# replicant-mcp (npm · replicant-mcp)

Android MCP server for AI-assisted development. Build, test, emulate, and automate.

- Trust score: 63/100 (medium)
- Change this week: +19
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `replicant-mcp`: 63/100 (this document), [markdown](https://verifymcp.io/servers/thecombatwombat-replicant-mcp/replicant-mcp.md), [page](https://verifymcp.io/servers/thecombatwombat-replicant-mcp/replicant-mcp)

## Channel facts

- Registry: `npm`
- Package: `replicant-mcp`
- Version: `1.6.7`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 70/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known high-severity CVE affects sharp 0.34.5, a direct dependency. A fixed version is available.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (156 of 160), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to thecombatwombat/replicant-mcp).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 87 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 49/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 1057 tokens (~75/item across 14 items; 14 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 81/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 42% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add thecombatwombat-replicant-mcp -- npx -y replicant-mcp
```

### Codex

```bash
codex mcp add thecombatwombat-replicant-mcp -- npx -y replicant-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "thecombatwombat-replicant-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "replicant-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add thecombatwombat-replicant-mcp --command npx --arg -y --arg replicant-mcp
```

### Hermes

```yaml
mcp_servers:
  thecombatwombat-replicant-mcp:
    command: "npx"
    args: ["-y", "replicant-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "thecombatwombat-replicant-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "replicant-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 63, +44)

- [security regression] GHSA-f88m-g3jw-g9cj affects this package: high
- [security regression] Known CVEs: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Provenance: unverified → pass
- [security improvement] Malware scan: unverified → pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [security] The attested source repository moved: thecombatwombat/replicant-mcp
- [functional regression] Security disclosure: fail → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] License: unverified → pass
- [functional improvement] Schema quality: unverified → fair
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional] Licence: MIT

### 2026-08-01 (score 19, +14)

- [functional improvement] Tool coverage: unverified → 100

### 2026-07-31 (score 5, −39)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-27 (score 44)

First indexed and scored.

## MCP tools (14)

### `cache` (~44 tokens)

Manage the cache. See rtfm for details.

Input parameters:

- `config` (object)
- `key` (string): Key to clear (optional)
- `operation` (string, required)

### `rtfm` (~84 tokens)

Get documentation. Pass category ('build'|'adb'|'emulator'|'ui'|'cache'|'index') or tool (tool name like 'ui-query').

Input parameters:

- `category` (string): Category: build, adb, emulator, ui, cache, index
- `tool` (string): Tool name (e.g., 'ui-query') for tool-specific docs

### `adb-device` (~27 tokens)

Manage device connections.

Input parameters:

- `deviceId` (string)
- `operation` (string, required)

### `adb-app` (~75 tokens)

Manage applications.

Input parameters:

- `apkPath` (string): APK path
- `filter` (string): Filter by name (case-insensitive)
- `limit` (number): Default: 20, max: 100
- `offset` (number): Pagination offset
- `operation` (string, required)
- `packageName` (string)

### `adb-logcat` (~81 tokens)

Read device logs. Returns summary with logId.

Input parameters:

- `level` (string)
- `lines` (number, required): Default: 100
- `package` (string)
- `rawFilter` (string)
- `since` (string): e.g., '01-20 15:30:00.000'
- `tags` (array)

### `adb-shell` (~82 tokens)

Execute shell commands with safety guards.

Input parameters:

- `command` (string, required)
- `maxChars` (number): Truncate output to N chars
- `previewChars` (number): Preview length (default: 200)
- `summaryOnly` (boolean): Compact preview only
- `timeout` (number): ms, default: 30000, max: 120000

### `emulator-device` (~67 tokens)

Manage Android emulators.

Input parameters:

- `avdName` (string)
- `device` (string): e.g., 'pixel_7'
- `emulatorId` (string)
- `operation` (string, required)
- `snapshotName` (string)
- `systemImage` (string)

### `gradle-build` (~43 tokens)

Build. Returns summary with buildId.

Input parameters:

- `flavor` (string)
- `module` (string): e.g., ':app'
- `operation` (string, required)

### `gradle-test` (~74 tokens)

Run tests. Returns summary with testId. With baseline, auto-detects regressions.

Input parameters:

- `filter` (string): e.g., '*LoginTest*'
- `module` (string)
- `operation` (string, required)
- `taskName` (string): Task name for baseline operations. Defaults to operation name.

### `gradle-list` (~34 tokens)

Introspect project structure.

Input parameters:

- `module` (string): e.g., ':app'
- `operation` (string, required)

### `gradle-get-details` (~97 tokens)

Fetch full output for a previous build/test by ID.

Input parameters:

- `detailType` (string, required)
- `id` (string, required)
- `maxChars` (number): Truncate to N chars
- `previewChars` (number): For summaryOnly with detailType logs/all: preview length in characters (default: 400)
- `summaryOnly` (boolean): Return compact summary payload for logs/tasks/all detail types (ignored for errors)

### `ui-query` (~116 tokens)

Query app UI. Accessibility-first.

Input parameters:

- `compact` (boolean): Paginated flat list (default: true). false for full tree.
- `debug` (boolean)
- `gridCell` (number)
- `gridPosition` (number)
- `limit` (number): Default: 20
- `maxTier` (number): Max fallback tier (1-5). Use 3 to stop before visual/grid payloads.
- `offset` (number)
- `operation` (string, required)
- `selector` (object)

### `ui-action` (~119 tokens)

Interact with app UI: tap, input, scroll. Use selector or coords.

Input parameters:

- `amount` (number): Scroll fraction (0-1, default: 0.5)
- `deviceSpace` (boolean): x/y in device-space (default true). Set false only for image-space coords.
- `direction` (string)
- `elementIndex` (number)
- `operation` (string, required)
- `selector` (object)
- `text` (string)
- `x` (number)
- `y` (number)

### `ui-capture` (~76 tokens)

Capture screenshots or visual snapshots.

Input parameters:

- `inline` (boolean)
- `localPath` (string)
- `maxDimension` (number): Max image dimension in pixels (default: 800). Higher = better quality, more tokens.
- `operation` (string, required)
- `raw` (boolean): Skip scaling, full device resolution.

## Diagnostics

Captured diagnostic sections: Provenance, Vulnerabilities, Dependencies. The full working is on the page: https://verifymcp.io/servers/thecombatwombat-replicant-mcp/replicant-mcp#diagnostics

## Score history

- 2026-08-03: 63
- 2026-08-02: 63
- 2026-08-01: 19
- 2026-07-31: 5
- 2026-07-30: 44
- 2026-07-28: 44
- 2026-07-27: 44

## Links

- npm package: https://www.npmjs.com/package/replicant-mcp
- Socket report: https://socket.dev/npm/package/replicant-mcp
- Repository: https://github.com/thecombatwombat/replicant-mcp
- Changelog RSS feed: https://verifymcp.io/servers/thecombatwombat-replicant-mcp/replicant-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/thecombatwombat-replicant-mcp/replicant-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/thecombatwombat-replicant-mcp/replicant-mcp