Skills/npm/mcp-server

mcp-server@1.2.10

VERIFIED

Publisher claims: "MCP Server for Phantom Wallet" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher phantom · publishing for 283 daysInstalls 58,948Last detonated 47 min ago
$claude mcp add mcp-server -- npx -y @phantom/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
PHANTOM_AUTH_BASE_URLPHANTOM_CLIENT_SECRETConfiguration, not credentials: PHANTOM_API_BASE_URL, PHANTOM_APP_ID, PHANTOM_CALLBACK_PORT, PHANTOM_CLIENT_ID, PHANTOM_CONNECT_BASE_URL, PHANTOM_MCP_DEBUG, PHANTOM_WALLETS_API_BASE_URL, STAGING
Where it talks to
phantom.app (its own)
What the honeypot saw
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 PHANTOM_AUTH_BASE_URL, PHANTOM_CLIENT_SECRET and talks to phantom.app. 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 PHANTOM_AUTH_BASE_URL=phantom.app,PHANTOM_CLIENT_SECRET=phantom.app -- npx -y @phantom/mcp-server

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

What changed since 1.2.9

vet-skills diff mcp-server 1.2.9 1.2.10

This version reaches for something 1.2.9 did not: 2 rewritten tool descriptors (login, simulate). Compared from the two recorded runs, not from source.

Rewritten tool descriptors
login, simulate

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 2026-11-17 and scored it 95/100 (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 · 59 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
38sprocessdependency install exit 0
58sclaimed30 tools: buy, evm_allowance, evm_send, evm_sign, evm_sign-typed, login, logout, pay, perps_account, perps_cancel, perps_close, perps_deposit, perps_history, perps_leverage, perps_markets, perps_open, perps_orders, perps_positions, perps_transfer, perps_withdraw, perps_withdraw-hl-spot, price, simulate, solana_send, solana_sign
58stoolsa966f66bfdb22b69
58stoolsf8e29e52c10b5d50
58stools772b2b46deceb24c
58stools53d0f802a3d6e13c
58stoolsd4bf3e273b51aa31
58stools063d660e3976104e
58stools3108ba5fc1aa7de7
58stools97bcce92f655e44a
58stools87ac3ad0d6f2af48
58stoolsa5c8d52ebde4a0bb
58stools85b6236df55e3020
58stools13306fa325e24d04
58stools70655a95daaa3ef0
58stoolsaa9d830847357585
58stoolsec83e8987baaf2a9
58stools081853a2bf59390c
58stools31377d982f6c8f84
58stools2705ab54e788a28f
58stoolsdc0b7d89d45eb3d5
58stools56294c542049edc9
58stools938c2ccfa272ffef
58stoolsf80999977bdaf61a
58stoolsec0e0767e77453a1
58stoolsb26bd5fa17f994e3
58stools82ca1c885860e444
58stoolse88828f1e8932359
58stools95eb075bf460ddd1
58stools42acb9cc06eb8cf3
58stools200c647fbc295c7d
58stools3678503f535bcf3c
58sprocessscript backend runs setup only
58sprocessno install scripts to re-run

Static findings

No findings across 1,518 lines in 17 files.

Cost to the agent

Instructions loaded
≈45 tok
1 file · 17 in bundle
Tool list per prompt
≈14,006 tok
30 tools · 467 per tool
Handshake
1863 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 535

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.