mobile-mcp@r1
VERIFIED· install onlyPublisher claims: "Enables an AI client to control an Android phone over Wi-Fi adb from a container or Kubernetes Pod, supporting actions such as tapping, typing, installing apps, opening URLs, and taking screenshots via Streamable HTTP." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Bundled scripts ran with no arguments; no agent task scenario for this bundle.- Tested
- 7 of 7 bundled scripts run with no arguments, with decoy credentials in the environment · every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
LEASE_TOKENSMOBILEMCP_AUTHMOBILEMCP_AUTH_DISABLEDConfiguration, not credentials: ADB_KEY_DIR, ADB_MDNS, ELEMENTS_TRIM, FAKE_PHONE_STATE, KEEPALIVE_SECONDS, LEASE_HOST, LEASE_INNER_LISTEN, LEASE_PORT, LEASE_UPSTREAM, MCP_LISTEN, MOBILEMCP_DISABLE_TELEMETRY, PHONE_ADB_PORTS, PHONE_ADDR, PHONE_LEASE, PHONE_WAKE, WAKE_ADB- Where it talks to
- no vendor host named in the code
- What we saw when it ran
- no credential files read · no network
- What we could not test
- use of the skill by an agent
Connect it with a scoped credential, under the guard. It asks for LEASE_TOKENS, MOBILEMCP_AUTH, MOBILEMCP_AUTH_DISABLED and talks to its vendor. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind. What the tools do with a real credential was not observed.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is mobile-mcp@r1 safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-19 and scored it 81/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 15 s · 2 scenarios · 0 deviationsStatic findings
echo "$1" > "$WDIR/phone.json"; chmod 666 "$WDIR/phone.json"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.console.log("ok: element trimming (dedupe, zero-size, short id, centre, label==text, inputs / icons kept, batch, untouched otherwise)");Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.&& rm -rf /var/lib/apt/lists/*Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.find "$ROOTFS" -xdev \( -name 'adbkey*' -o -name '.git' -o -name '.env' -o -name '.netrc' -o -name '.git-credentials' \Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.WPORT=$((PORT + 3)); WDIR=$(mktemp -d); chmod 777 "$WDIR"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.