MCP.Market

TAR Engine MCP server

by qingxuantang·io.github.qingxuantang/tar-engine·v0.3.3·2 stars
No reviews yet

Audit AI skill safety before you ship. Static, semantic, adversarial, supply chain scans.

B78/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B78/100

full report

Adoption
Growing

2 stars19 downloads/wk

Reviews

Write one

Nobody has reviewed TAR Engine yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

TAR Engine tools

No tool declarations could be read from the package source. They show once the server is installed.

Public scan report

scanner v0.1.9 · 2026-09-25 · same rubric, same numbers if you re-run it

no findings
  • Code scan5 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancelast push 64 days ago12/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 78/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How TAR Engine compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
78/100
higher than 57% of 48,255 servers
GitHub stars
2
more than 75% of 28,688 servers
Downloads a week
19
more than 6% of 12,191 servers with a package

Install TAR Engine in Claude Code, Cursor or VS Code

claude mcp add tar-engine -- uvx tar-engine
Add to Cursor

What the publisher says

From the TAR Engine repository's README, as published. We do not edit it. Read it on GitHub

TAR Engine — audit AI skill safety before you ship

Static + semantic + adversarial + supply-chain audit for AI agent skills. Run it in CI, or call it as an MCP tool from Claude Code / Cursor / Codex. BYOK for the LLM layers; free hosted tier + live Playground on tarai.dev.

Listed on the official Model Context Protocol Registry and published to PyPI — one-click install into any MCP-compatible agent.

tar-engine audits SKILL.md (OpenClaw, Claude Code), Codex skill.yaml, Claude Code custom commands (.claude/commands/.md), and OpenCode configs** — with no change to how you author skills. The core idea: a skill can pass every static red-flag check and still behave maliciously at runtime. TAR Engine catches that.

Three ways to run it — two of them install nothing on your machine:

  • Hosted — zero install. Paste or upload a skill on the tarai.dev Playground and read the audit in your browser. Nothing to install, nothing to trust locally.
  • In CI — zero install into your agent. The GitHub Action runs a pinned release inside your own CI sandbox: tar-engine scan ./skills --min-score 70 exits 1 if any skill scores below the bar. A pre-publish gate, not a nicer directory card.
  • In your agent — opt in. Install the MCP server and audit any SKILL.md while you write. It's a pinned, hash-verifiable PyPI release — no arbitrary git+https install. Details below.

What an audit looks like

Point it at a skill that looks fine. A "weekly note formatter" whose SKILL.md reads clean — but buried in it is a curl … | bash step, a "cloud sync" that tars up ~/.aws and ~/.ssh, and an instruction telling the agent to hide those network calls from you:

weekly-note-formatter        0 / 100   grade F   risk CRITICAL

  L01 static      SS-003  critical  remote script piped to shell (curl … | bash)
  L01 static      PI-002  critical  hidden instruction — "don't tell the user"
  L02 semantic    SEM-003 critical  only formats docs, yet packages up AWS creds + SSH keys
  L02 semantic    SEM-004 high      instructs the model to lie about its network calls
  L03 adversarial AR-002  high      3/3 role-jailbreak probes changed the skill's behavior

  → below --min-score 70, exit 1

Regex catches the curl | bash. The semantic and adversarial layers catch the parts regex can't: intent that exceeds the skill's stated purpose, and instructions that turn the agent against its user. Every finding cites the exact source line with a fix.

The four audit layers

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

TAR Engine: common questions

Is TAR Engine MCP server safe?
Mostly: it is graded B (78/100). Read the TAR Engine safety report
How do I install TAR Engine?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does TAR Engine need an API key?
Yes. The registry entry asks for TAR_ENGINE_BYOK_OPENAI_KEY, TAR_ENGINE_BYOK_ANTHROPIC_KEY.
Is TAR Engine maintained?
The last commit was 104 days ago (2026-07-23). The latest release is v0.3.3.
How does TAR Engine compare with other MCP servers?
safety score 78/100 (higher than 57% of 48,255 servers); github stars 2 (more than 75% of 28,688 servers); downloads a week 19 (more than 6% of 12,191 servers with a package). Full comparison.