Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

replicant-mcp

NPM · REPLICANT-MCP

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

Available components

0 this week 86 Trust /100

Last scanned (15 hours ago)

Scores higher than 89% of npm servers

Category Developer Tools

Trust breakdown (7 categories)

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. How we score → Why this is hard to score →

Supply Chain Security81
  • No malware found by supply-chain analysis.Pass
  • CVE check failed: a known high-severity CVE affects sharp 0.34.5, a direct dependency. A fixed version is available. View diagnostics → Fail
  • No install/post-install scripts declared.Pass
  • 46 of 154 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency100
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to thecombatwombat/replicant-mcp). View diagnostics → Pass
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 183 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability61
  • AI-judged instruction clarity (fair).Partial
  • Tool/resource definitions use about 1057 tokens (~75/item across 14 items; 14 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage81
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 42% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 15 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (16)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 28 Oct 26 +1
    • Stability: 0.97 → pass security
  • 27 Oct 26 −1
    • Stability: pass → 0.97 functional
  • 22 Oct 26 0
    • CVE-2026-114113 affects this package: high ▼ security
    • CVE-2026-114111 affects this package: high ▼ security
    • CVE-2026-114112 affects this package: high ▼ security
    • GHSA-wq5f-xc86-pv6w no longer affects this package ▲ security
    • GHSA-rgj7-g3m4-5g8c no longer affects this package ▲ security
    • GHSA-f88m-g3jw-g9cj no longer affects this package ▲ security
  • 21 Oct 26 +1
    • Stability: 0.97 → pass security
  • 20 Oct 26 −1
    • Stability: pass → 0.97 functional
  • 17 Oct 26 +3
    • Stability: 0.83 → pass security
  • 15 Oct 26 −3
    • Stability: pass → 0.80 functional
  • 14 Oct 26 +1
    • Stability: 0.97 → pass security
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 7 Nov 2026 · Analysed npm/replicant-mcp@1.6.7

Provenance Verified

A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.

Result Verified
Ecosystem npm
Reason Verified
Discovered via Registry attestation endpoint
Source repo thecombatwombat/replicant-mcp
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/thecombatwombat/replicant-mcp/.github/workflows/release.yml@refs/tags/v1.6.7
Rekor log index 1457184919
Predicate type SLSA build provenance https://slsa.dev/provenance/v1
Subject digest sha512:48d8311c628c122d7844319c3e4c500698cf947296489634b00ea4e16cf6adce3c0f30432f7aaddf06e79ddcdb2975f7e25e3aaa64a45828e0259cad3

Background: How many MCP packages publish verified provenance →

Vulnerabilities 3 findings
ID CVE Severity Vector Fix available
GHSA-f88m-g3jw-g9cj CVE-2026-114113 high yes
GHSA-rgj7-g3m4-5g8c CVE-2026-114112 high yes
GHSA-wq5f-xc86-pv6w CVE-2026-114111 high yes

Background: What a vulnerability scan can and cannot prove →

Dependencies 154 packages
Packages resolved 154
Stale 46
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 14 exposed · ~1,019 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
adb-app ~75

Manage applications.

NameTypeReqDescription
apkPathstring–APK path
filterstring–Filter by name (case-insensitive)
limitnumber–Default: 20, max: 100
offsetnumber–Pagination offset
operationstringyes–
packageNamestring––

No output schema declared.

No examples provided.

adb-device ~27

Manage device connections.

NameTypeReqDescription
deviceIdstring––
operationstringyes–

No output schema declared.

No examples provided.

adb-logcat ~81

Read device logs. Returns summary with logId.

NameTypeReqDescription
levelstring––
linesnumberyesDefault: 100
packagestring––
rawFilterstring––
sincestring–e.g., '01-20 15:30:00.000'
tagsarray––

No output schema declared.

No examples provided.

adb-shell ~82

Execute shell commands with safety guards.

NameTypeReqDescription
commandstringyes–
maxCharsnumber–Truncate output to N chars
previewCharsnumber–Preview length (default: 200)
summaryOnlyboolean–Compact preview only
timeoutnumber–ms, default: 30000, max: 120000

No output schema declared.

No examples provided.

cache ~44

Manage the cache. See rtfm for details.

NameTypeReqDescription
configobject––
keystring–Key to clear (optional)
operationstringyes–

No output schema declared.

No examples provided.

emulator-device ~67

Manage Android emulators.

NameTypeReqDescription
avdNamestring––
devicestring–e.g., 'pixel_7'
emulatorIdstring––
operationstringyes–
snapshotNamestring––
systemImagestring––

No output schema declared.

No examples provided.

gradle-build ~43

Build. Returns summary with buildId.

NameTypeReqDescription
flavorstring––
modulestring–e.g., ':app'
operationstringyes–

No output schema declared.

No examples provided.

gradle-get-details ~97

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

NameTypeReqDescription
detailTypestringyes–
idstringyes–
maxCharsnumber–Truncate to N chars
previewCharsnumber–For summaryOnly with detailType logs/all: preview length in characters (default: 400)
summaryOnlyboolean–Return compact summary payload for logs/tasks/all detail types (ignored for errors)

No output schema declared.

No examples provided.

gradle-list ~34

Introspect project structure.

NameTypeReqDescription
modulestring–e.g., ':app'
operationstringyes–

No output schema declared.

No examples provided.

gradle-test ~74

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

NameTypeReqDescription
filterstring–e.g., '*LoginTest*'
modulestring––
operationstringyes–
taskNamestring–Task name for baseline operations. Defaults to operation name.

No output schema declared.

No examples provided.

rtfm ~84

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

NameTypeReqDescription
categorystring–Category: build, adb, emulator, ui, cache, index
toolstring–Tool name (e.g., 'ui-query') for tool-specific docs

No output schema declared.

No examples provided.

ui-action ~119

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

NameTypeReqDescription
amountnumber–Scroll fraction (0-1, default: 0.5)
deviceSpaceboolean–x/y in device-space (default true). Set false only for image-space coords.
directionstring––
elementIndexnumber––
operationstringyes–
selectorobject––
textstring––
xnumber––
ynumber––

No output schema declared.

No examples provided.

ui-capture ~76

Capture screenshots or visual snapshots.

NameTypeReqDescription
inlineboolean––
localPathstring––
maxDimensionnumber–Max image dimension in pixels (default: 800). Higher = better quality, more tokens.
operationstringyes–
rawboolean–Skip scaling, full device resolution.

No output schema declared.

No examples provided.

ui-query ~116

Query app UI. Accessibility-first.

NameTypeReqDescription
compactboolean–Paginated flat list (default: true). false for full tree.
debugboolean––
gridCellnumber––
gridPositionnumber––
limitnumber–Default: 20
maxTiernumber–Max fallback tier (1-5). Use 3 to stop before visual/grid payloads.
offsetnumber––
operationstringyes–
selectorobject––

No output schema declared.

No examples provided.

Install

How do I install the replicant-mcp server?

replicant-mcp runs locally as an npm package, launched with npx -y replicant-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · replicant-mcp

# add to Claude Code
claude mcp add thecombatwombat-replicant-mcp -- npx -y replicant-mcp
Common questions

What is the replicant-mcp server?

replicant-mcp is listed in the public MCP registry as io.github.thecombatwombat/replicant-mcp. Android MCP server for AI-assisted development. Build, test, emulate, and automate. This page covers its npm package (replicant-mcp).

Is the replicant-mcp server safe to use?

replicant-mcp scores 86 out of 100 on VerifyMCP. We recorded 3 known advisories against it as of 7 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the replicant-mcp server expose?

replicant-mcp exposes 14 tools: cache, rtfm, adb-device, adb-app, adb-logcat, and 9 more. Their descriptions and schemas cost roughly 1,019 tokens of context every time the server is loaded.

Is the replicant-mcp server still maintained?

replicant-mcp is still listed as active in the MCP registry. We last reached this channel on 7 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the replicant-mcp server under?

replicant-mcp declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

What did VerifyMCP test on the replicant-mcp server?

VerifyMCP ran 16 checks on replicant-mcp, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.