ModelsAtlas
Explore
Atlas / MCP servers / spencerbeggs / vitest-agent

vitest-agentSAFE

mcp/spencerbeggs/vitest-agent
MCP server by spencerbeggs · Audited 2026-10-12
⚑ Report / re-scanSource ↗

A Vitest reporter that keeps results of test runs focused for LLMs

Verdict
SAFE
Grade
B
Trust score
87 /100
Exposed tools
2 2r · 0w · 0d
Transport
—
License
MIT
Stars
2
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

Monorepo for the vitest-agent package family — a Vitest plugin, reporter, CLI, MCP server and Claude Code plugin that turn a test run into structured intelligence for LLM coding agents. It produces shape-tailored console output, persists every run to SQLite at an XDG-derived path and exposes test status, coverage, failure history and trends over a CLI and an MCP server.

User documentation lives at vitest-agent.dev. This README is the developer-facing hub for working in the repo itself.

Packages

The seven publishable packages live under packages/. @vitest-agent/sdk has no internal dependencies; the dependency flow is plugin → reporter → ui → sdk, with the sidecar reaching consumers through the CLI.

The sidecar's per-platform binaries ship as optionalDependencies from four sub-packages — @vitest-agent/sidecar-darwin-arm64, -linux-arm64

Read from source at commit bf810af73936OBSERVED · 2026-10-12
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.

claude-code
claude mcp add docs -- npx -y [email protected]
claude-desktop
{
  "mcpServers": {
    "docs": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ]
    }
  }
}
03

Exposed tools (2)

2 read · 0 write · 0 destructive.

ToolRiskDescription
intreadIntegration
vitest-agentreadVitest test data, coverage analysis, TDD orchestration and notes for LLM coding agents, served by the vitest-agent MCP server and recorded by lifecycle hooks.
04

Trust audit

SAFEgrade B · trust 87/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
declared (4 observation(s))
Network
declared (1 observation(s))
Shell
declared (1 observation(s))
Dependencies
not all pinned
Secrets in source
none-found

Findings (19)

LOWInventory / provenance · inv.hidden_file · CWE-1104
.changeset/.markdownlint.json
.markdownlint.json
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWInventory / provenance · inv.hidden_file · CWE-1104
.envrc
.envrc
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWInventory / provenance · inv.hidden_file · CWE-1104
.gitmodules
.gitmodules
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWInventory / provenance · inv.hidden_file · CWE-1104
lib/configs/.markdownlint-cli2.jsonc
.markdownlint-cli2.jsonc
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWInventory / provenance · inv.hidden_file · CWE-1104
website/docs/.markdownlint.json
.markdownlint.json
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
packages/sdk/__test__/match-vitest-command.test.ts:24
it("matches PM-mediated exec (pnpm exec, npm exec, yarn exec, bun x)", () => {
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
packages/cli/__test__/bin/version.e2e.test.ts:16
import packageJson from "../../package.json" with { type: "json" };
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
packages/cli/savvy.build.ts:5
localPaths: ["../../website/lib/models/cli"],
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
packages/engine/__test__/integration/utils/fixtures.ts:3
import { makeTestLayer } from "../../utils/layers.js";
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
packages/engine/__test__/utils/layers.ts:1
export { DataStoreTestLayer, makeTestLayer } from "../../src/testing/layers.js";
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
packages/engine/savvy.build.ts:5
localPaths: ["../../website/lib/models/engine"],
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
package.json
@okfit/plugin, @savvy-web/silk
Why it matters. 2 dependency range(s) float
Fix. pin exact versions or ship a lockfile
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
packages/cli/package.json
@savvy-web/bundler
Why it matters. 1 dependency range(s) float
Fix. pin exact versions or ship a lockfile
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
packages/engine/package.json
@savvy-web/bundler
Why it matters. 1 dependency range(s) float
Fix. pin exact versions or ship a lockfile
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
packages/mcp/package.json
@savvy-web/bundler
Why it matters. 1 dependency range(s) float
Fix. pin exact versions or ship a lockfile
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
packages/plugin/package.json
magic-string, @savvy-web/bundler, vite
Why it matters. 3 dependency range(s) float
Fix. pin exact versions or ship a lockfile
LOWPrompt injection · prompt.credential_read · CWE-94, CWE-1427
okf/conventions/front-end-entry-contract.md:116
read `process.env` / `process.cwd()` to thread input into the engine's
Why it matters. asks the agent to read credentials
LOWPrompt injection · prompt.credential_read · CWE-94, CWE-1427
website/docs/en/mcp/environment-variables.mdx:31
3. The reporter, MCP server, and sidecar read `process.env.VITEST_AGENT_*` at startup. The reporter records `actor_type='agent'` plus the canonical UUIDs on every `test_runs` row. The MCP server popul
Why it matters. asks the agent to read credentials
LOWPrompt injection · prompt.transfer_instruction · CWE-94, CWE-1427
okf/decisions/index.md:62
* [The MCP Server Survives Post-Connect Crashes](51-the-mcp-server-survives-post-connect-crashes.md) - unhandledRejection and uncaughtException guards keep the MCP process alive after a client connect
Why it matters. an instruction to move sensitive data to an outside destination
Fix. remove; a skill never needs the user's secrets off the machine

Gates applied: no_behavioural_pass.

Audited 2026-10-12 · audit v0.4.1 · source sha bf810af73936full audit observations/trust-audit/mcp-server/spencerbeggs__vitest-agent.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-12bf810af73936SAFEB87first audit
06

Questions

What is the @vitest-agent/mcp MCP server?

A Vitest reporter that keeps results of test runs focused for LLMs

What tools does @vitest-agent/mcp expose?

2 in total: 2 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is @vitest-agent/mcp safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (87/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does @vitest-agent/mcp need?

No credential environment variables were found in its source, so it appears to need none.

How current is this page?

The grade is for one exact copy of the source (bf810af73936), read on 2026-10-12. The repository is watched and re-audited when it changes.

Advertisement