Skills/npm/mcp-server

mcp-server@1.4.1

VERIFIED

Publisher claims: "MCP server for AgentDrive: sync coding-agent sessions and resume them in any other agent, in any direction." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher adrive · publishing for 187 daysInstalls 3,265Last detonated 11 min ago
$claude mcp add mcp-server -- npx -y @adrive/mcp-server
WatchReport an issue

Coverage

Server started and answered tools/list.
Tested
MCP initialize and tools/list · every tool description, for hidden instructions · every file read, file written and host contacted by what ran
Not tested
what the tools do when called with real credentials

Before you give it your token

It will ask for
AGENTDRIVE_API_KEYConfiguration, not credentials: AGENTDRIVE_AGENT_PLATFORM, AGENTDRIVE_AGENT_ROLE, AGENTDRIVE_API_URL, CODEX_HOME
Where it talks to
agentdrive.sh (its own)
What we saw when it ran
no credential files read · no network
What we could not test
what the tools do when called with real credentials

Connect it with a scoped credential, under the guard. It asks for AGENTDRIVE_API_KEY and talks to agentdrive.sh. 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.

$vet-skills run --secrets AGENTDRIVE_API_KEY=agentdrive.sh -- npx -y @adrive/mcp-server

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

What changed since 1.4.0

vet-skills diff mcp-server 1.4.0 1.4.1

In the sandbox, this version reached for nothing 1.4.0 did not. Compared from the two recorded runs, not from source.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-21 and scored it 87/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 31 s · 2 scenarios
t+CategoryObserved action
0.0sprocessno install scripts in bundle
10sprocessdependency install exit 0
30sfilesystemread ~/.config/agentdrive/config.json outside project
30sclaimed3 tools: drive_connect, drive_sessions, drive_resume
30stools3d14088dd6c0132c
30stools1a771b2f32cdb790
30stools4d860e2775b5c6e2
30sprocessscript backend runs setup only
30sprocessno install scripts to re-run

Static findings

MEDIUM
MCP server using network transport (SSE/HTTP)dist/registry.js:71 · MCP server using network transport (SSE/HTTP) — data sent over network// (packages/mcp-server/src/index.ts) and the hosted Streamable-HTTP endpointFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04

No other findings across 3,575 lines in 81 files.

Cost to the agent

Instructions loaded
≈64 tok
1 file · 81 in bundle
Tool list per prompt
≈444 tok
3 tools · 148 per tool
Handshake
467 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 199

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

Not checked against OSV yet; the weekly check has not reached this version.