Agent skill

Vinkius Deploy

by vinkius-labs in vinkius-labs/mcpfusion

How to deploy MCP servers to Vinkius Edge using mcpfusion deploy.

Apache-2.0Auto-check: notesAgent Workflows

Install Vinkius Deploy

skills CLI
$ npx skills add vinkius-labs/mcpfusion --skill vinkius-deploy -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install vinkius-labs/mcpfusion vinkius-deploy --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/vinkius-labs/mcpfusion.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/vinkius-deploy .claude/skills/vinkius-deploy && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
vinkius-deploy
GitHub stars
256
Token cost
~1.7k tokens
SKILL.md length
446 words
Files
2 (incl. references)
Skills in repo
2
Repo updated
First seen
Licence
Apache-2.0

At a glance

How to deploy MCP servers to Vinkius Edge using mcpfusion deploy.

  • Works in 8 steps: src/server.ts → src/index.ts → src/server.js → …
  • Configuring remote settings
  • SKILL.md covers Quick Start, Configuration Files, Edge Constraints — CRITICAL and Edge-Compatible Server…, plus 4 more sections
  • Runs TypeScript scripts from its folder; calls bundle; reaches cloud.vinkius.com and custom.api.com; needs MCPFUSION_DEPLOY_TOKEN

What it does

Vinkius Deploy is an agent skill from vinkius-labs/mcpfusion. How to deploy MCP servers to Vinkius Edge using mcpfusion deploy. Use this skill whenever deploying, configuring remote settings, preparing an entrypoint for edge deployment, or troubleshooting deploy-related errors. Activate when the user says "deploy", "publish to edge", "mcpfusion deploy", "push to Vinkius", mentions .MCPFusionrc, MCPFUSIONDEPLOYTOKEN, or any edge deployment topic.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/example-edge-server.ts`). Compatibility notes: Requires Node.js = 18, MCP Fusion CLI (included in @mcpfusion/core)

It sits in Agent Workflows, covering MCP servers and Deployment. It works with Model Context Protocol, Node.js and OpenAI. The repository describes itself as: MCP Fusion - The TypeScript framework for secure MCP servers. The licence is Apache-2.0.

When your agent uses it

  • Configuring remote settings
  • Preparing an entrypoint for edge deployment
  • Troubleshooting deploy-related errors
  • Publish to edge

Example prompts

  • “deploy”
  • “publish to edge”
  • “mcpfusion deploy”
  • “/vinkius-deploy”

Requirements

  • Node.js
  • A credential in MCPFUSION_DEPLOY_TOKEN
  • Compatibility (from SKILL.md): Requires Node.js >= 18, MCP Fusion CLI (included in @mcpfusion/core)

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

  1. src/server.ts
  2. src/index.ts
  3. src/server.js
  4. src/index.js
  5. server.ts
  6. index.ts
  7. server.js
  8. index.js

What it can do on your machine

Read from SKILL.md and the folder at commit 1dab501. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships script files (TypeScript), which the agent can run.

    Shell commands in SKILL.md call:

    • bundle

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • cloud.vinkius.com
    • custom.api.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • MCPFUSION_DEPLOY_TOKEN

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    Requires Node.js >= 18, MCP Fusion CLI (included in @mcpfusion/core)

    From compatibility in the SKILL.md frontmatter.

Context cost

Vinkius Deploy loads about 1.7k tokens when it runs, and up to ~3.6k if it reads all its reference files. Until then it costs about 102 tokens; SKILL.md has 446 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~102
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:28
    # 2. Set the deploy token in .env
  • NoteMentions a .env fileSKILL.md:29
    EN=<connection-token-from-dashboard>" >> .env
  • NoteMentions a .env fileSKILL.md:52
    ### `.env` (deploy token)
  • NoteMentions a .env fileSKILL.md:110
    read .MCPFusionrc + .env
  • NoteMentions a .env fileSKILL.md:204
    | `set MCPFUSION_DEPLOY_TOKEN=<token> in .env` | Token not found | Add token to `.env` or pass `--token` |

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from vinkius-labs/mcpfusion at commit 1dab501, republished under its Apache-2.0 licence (© vinkius-labs). 446 words, ~1,748 tokens.

Download SKILL.mdSave it as .claude/skills/vinkius-deploy/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
vinkius-deploy
description
How to deploy MCP servers to Vinkius Edge using `mcpfusion deploy`. Use this skill whenever deploying, configuring remote settings, preparing an entrypoint for edge deployment, or troubleshooting deploy-related errors. Activate when the user says "deploy", "publish to edge", "mcpfusion deploy", "push to Vinkius", mentions .MCPFusionrc, MCPFUSION_DEPLOY_TOKEN, or any edge deployment topic.
compatibility
Requires Node.js >= 18, MCP Fusion CLI (included in @mcpfusion/core)
license
Apache-2.0
metadata.author
vinkius-labs
metadata.version
1.0
metadata.tags
deploy, edge, cloud, cli

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

bash
# 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)
json
{
  "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)
env
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
typescript
// 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.

Edge-Compatible Server Entrypoint

See references/example-edge-server.ts for a complete example.

Key differences from a standard server.ts:

diff
- import { autoDiscover } from '@mcpfusion/core';
+ // Explicit imports — no filesystem in V8 isolates
+ import { listProducts } from './tools/product.js';
+ import { getInvoice } from './tools/billing.js';

  const registry = f.registry();
- await autoDiscover(registry, ...);
+ registry.register(listProducts);
+ registry.register(getInvoice);

Deploy Pipeline — What Happens Under the Hood

read .MCPFusionrc + .env
       ↓
resolve entrypoint (src/server.ts → src/index.ts → server.ts → index.ts)
       ↓
check for edge-incompatible APIs (autoDiscover, SandboxEngine, Inspector)
       ↓
esbuild bundle (IIFE, platform: browser, es2022, tree-shaking, minify)
       ↓
size check (max 500KB raw)
       ↓
gzip compress + SHA256 hash
       ↓
POST /servers/:serverId/deploy (Bearer token)
       ↓
response: { deployment_id, server_name, url }
Bundle Characteristics
PropertyValue
FormatIIFE (Immediately Invoked Function Expression)
Platformbrowser (no Node.js APIs)
TargetES2022
Max bundle size500KB (raw, before gzip)
DependenciesAll bundled inside (zod, MCP Fusion, MCP SDK)
Node.js modulesAliased to edge stubs (AST-compatible, never called)

CLI Reference

mcpfusion deploy

Bundle, compress, and deploy to Edge.

bash
mcpfusion deploy                        # auto-detect entrypoint
mcpfusion deploy --server ./src/app.ts  # explicit entrypoint
mcpfusion deploy --token <token>        # override MCPFUSION_DEPLOY_TOKEN
mcpfusion deploy --allow-insecure       # suppress HTTP plaintext warning
mcpfusion remote

Configure the target server and API endpoint.

bash
MCP mcpfusion remote                              # show current config
MCP mcpfusion remote --server-id <uuid>           # set server ID (uses default cloud)
MCP mcpfusion remote https://custom.api.com       # override API endpoint
MCP mcpfusion remote https://custom.api.com --server-id <uuid>  # both at once
mcpfusion dev

Start HMR dev server with auto-reload (for local development).

bash
mcpfusion dev --server ./src/server.ts
mcpfusion dev --server ./src/server.ts --dir ./src/tools
fusion lock

Generate or validate capability lockfile.

bash
fusion lock                               # generate/update lockfile
fusion lock --check                       # verify (CI gate)
Show full SKILL.md (175 more words)Show less
mcpfusion create

Scaffold a new MCP mcpfusion server project.

bash
mcpfusion create my-server
mcpfusion create my-server -y                 # skip prompts
mcpfusion create my-server --vector prisma --transport sse
mcpfusion inspect

Launch the real-time TUI dashboard (requires @mcpfusion/inspector).

bash
mcpfusion inspect --demo            # built-in simulator
fusion insp --pid 12345          # connect to server PID

Troubleshooting

ErrorCauseFix
run: MCP mcpfusion remote --server-id <uuid>No .MCPFusionrc or missing serverIdRun mcpfusion remote --server-id <uuid>
set MCPFUSION_DEPLOY_TOKEN=<token> in .envToken not foundAdd token to .env or pass --token
connection token revoked or invalid (401)Invalid or expired tokenGenerate a new token in the dashboard
connection token does not belong to this server (403)Token/server mismatchCheck your server-id matches the token
server not found (404)Invalid server UUIDVerify the server exists in the dashboard
bundle too large: NNNkb (max 500KB)Fat bundle exceeds limitRemove unused imports, check tree-shaking
autoDiscover() uses fs.readdirEdge-incompatible APISwitch to explicit registry.register()
DNS resolution failedWrong remote URLCheck mcpfusion remote config
connection refusedAPI not runningVerify the remote URL is reachable

Entrypoint Auto-Detection

When --server is not provided, the CLI probes these paths in order:

  1. src/server.ts
  2. src/index.ts
  3. src/server.js
  4. src/index.js
  5. server.ts
  6. index.ts
  7. server.js
  8. index.js

© vinkius-labs, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in .claude/skills/vinkius-deploy of vinkius-labs/mcpfusion.

  • SKILL.md
  • references/example-edge-server.ts

Open the folder on GitHubat commit 1dab501

Compare with similar skills

Vinkius Deploy next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Vinkius Deploy compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Vinkius Deploy this skillvinkius-labs/mcpfusion256—~1.7kAutomated safety check: NotesApache-2.0
Chatgpt AppsLeoYeAI/openclaw-master-skills2.2k—~4.6kAutomated safety check: PassMIT
agentmemory Setup and Diagnosticsrohitg00/agentmemory29k—~1kAutomated safety check: NotesApache-2.0
Codex with ChatGPT Planning LoopXiaoDuoYa/codex-with-chatgpt7.1k—~11kAutomated safety check: NotesMIT
FastmcpTommy-yw/RunbookHermes5463 repos~2.1kAutomated safety check: PassMIT
Cao MCP Appsawslabs/cli-agent-orchestrator1.4k—~1.9kAutomated safety check: PassApache-2.0

Similar skills

  • Chatgpt Apps

    LeoYeAI/openclaw-master-skills

    Complete ChatGPT Apps builder - Create, design, implement, test, and deploy ChatGPT Apps with MCP servers, widgets, auth, database integration, and automated deployment

    2.2k GitHub stars~4.6k tokensUpdated 2 mo ago
    Agent WorkflowsAuto-check passed
  • Sets up and troubleshoots a local agentmemory install, covering the MCP connection, environment variables, ports, authentication and optional feature flags.

    29k GitHub stars~1k tokensUpdated today
    Agent WorkflowsAuto-check: notes
  • Codex with ChatGPT Planning Loop

    XiaoDuoYa/codex-with-chatgpt

    Uses ChatGPT in the browser as the planning and review brain for a Codex session, with Codex keeping all execution and ChatGPT reading the workspace through a bridge.

    7.1k GitHub stars~11k tokensUpdated 8 days ago
    Agent WorkflowsAuto-check: notes
  • Fastmcp

    Tommy-yw/RunbookHermes

    Build, test, inspect, install, and deploy MCP servers with FastMCP in Python.

    546 GitHub starsUsed in 3 repos~2.1k tokens
    Agent WorkflowsAuto-check passed
  • Cao MCP Apps

    awslabs/cli-agent-orchestrator

    Official

    Enable, operate, and extend CAO's MCP Apps surface — the host-rendered fleet dashboard visible inside MCP App hosts (Claude Desktop, ChatGPT, VS Code Copilot, Goose, Postman).

    1.4k GitHub stars~1.9k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Chatgpt Apps

    Haohao-end/openagent

    Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI.

    808 GitHub starsUsed in 1 repo~4.9k tokens
    Agent WorkflowsAuto-check passed

More from vinkius-labs/mcpfusion

  • Mcpfusion Development

    vinkius-labs/mcpfusion

    How to build production MCP servers with MCP Fusion using the MVA (Model-View-Agent) pattern.

    256 GitHub stars~4.3k tokensUpdated 18 days ago
    Auto-check passed

Categories

Questions about Vinkius Deploy

What does Vinkius Deploy do?

How to deploy MCP servers to Vinkius Edge using mcpfusion deploy. Vinkius Deploy is an agent skill from vinkius-labs/mcpfusion. How to deploy MCP servers to Vinkius Edge using mcpfusion deploy.

When should I use Vinkius Deploy?

Vinkius Deploy fits situations like: configuring remote settings; preparing an entrypoint for edge deployment; troubleshooting deploy-related errors; publish to edge.

How do I install Vinkius Deploy in Claude Code?

Run `npx skills add vinkius-labs/mcpfusion --skill vinkius-deploy -a claude-code`. Or copy the skill folder (.claude/skills/vinkius-deploy in vinkius-labs/mcpfusion) into .claude/skills/vinkius-deploy in your project. Claude Code loads it when a task matches its description.

How do I install Vinkius Deploy in Codex?

Run `npx skills add vinkius-labs/mcpfusion --skill vinkius-deploy -a codex`. Or copy the skill folder (.claude/skills/vinkius-deploy in vinkius-labs/mcpfusion) into .agents/skills/vinkius-deploy in your project. Codex loads it when a task matches its description.

Can I use Vinkius Deploy in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add vinkius-labs/mcpfusion --skill vinkius-deploy -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/vinkius-deploy, .gemini/skills/vinkius-deploy, .github/skills/vinkius-deploy and .opencode/skills/vinkius-deploy in your project.

What does Vinkius Deploy need to run?

Going by SKILL.md and its folder, Vinkius Deploy needs TypeScript for the scripts in its folder, the command-line tools its instructions call (bundle) and credentials named MCPFUSION_DEPLOY_TOKEN. Our summary lists: Node.js; A credential in MCPFUSION_DEPLOY_TOKEN. Compatibility (from SKILL.md): Requires Node.js >= 18, MCP Fusion CLI (included in @mcpfusion/core).

Does Vinkius Deploy access the network?

SKILL.md names 2 domains. In commands or code: cloud.vinkius.com and custom.api.com; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is Vinkius Deploy safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Vinkius Deploy use?

Vinkius Deploy is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Vinkius Deploy use?

About 1.7k tokens (SKILL.md is roughly 7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.9k tokens, read only when the agent opens those files.

What are the alternatives to Vinkius Deploy?

Skills that share tags, products or a category with Vinkius Deploy: Chatgpt Apps (LeoYeAI/openclaw-master-skills, 2.2k stars), agentmemory Setup and Diagnostics (rohitg00/agentmemory, 29k stars), Codex with ChatGPT Planning Loop (XiaoDuoYa/codex-with-chatgpt, 7.1k stars) and Fastmcp (Tommy-yw/RunbookHermes, 546 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Vinkius Deploy?

vinkius-labs (a GitHub organization) maintains it in vinkius-labs/mcpfusion, which has 256 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on September 20, 2026.

Source: vinkius-labs/mcpfusion on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.