MCP.Market

Vtai Agent MCP server

by velsrocky·io.github.velsrocky/vtai-agent·v0.7.0
No reviews yet

System-automation agent MCP server for opencode/claude/pi: guarded shell, dry-run-first, audited.

A92/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A92/100

full report

Adoption
Growing

0 stars455 downloads/wk

Reviews

Write one

Nobody has reviewed Vtai Agent yet.

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

Vtai Agent tools (9, 1 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • auto_mode

    Autonomous loop: dispatch the goal to a coding CLI (opencode by default), review the reply against the goal, and iterate with corrective prompts until the answer satisfies the goal or max_iterations is reached. Use this for the '@vt-ai_automode_on' keyword.

  • backup_sync

    Incremental directory backup via rsync. Reports the transfer plan and can verify with a checksum pass. Deletion of extraneous files is opt-in and never happens during a dry run.

  • delegate_coding

    Delegate a coding task to opencode, claude, or pi in headless mode. Snapshots the repo, captures the diff, and rolls back if an optional verify command fails. The working directory must be a git repo.

  • disk_audit

    Read-only scan for reclaimable disk space: largest/oldest files plus cache directory sizes. Deletes nothing.

  • inspect_application

    Analyze a local application with REA (reverse engineering) under full guardrails. The target is deny-glob checked, copied into a quarantine dir, analyzed there (REA capability must be enabled in config), and the returned evidence carries an audit digest. The original target is never touched.

  • organize_files

    Content-aware cleanup: sort a directory's files into Documents/Images/ Videos/Audio/Archives/Installers/Code/Data/Fonts/Models. Collisions are auto-renamed. Everything stays inside the target directory.

  • run_shellwrite action

    Run an allowlisted shell command. Protected paths and non-allowlisted binaries are rejected. Use dry_run=true to preview without executing.

  • system_info

    Snapshot this machine: CPU, memory, disks, load, and AMD GPU state. Read-only and safe to call before deciding how to act.

  • transcode_media

    Batch transcode videos with AMD GPU (VAAPI) acceleration. Output goes to a 'transcoded' subfolder; originals are never modified.

Public scan report

scanner v0.1.10 · 2026-10-25 · same rubric, same numbers if you re-run it

no findings
  • Code scan24 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 qualitylocal package, no credentials required12/15
  • Maintenancelast push 2 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Vtai Agent compares

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

Safety score
92/100
higher than 90% of 4,460 AI and agents servers
Tools
9
the typical AI and agents server has 6
Tools that change things
11%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
455
more than 85% of 1,538 AI and agents servers with a package

What its tools let an agent do: 8 read · 1 run or deploy

Install Vtai Agent in Claude Code, Cursor or VS Code

claude mcp add vtai-agent -- uvx vtai-agent
Add to Cursor

What the publisher says

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

<!-- mcp-name: io.github.velsrocky/vtai-agent -->

VT-AIAgent

System-automation agent for your machine, exposed as an MCP server for opencode / Claude Code / pi — and drivable directly via the vtai CLI.

Tools

Safety model

paths defeat ../symlink escapes; guardrails.deny_globs protect secrets.

  • Dry-run by default (guardrails.dryrundefault) — previews never touch disk.
  • Path containment: writes only inside paths.writable_roots, resolved

with an explicit read/write policy, resolve inside trustedbindirs, carry no exec-enabling flags, and every path argument passes the same checks.

  • Fail-closed shell sandbox: the binary must be a bare allowlisted name

into a CIRCUIT BREAKER instruction the looping model can't miss.

  • Kill switch: drop a KILL file in data_dir to abort executing tools.
  • Echo-loop breaker: N identical denials in a window escalate the refusal

token cost exceeds it; spend is recorded per run.

  • Budget cap: budgetusdper_run aborts an orchestrated run when accrued

invocation (orchestrated, MCP, or CLI) attributed to a run row.

  • Audit: every allow and deny is logged to SQLite in data_dir, each

Quick start

Prerequisites

1. Install

git clone https://github.com/velsrocky/vtai-agent.git
cd vtai-agent
uv sync --dev

uv sync needs uv >= 0.13.1 (the lockfile is revision = 5; the floor is declared as [tool.uv] required-version, so an older uv says so plainly instead of failing on a lockfile parse).

2. Configure

The agent reads one TOML file. Which one is resolved in this order:

  1. $VT_CONFIG — explicit override
  2. config/settings.toml next to the package (i.e. the clone you just made)
  3. ~/.vtaiagent/settings.toml — the per-user file

A machine with no config file anywhere fails loudly on first use — the built-in defaults leave nothing protected (shell_allowlist empty) so nothing runs, and vtai info says so plainly ("no config file there"). vtai init writes a starter config; vtai init --doctor runs the full preflight right after it.

Shortened. The full README is on GitHub.

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

Vtai Agent: common questions

Is Vtai Agent MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the Vtai Agent safety report
How do I install Vtai Agent?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Vtai Agent need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Vtai Agent maintained?
The last commit was 13 days ago (2026-10-22). The latest release is v0.7.0.
What can I use instead of Vtai Agent?
Servers from other publishers that do the same job: Basic Memory MCP server, HOL Guard MCP server and Agent-Native Chat MCP server.
How does Vtai Agent compare with other AI and agents MCP servers?
safety score 92/100 (higher than 90% of 4,460 AI and agents servers); tools 9 (the typical AI and agents server has 6); tools that change things 11% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Vtai Agent

Same job from other publishers: the closest match first, then the best rated.

  • Basic Memory
    Local-first knowledge management with bi-directional LLM sync via Markdown files.
    B
  • HOL Guard
    Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.
    A
  • Agent-Native Chat
    Minimal chat-first app with durable threads, actions, and the app-agent loop
    A
  • Agent Recall
    Correction-first agent memory. Precision KPI tracks if agents heed warnings. 5 layers, local-only.
    A
  • Roast My Design System
    Audit your Design System and serve your Agent the rules that keep AI-written UI on-system.
    A