Skills/npm/mcp-sqlite

mcp-sqlite@0.16.2

VERIFIED

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

Registry npm (MCP server)Publisher mokei · publishing for 647 daysInstalls 1,534Last detonated 1 h ago
$claude mcp add mcp-sqlite -- npx -y @mokei/mcp-sqlite
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 the honeypot saw
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 0.16.0

vet-skills diff mcp-sqlite 0.16.0 0.16.2

In the sandbox, this version reached for nothing 0.16.0 did not. Compared from the two recorded runs, not from source.

0.16.0 was not run in the sandbox (install failed); the comparison covers what static analysis recorded only. Only one of the two runs produced a tool list; tools are not compared.

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 2026-11-15 and scored it 92/100 (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 · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
6.6sprocessdependency install exit 0
27sclaimed3 tools: sqlite_all, sqlite_get, sqlite_run
27stoolsca199ebc0bbecd6b
27stools9368f3c12f7414bb
27stools36bc515368f94559
27sprocessscript backend runs setup only
27sprocessno install scripts to re-run

Static findings

MEDIUM
File type combined with upload actionlib/index.js:51 · File type combined with upload action — agent may exfiltrate local data filesconst results = db.prepare(req.input.sql).all(req.input.parameters ?? {});Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionlib/index.js:83 · File type combined with upload action — agent may exfiltrate local data filesconst changes = db.prepare(req.input.sql).run(req.input.parameters ?? {});Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionlib/index.js:67 · File type combined with upload action — agent may exfiltrate local data filesconst result = db.prepare(req.input.sql).get(req.input.parameters ?? {});Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈41 tok
1 file · 8 in bundle
Tool list per prompt
≈357 tok
3 tools · 119 per tool
Handshake
957 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 89

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.