deploy-mcp-oauth-vps

deploy-mcp-oauth-vps is a skill for Codex from vinilana/invokta. It costs 82 tokens per session (699 once invoked), scanned A, original, MIT.

A deployment procedure for running an MCP OAuth service stack with Docker Compose on a VPS, including hosts using Traefik or bundled Caddy. It covers releases, upgrades, checks, backups, and rollback preparation.

In plain words
What is it for?
Use it to set up or update the stack, choose the correct edge-proxy configuration, rebuild or transfer images, configure the environment, bootstrap an owner, run health checks, and roll back when needed.
Why use it?
It helps avoid deploying an incompatible proxy or an unverified release. The procedure checks the host, validates the Compose setup, protects database backups, and confirms service health.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

Good fit Use it to set up or update the stack, choose the correct edge-proxy configuration, rebuild or transfer images, configure the environment, bootstrap an owner, run health checks, and roll back when needed.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vinilana/invokta/deploy-mcp-oauth-vps
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add vinilana/invokta --skill deploy-mcp-oauth-vps
Clone the repo
git clone --depth 1 https://github.com/vinilana/invokta

Made for: Codex.

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 deploy-mcp-oauth-vps

README.md
[![agentmods](https://agentmods.dev/badge/skills/vinilana/invokta/deploy-mcp-oauth-vps/github.svg)](https://agentmods.dev/skills/vinilana/invokta/deploy-mcp-oauth-vps)
Your own site
<a href="https://agentmods.dev/skills/vinilana/invokta/deploy-mcp-oauth-vps"><img src="https://agentmods.dev/badge/skills/vinilana/invokta/deploy-mcp-oauth-vps/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 deploy-mcp-oauth-vps

Your own site · 80×15
<a href="https://agentmods.dev/skills/vinilana/invokta/deploy-mcp-oauth-vps"><img src="https://agentmods.dev/badge/skills/vinilana/invokta/deploy-mcp-oauth-vps.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 699 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
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 $0.00082 $0.00699
Opus 5 $0.00041 $0.00349
Sonnet 5 $0.00016 $0.00140
Haiku 4.5 $0.00008 $0.00070

Measured 10d ago against content hash 9dd258f704cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

deploy-mcp-oauth-vps scanned grade A with 0 findings 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 10d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

examples/auth-self-hosted-oauth-engine/.agents/skills/deploy-mcp-oauth-vps/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deploy MCP OAuth to a VPS

Resolve the project root as three directories above this SKILL.md. Perform all local reads and commands from that root before inspecting any remote host.

Choose the edge topology

  1. Read AGENTS.md, docs/DEPLOYMENT_RUNBOOK.md, and docs/PRODUCTION_CHECKLIST.md completely.
  2. Inspect the target before writing: running containers, Compose files, volumes, free ports, edge proxy, health, current image version, and .env key names without printing values.
  3. Use compose.yaml when ports 80 and 443 are free for bundled Caddy.
  4. Use compose.yaml plus compose.hostinger.yaml when Traefik already owns the edge. Set a unique APP_TRAEFIK_ROUTER_PREFIX.
  5. Do not start a second edge proxy on occupied ports.
  6. Derive networks and service reachability from the merged Compose output and the running proxy. Do not invent an external Traefik network when the files do not declare one.

Prepare a recoverable release

  • Run npm run check before packaging.
  • Validate the selected Compose merge before building.
  • Back up PostgreSQL before migrations and protect the backup permissions.
  • Tag the current image with an explicit rollback version.
  • Transfer only source, manifests, migrations, Compose files, and proxy config.
  • Exclude .env, .git, node_modules, dist, logs, database files, and credentials from transfer packages.
  • Preserve existing volumes and the remote .env.

Deploy in dependency order

  1. Build the migrate, auth, and engine image targets.
  2. Start with up -d --no-build only after the build succeeds.
  3. Wait for PostgreSQL, the one-shot migration, OAuth, and engine health.
  4. Do not rerun owner bootstrap when an owner already exists.
  5. Create the owner interactively only for a confirmed new deployment; never persist the bootstrap password on the VPS.

Verify publicly

  • Confirm container health, restart counts, and application versions.
  • Review migration, auth, and engine logs for sanitized errors.
  • Run the public MCP deployment probe.
  • Verify protected-resource metadata, authorization discovery, and JWKS.
  • Run the DCR probe and confirm temporary-client cleanup.
  • Complete one real login, consent, callback, token exchange, and authenticated MCP request before declaring a new OAuth integration ready.

Read the full file on GitHub · 66 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. 10d ago First seen · 66 lines · 82 tokens per session scan A 9dd258f704cd

Subscribe to this mod's changes

deploy-mcp-oauth-vps is a skill published in the GitHub repository vinilana/invokta (129 stars, last pushed yesterday), licensed MIT. It adds 82 tokens to every session and 699 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. 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

azd-deployment

Deploy containerized frontend + backend applications to Azure Container Apps with remote builds, managed identity, and idempotent infrastructure.

sickn33/agentic-awesome-skills · 29 tokens

openshell-cli

Guide agents through using the OpenShell CLI (openshell) for sandbox management, gateway registration, provider configuration and refresh, policy iteration, settings, service exposure, BYOC workflows, and attached-provider inference. Covers basic through advanced multi-step workflows. Trigger keywords - openshell…

NVIDIA/OpenShell · 128 tokens

langbot-deploy

Deploy and configure a LangBot instance — Docker / Docker Compose, Kubernetes, the config.yaml model, the Box sandbox runtime, the plugin runtime, and the global API key. Use when installing, deploying, upgrading, or configuring LangBot in production or self-hosted environments. Triggers on "deploy langbot", "langbot…

langbot-app/LangBot · 104 tokens

compute-env-setup

Set up a compute environment on a remote provider so Claude Science jobs can run there. Covers direct SSH/conda hosts, Slurm clusters, container-via-bridge runners, and managed-API providers (Modal, GCP, RunPod). Use when standing up a new provider, porting an env to a different backend, adding a tool that needs its…

UnicomAI/wanwu · 134 tokens

azure-cloud-migrate

Assess and migrate cross-cloud workloads to Azure with reports and code conversion. Supports Lambda→Functions, Beanstalk/Heroku/App Engine→App Service, Fargate/Kubernetes/Cloud Run/Spring Boot→Container Apps. WHEN: migrate Lambda to Functions, AWS to Azure, migrate Beanstalk, migrate Heroku, migrate App Engine, Cloud…

microsoft/skills · 106 tokens

atmos-helmfile

Helmfile orchestration: sync/apply/destroy/diff, Kubernetes deployments, varfile generation, EKS integration, source management.

cloudposse/atmos · 33 tokens