mcpfusion: Skill for Claude Code

.claude/skills/vinkius-deploy/SKILL.md

vinkius-deploy is a skill for Claude Code from vinkius-labs/mcpfusion. It costs 94 tokens per session (1,767 once invoked), scanned A, original, Apache-2.0.

A guide for deploying MCP servers to Vinkius Edge, where the server runs in a V8 Isolate, a restricted runtime without filesystem or process access. It covers remote configuration, deployment tokens, bundling, and the deploy command.

In plain words
What is it for?
Use it to prepare, configure, deploy, or troubleshoot MCP Fusion servers running on Vinkius Edge.
Why use it?
It explains the project settings and credentials needed to upload a server and highlights runtime limits that can make server code incompatible with Edge.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is vinkius-labs/mcpfusion's own configuration. It tells Claude Code how to work on mcpfusion itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcpfusion configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is mcpfusion deploy --server ./src/app.ts # explicit entrypoint.

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/vinkius-labs/mcpfusion/main/.claude/skills/vinkius-deploy/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/vinkius-labs/mcpfusion

Made for: Claude Code.

Wrote 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.

agentmods badge for vinkius-deploy

README.md
[![agentmods](https://agentmods.dev/badge/skills/vinkius-labs/mcpfusion/vinkius-deploy/github.svg)](https://agentmods.dev/skills/vinkius-labs/mcpfusion/vinkius-deploy)
Your own site
<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.

agentmods 80×15 button for vinkius-deploy

Your own site · 80×15
<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>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,767 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
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.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00094 $0.01767
Opus 5 $0.00047 $0.00883
Sonnet 5 $0.00019 $0.00353
Haiku 4.5 $0.00009 $0.00177

Measured 9d ago against content hash 7458ace06f2d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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 9d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (references/example-edge-server.ts), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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`
Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/skills/vinkius-deploy/SKILL.md · 225 lines

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
  • remote defaults to https://cloud.vinkius.com (omit to use default)
  • serverId is 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.

Read the full file on GitHub · 225 lines

Files

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.

Changes

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.

  1. 9d ago First seen · 225 lines · 94 tokens per session scan A 7458ace06f2d

Subscribe to this mod's changes

vinkius-deploy is a skill published in the GitHub repository vinkius-labs/mcpfusion (256 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 94 tokens to every session and 1,767 once invoked, about $0.0005 per session on Opus 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.

Related

Other skills, from other repositories

odoo-data-quality-gate

Audit an Odoo database's data quality with evidence before trusting AI answers, importing, or migrating — duplicates, missing required values, orphaned references, format anomalies — and drive remediation through odoo-mcp's gated write workflow. Use when the user asks to "check data quality", "clean up data", "prepare…

erpipe-org/mcp-odoo · 85 tokens

odoo-migration-copilot

Plan and de-risk an Odoo version upgrade (16→17→18→19/20) using odoo-mcp's migration workbench — audit custom addons, classify upgrade-log failures into a worklist, resolve model renames, and preview JSON-2 payloads for the XML-RPC sunset. Use when the user mentions upgrading/migrating Odoo versions, broken upgrade…

erpipe-org/mcp-odoo · 100 tokens

odoo-month-end-close

Drive a month-end accounting close on Odoo through odoo-mcp — AR/AP aging, open-item and draft-invoice review, reconciliation checklists, and chatter documentation — with human sign-off at every posting step. Use when the user asks to "close the month", "review receivables/payables", "check aging", or prepare finance…

erpipe-org/mcp-odoo · 81 tokens

odoo-agency-fleet-review

Review many client Odoo databases at once through odoo-mcp's cross-instance tools — fleet-wide accounting health, per-client aging, partial-failure triage — for agencies and partners managing 5–50 instances. Use when the user asks "which client...", "across all instances/databases", or wants a fleet/portfolio status.

erpipe-org/mcp-odoo · 77 tokens

ingest-gradle-upgrade

Ingests a Gradle wrapper upgrade for this repository: reads the release notes, upgrade guides, and linked documentation for the version upgraded to, then updates this repo's own code/tooling and the shipped Gradle MCP skills (src/main/skills/) so everything stays accurate for that version. Positive Triggers (when to…

rnett/gradle-mcp · 279 tokens

authoring-gradle-builds

Authoring and modifying Gradle build logic, including settings, plugins, dependencies, tasks, conventions, and upgrades. Activate when build files or plugins must change; use using-gradle for inspection or execution without build-definition edits.

rnett/gradle-mcp · 52 tokens