Skills/npm/mcp-server

mcp-server@0.8.4

VERIFIED

Publisher claims: "MCP server for AllRatesToday — let AI coding tools (Claude Code, Cursor, Claude Desktop) fetch real-time and historical currency exchange rates." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher allratestoday · publishing for 213 daysInstalls 3,802Last detonated 16 h ago
$claude mcp add mcp-server -- npx -y @allratestoday/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
ALLRATES_API_KEYConfiguration, not credentials: ALLRATES_BASE_URL
Where it talks to
allratestoday.com (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 ALLRATES_API_KEY and talks to allratestoday.com. 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 ALLRATES_API_KEY=allratestoday.com -- npx -y @allratestoday/mcp-server

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

What changed since 0.8.1

vet-skills diff mcp-server 0.8.1 0.8.4

This version reaches for something 0.8.1 did not: 1 rewritten tool descriptor (get_bank_rates). Compared from the two recorded runs, not from source.

Rewritten tool descriptors
get_bank_rates

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 2026-11-19 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 · 25 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
5.2sprocessdependency install exit 0
25sclaimed9 tools: get_exchange_rate, get_historical_rates, get_rates_authenticated, list_currencies, list_central_banks, get_official_rates, get_reference_rate, get_bank_rates, request_trial_key
25stoolsb06c356dce123cf7
25stoolsff9ee344e80c0d98
25stoolsfaab6dcfbe5ecd4d
25stoolse6f2bc51a9f4fc18
25stools6ab5aca01c3daeb5
25stoolsc9b03572474eb89a
25stools22ece240188d6cdc
25stoolsf708620b1f8dc41d
25stools3ca1fad268088b20
25sprocessscript backend runs setup only
25sprocessno install scripts to re-run

Static findings

LOW
Account verification phishing language detectedREADME.md:47 · Account verification phishing language detected · informational: not an instruction file2. Verify your emailFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

No other findings across 1,568 lines in 12 files.

Cost to the agent

Instructions loaded
≈75 tok
1 file · 12 in bundle
Tool list per prompt
≈2,906 tok
9 tools · 323 per tool
Handshake
695 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 611

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

No advisories in OSV for @allratestoday/mcp-server@0.8.4 as of 16 h ago. This is the package itself, not its dependencies.