Skills/npm/mcp-fetch

mcp-fetch@1.6.4

VERIFIED

Publisher claims: "A Model Context Protocol server that provides web content fetching capabilities with automatic image saving and optional AI display" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher kazuph · publishing for 711 daysInstalls 3,641Last detonated 1 h ago
$claude mcp add mcp-fetch -- npx -y @kazuph/mcp-fetch
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
no credential variables read in the code
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
what the tools do when called with real credentials

Reasonable to connect. No credential asked for, no third-party host named, Server started and answered tools/list.

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

What changed since 1.6.3

vet-skills diff mcp-fetch 1.6.3 1.6.4

In the sandbox, this version reached for nothing 1.6.3 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 88/100 (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 · 34 s · 2 scenarios
t+CategoryObserved action
0.0sprocessno install scripts in bundle
14sprocessdependency install exit 0
34sfilesystemread ~/Downloads/mcp-fetch outside project
34sclaimed1 tool: imageFetch
34stoolsabcc689a1a0f7d06
34sprocessscript backend runs setup only
34sprocessno install scripts to re-run

Static findings

No findings across 1,632 lines in 8 files.

Cost to the agent

Instructions loaded
≈69 tok
1 file · 8 in bundle
Tool list per prompt
≈878 tok
1 tool · 878 per tool
Handshake
1429 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 1052

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 @kazuph/mcp-fetch@1.6.4 as of 26 min ago. This is the package itself, not its dependencies.