mcp@11.3.2

VERIFIED

Publisher claims: "Warm local stdio MCP server" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher warmio · publishing for 307 daysInstalls 2,339Last detonated 15 min ago
$claude mcp add mcp -- npx -y @warmio/mcp
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
WARM_MCP_CREDENTIALSConfiguration, not credentials: CALLBACK_PATH, WARM_API_TIMEOUT_MS, WARM_CONFIG_DIR
Where it talks to
no vendor host named in the codeAlso warm.io — not the publisher's domain; check what for before connecting.
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, and read the third-party hosts first. The code names warm.io as well as its own vendor. The guard injects WARM_MCP_CREDENTIALS only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- npx -y @warmio/mcp

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

What changed since 11.3.1

vet-skills diff mcp 11.3.1 11.3.2

In the sandbox, this version reached for nothing 11.3.1 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 83/100 (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 · 27 s · 2 scenarios
t+CategoryObserved action
0.0sprocessno install scripts in bundle
6.9sprocessdependency install exit 0
27sfilesystemread ~/.config/warm/oauth_tokens.json outside project
27sclaimed7 tools: get_financial_context, get_transactions, request_handoff, get_handoff_status, search_operations, describe_operation, invoke_operation
27stools4f7f06e687542c6b
27stools1e7302f326040cb3
27stools3c26fdd034926b56
27stools6195e004aceda14c
27stools75661b7422dd9026
27stools1ff38b9b1e9ba72e
27stoolscac797545fa224ee
27sprocessscript backend runs setup only
27sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathsdist/load-env.js:14 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconst candidate = path.join(process.cwd(), '.env');Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsdist/install.js:96 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconst WARM_TOML_ENV_BLOCK = /\n?\[mcp_servers\.warm\.env\][\s\S]*?(?=\n\[[^\n]+\]|\s*$)/g;Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

Cost to the agent

Instructions loaded
≈41 tok
1 file · 33 in bundle
Tool list per prompt
≈1,657 tok
7 tools · 237 per tool
Handshake
885 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 313

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.

mcp@11.3.2 safety verdict: Verified — KillerSkills