tools like adb-logcat or adb-app, though it could be more specific about the context (Android ADB).

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?

No guidance on when to use this tool vs alternatives. With siblings like adb-logcat and adb-app, there is no indication of selection criteria or when not to use the tool.

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

Deploy Server