Server providing Argo CD integration for MCP clients.
Nothing to run from here
Vtai Agent is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
94/100
trust score
9
tools declared
local
runs on your machine
—
downloads a day
What it does
System-automation agent MCP server for opencode/claude/pi: guarded shell, dry-run-first, audited.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user vtai-agent-mcp '--' uvx --from vtai-agent vtai
# 2 — ask your agent for something these tools do
# system_info, run_shell, organize_files and 6 more
Vtai Agent costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
VEAll 1 server
velsrocky1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Vtai Agent as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need uv (docs.astral.sh/uv): uvx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user vtai-agent-mcp '--' uvx --from vtai-agent vtaiReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
9 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Snapshot this machine: CPU, memory, disks, load, and AMD GPU state.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| include_gpu | boolean | no | Probe rocm-smi/vulkaninfo for GPU state (default true). |
Run an allowlisted shell command. Protected paths and non-allowlisted binaries are rejected. Use dry_run=true to preview without executing.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| command | string | yes | Shell command; argv[0] must be in the allowlist. |
| dry_run | boolean | no | Preview only (defaults to config dry_run_default). |
| timeout | number | no | Seconds before the command is killed (1-300). |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| directory | string | no | Directory to tidy (default ~/Downloads). |
| dry_run | boolean | no | Plan only, move nothing (defaults to config dry_run_default). |
| recursive | boolean | no | Descend into subdirectories. |
| confirm_mime | boolean | no | Use file mime type for unknown extensions. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| source | string | yes | Directory to back up. |
| destination | string | yes | Backup destination (must be in writable_roots). |
| dry_run | boolean | no | Preview only (defaults to config dry_run_default). |
| delete_extraneous | boolean | no | Delete destination files not in source (dangerous). |
| compress | boolean | no | Use rsync -z. |
| verify | boolean | no | Re-run with checksums after transfer. |
Batch transcode videos with AMD GPU (VAAPI) acceleration. Output goes to a 'transcoded' subfolder; originals are never modified.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| directory | string | yes | Directory containing videos. |
| dry_run | boolean | no | Report jobs without encoding. |
| codec | string | no | h264_vaapi | hevc_vaapi | av1_vaapi | libx264 (config default). |
| crf | integer | no | Quality for software codecs, 0-51 (lower = better). |
| recursive | boolean | no | Descend into subdirectories. |
| overwrite | boolean | no | Re-encode even if output exists. |
Read-only scan for reclaimable disk space: largest/oldest files plus cache directory sizes. Deletes nothing.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | no | Root to scan. |
| min_size_mb | integer | no | Only report files at least this large. |
| older_than_days | integer | no | Only report files older than this. |
| limit | integer | no | Max files to report. |
| include_caches | boolean | no | Also measure known cache directories. |
Delegate a coding task to opencode, claude, or pi in headless mode.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| cli | string | yes | opencode | claude | pi |
| prompt | string | yes | The coding task to perform. |
| working_dir | string | yes | Project directory (must be a git repo, in writable_roots). |
| dry_run | boolean | no | Snapshot and plan only (defaults to config dry_run_default). |
| verify_command | string | no | Allowlisted command that must pass afterward, e.g. "pytest". |
| auto_rollback | boolean | no | Restore the snapshot if verification fails. |
| require_approval | boolean | no | Keep the diff only after an interactive human yes. Defaults to True; pass false only for pre-reviewed tasks. |
| timeout | number | no | Seconds before the delegate is killed. |
| skip_permissions | boolean | no | Allow --dangerously-skip-permissions (unattended runs). |
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
| Parameter | Type | Required | Notes |
|---|---|---|---|
| goal | string | yes | The full goal or question to satisfy. |
| working_dir | string | no | Project directory the CLI runs in (must be writable). |
| cli | string | no | opencode | claude | pi |
| max_iterations | integer | no | Max review/reprompt rounds (1-10). |
| timeout | number | no | Per-iteration seconds before the CLI is killed. |
| dry_run | boolean | no | Preview only (defaults to config dry_run_default). |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| goal | string | yes | What you want to learn from the target app. |
| target | string | yes | Path to the app (directory, ASAR, or binary). |
| judge | boolean | no | Verify the evidence answers the goal with the judge model. |
| keep_copy | boolean | no | Keep the quarantine copy after the run for audit. |
| timeout | number | no | Seconds before REA is killed (config default: 1800). |
| dry_run | boolean | no | Preview the plan without running REA. |
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Vtai Agent or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 94 / 100
Release 0.7.0 · scanned 28 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score94
Findings11 threat · 6 capability
Capabilityhigh
Coveragesource
Verificationsource
Surface digestfeec474c3a8f30bab63a85b25ccf35278c28ab38973f3716efdccfbbcf03bad4
Score vectorthreat 100 → client 94
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (9 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| system_info | no tags | |
| run_shell | code-exec | code-exec: keyword "shell" in tool name, parameter "command" |
| organize_files | no tags | |
| backup_sync | no tags | |
| transcode_media | no tags | |
| disk_audit | no tags | |
| delegate_coding | code-exec | code-exec: parameter "command" |
| auto_mode | no tags | |
| inspect_application | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digestfeec474c3a8f30ba
Scanned2026-10-28
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.7.0. Pin a release below and the command asks for exactly that one.
0.7.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Vtai Agent can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.