mcp@6.2.0

VERIFIED

Publisher claims: "Model Context Protocol server for vitest-agent. Exposes 30 tools for agent access to test data, TDD lifecycle, and session management." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher vitest-agent · publishing for 150 daysInstalls 8,601Last detonated 12 min ago
$claude mcp add mcp -- npx -y @vitest-agent/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
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 6.1.11

vet-skills diff mcp 6.1.11 6.2.0

In the sandbox, this version reached for nothing 6.1.11 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 2026-11-22 and scored it 87/100 (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 · 39 s · 2 scenarios
t+CategoryObserved action
0.0sprocessno install scripts in bundle
19sprocessdependency install exit 0
39sfilesystemread ~/.local/share/vitest-agent/github.com__spencerbeggs__vitest-agent outside project
39sfilesystemwrote ~/.local/share/vitest-agent/github.com__spencerbeggs__vitest-agent/data.db · ~/.local/share/vitest-agent/github.com__spencerbeggs__vitest-agent/data.db-journal · ~/.local/share/vitest-agent/github.com__spencerbeggs__vitest-agent/data.db-wal · ~/.local/share/vitest-agent/github.com__spencerbeggs__vitest-agent/data.db-shm
39sprocessexec /app/apps/web/node_modules/.bin/git
39sprocessexec /root/.cache/node/corepack/v1/pnpm/10.28.0/dist/node-gyp-bin/git
39sprocessexec /app/node_modules/.bin/git
39sprocessexec /pnpm/git
39sprocessexec /usr/local/sbin/git
39sprocessexec /usr/local/bin/git
39sprocessexec /usr/sbin/git
39sprocessexec /usr/bin/git
39sclaimed30 tools: ping, help, test_status, test_overview, test_coverage, test_history, test_trends, test_errors, file_coverage, settings_list, cache_health, configure, commit_changes, turn_search, failure_signature_get, acceptance_metrics, triage_brief, wrapup_prompt, inventory, test, register_agent, note, hypothesis, tdd_task, tdd_phase_transition_request
39stools66e77766832f8fc6
39stools68663fb282e7c7a3
39stools5953e7d58b47a282
39stoolsff7d666a12fa43a2
39stools82eb8e98f2f4d58d
39stoolsa6c8308f28eeb935
39stools4e538f50476f5975
39stoolsbe53f88b1f196e10
39stoolsf2f296baf26007d7
39stools662b3f6b36c5af86
39stools10082be55bbadfb1
39stools5022c5c9e1bb074f
39stoolsf654a8945580756c
39stools2a97106eabb31088
39stoolsfc051325f7bbe1b0
39stoolsf60a2817c64ebec8
39stoolsdbf4b2222d0dfc8c
39stoolsc04c52f732892b0a
39stools5cf356b02480d4d0
39stools568a4568522b4daf
39stoolsd8857a6d1b32d354
39stoolscbbe1a7c9bc32976
39stools78418cf0e6e34f9b
39stoolsebebba74c91234d7
39stoolsde511a3bdeed8aa5
39stoolsc0cdb33d7468aebe
39stools7356e95539b3f0f4
39stools0da3ad5f6ac6c178
39stoolsa1c68cffec05ee61
39stools0bd36b924b2be51f
39sprocessscript backend runs setup only
39sprocessno install scripts to re-run

Static findings

No findings across 14,874 lines in 57 files.

Cost to the agent

Instructions loaded
≈68 tok
1 file · 57 in bundle
Tool list per prompt
≈8,276 tok
30 tools · 276 per tool
Handshake
4710 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 371

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.