Borrowing it
Nothing to install: this file belongs to vinkius-labs/mcpfusion. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vinkius-labs/mcpfusion/main/.claude/skills/vinkius-deploy/SKILL.mdgit clone --depth 1 https://github.com/vinkius-labs/mcpfusionWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/vinkius-labs/mcpfusion/vinkius-deploy)<a href="https://agentmods.dev/skills/vinkius-labs/mcpfusion/vinkius-deploy"><img src="https://agentmods.dev/badge/skills/vinkius-labs/mcpfusion/vinkius-deploy/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/vinkius-labs/mcpfusion/vinkius-deploy"><img src="https://agentmods.dev/badge/skills/vinkius-labs/mcpfusion/vinkius-deploy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 28 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 29 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 110 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Excessive Agency · line 186 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00094 | $0.01767 |
| Opus 5.5 | $0.00038 | $0.00707 |
| Sonnet 5.5 | $0.00019 | $0.00353 |
| Haiku 4.5 | $0.00009 | $0.00177 |
Grade A, and why
vinkius-deploy scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
### ❌ `SandboxEngine` — Requires `child_process` and `fs` Copies of this mod
1 near-identical copy found in the catalogue:
- vinkius-deploy — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deploying to Vinkius Edge
mcpfusion deploy bundles your MCP server into a self-contained fat bundle, compresses it, and uploads it to Vinkius Edge where it runs inside a V8 Isolate.
Quick Start
# 1. Configure the remote (once per project)
MCP mcpfusion remote --server-id <uuid-from-dashboard>
# 2. Set the deploy token in .env
echo "MCPFusion_DEPLOY_TOKEN=<connection-token-from-dashboard>" >> .env
# 3. Deploy
mcpfusion deploy
The server UUID and connection token are obtained from the Vinkius Cloud dashboard after creating a server instance.
Configuration Files
.MCPFusionrc (auto-generated by mcpfusion remote)
{
"remote": "https://cloud.vinkius.com",
"serverId": "abc-123-def"
}
- Auto-added to
.gitignore remotedefaults tohttps://cloud.vinkius.com(omit to use default)serverIdis the target server UUID from the dashboard
.env (deploy token)
MCPFUSION_DEPLOY_TOKEN=your-connection-token-here
The token authenticates the deploy request. It can also be passed via --token <value> flag.
Edge Constraints — CRITICAL
V8 Isolates do NOT have filesystem or process access. The following patterns are incompatible with edge deployment:
❌ autoDiscover() — Requires fs.readdir
// WRONG — autoDiscover() scans the filesystem at runtime
await autoDiscover(registry, fileURLToPath(new URL('./tools', import.meta.url)));
// CORRECT — explicit imports for edge
import { listUsers } from './tools/users.js';
import { getInvoice } from './tools/billing.js';
registry.register(listUsers);
registry.register(getInvoice);
❌ SandboxEngine — Requires child_process and fs
SandboxEngine cannot run inside V8 isolates. Remove it for edge deploys — tool code runs directly in the isolate.
❌ Inspector / @mcpfusion/inspector — Requires Node.js IPC
The TUI inspector cannot run inside V8 isolates.
⚠️ fast-redact — Uses Function constructor
May have limited support. Verify it works in your isolate before deploying.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 225 lines · 94 tokens per session scan A 7458ace06f2d
vinkius-deploy is a skill published in the GitHub repository vinkius-labs/mcpfusion (255 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 94 tokens to every session and 1,767 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
vinkius-deploy compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| vinkius-deployvinkius-labs/mcpfusion | Skill | 255 | 1mo ago | Apache-2.0 | A | 94 | Claude Code |
| threebrowser-studio-mcpSamG-Coder/ThreeBrowserStudio | Skill | 25 | 4d ago | MIT | A | 122 | Codex |
| onplana-project-plannerOnplana/onplana-mcp-server | Skill | 5 | 18d ago | MIT | A | 133 | Claude Code |
| just-publishjust-done/just-publish-mcp | Skill | 1 | yesterday | MIT | A | 195 | Codex |
| onplana-autonomous-agentOnplana/onplana-mcp-server | Skill | 5 | 18d ago | MIT | A | 102 | Claude Code |
| mcp-ads-professional-campaignerRoyAzran/mcp-ads | Skill | 3 | 5d ago | MIT | A | 55 | Claude Code, Codex |
| ads-managerRoyAzran/mcp-ads | Skill | 3 | 5d ago | MIT | A | 92 | Claude Code |