A publishing guide for MCP servers, which are programs that let AI tools use external capabilities. It covers TypeScript/Node.js packages published to npm and Python packages run or published through UVX and PyPI.

Use it to check an MCP server’s configuration, verify its git and package metadata, and prepare it for npm or PyPI distribution.

It helps catch package, repository-link, and README problems before public release. It also provides validation steps for each supported runtime.

How MCDxAI/minecraft-dev-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to MCDxAI/minecraft-dev-mcp. 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/MCDxAI/minecraft-dev-mcp/main/.claude/skills/mcp-publish/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/MCDxAI/minecraft-dev-mcp

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/mcdxai/minecraft-dev-mcp/mcp-publish/github.svg)](https://agentmods.dev/skills/mcdxai/minecraft-dev-mcp/mcp-publish)

Your own site

<a href="https://agentmods.dev/skills/mcdxai/minecraft-dev-mcp/mcp-publish"><img src="https://agentmods.dev/badge/skills/mcdxai/minecraft-dev-mcp/mcp-publish/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/mcdxai/minecraft-dev-mcp/mcp-publish"><img src="https://agentmods.dev/badge/skills/mcdxai/minecraft-dev-mcp/mcp-publish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 560 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 warn 7 Sept 2026

SkillSpector: 4 findings, up to medium

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 →

medium MCP Rug Pull · line 59
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Fix: Pin the version: npx @scope/[email protected]
medium MCP Rug Pull · line 59
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Fix: Pin the version: npx @scope/[email protected]
medium MCP Rug Pull · line 65
uvx/uv tool run commands without ==version create a rug-pull risk.

Fix: Pin the version: uvx package-name==1.2.3
medium MCP Rug Pull · line 65
uvx/uv tool run commands without ==version create a rug-pull risk.

Fix: Pin the version: uvx package-name==1.2.3

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.

Model	Per session	Once invoked
Fable 5.1	$0.00068	$0.00560
Opus 5	$0.00034	$0.00280
Sonnet 5	$0.00014	$0.00112
Haiku 4.5	$0.00007	$0.00056

Measured 9d ago against content hash 536673d4d544, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

mcp-publish 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 9d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/validate_npm.py, scripts/validate_uvx.py), 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.

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.

.claude/skills/mcp-publish/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Server Publishing

Guides publishing MCP servers to NPM or PyPI/UVX.

Workflow

Detect server type
Run validation script
Fix issues
Publish

Type Detection

Check project root:

package.json -> TypeScript/Node.js -> See references/npm.md
pyproject.toml -> Python -> See references/uvx.md

If both exist, ask which runtime the server targets.

Validation

Run before publishing:

TypeScript/Node.js:

python <skill-path>/scripts/validate_npm.py <project-path>

Python:

python <skill-path>/scripts/validate_uvx.py <project-path>

Replace <skill-path> with this skill's location and <project-path> with the MCP server directory.

Fix all errors before proceeding to publish.

Repository URL Validation

After running validation, check that the package manifest matches the git remote:

Get the configured git remote: git remote get-url origin
Compare with repository field in package.json or pyproject.toml
If mismatch, confirm with user which is correct before proceeding
Update the manifest file if needed

README Installation Section

Before publishing, verify and update the README installation instructions.

Validation checks for all four installation methods:

TypeScript/Node.js:

npx command: npx @scope/package-name
Global install: npm install -g @scope/package-name
Claude Desktop config (claude_desktop_config.json with mcpServers)
Claude Code CLI: claude mcp add

Python:

uvx command: uvx package-name
Pip install: pip install package-name
Claude Desktop config (claude_desktop_config.json with mcpServers)
Claude Code CLI: claude mcp add

Update README sections automatically if any methods are missing.

Pre-Publish Checklist

Verify before any publish:

Version incremented from last release
README.md exists with server description
LICENSE file present
No secrets in committed files
Build artifacts excluded via .gitignore
Server runs locally without errors
Repository URL in manifest matches git remote
README installation instructions are correct

Read the full file on GitHub · 84 lines

Files

What ships with it

4 files 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.

9d ago First seen · 84 lines · 68 tokens per session scan A 536673d4d544

Subscribe to this mod's changes

mcp-publish is a skill published in the GitHub repository MCDxAI/minecraft-dev-mcp (37 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 560 once invoked, about $0.0003 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.

Building agents DevOps and cloud java-decompiler mcp-server minecraft-mod model-context-protocol mojmap yarn-mappings

opik-diagnose

Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and low online-eval scores. With the Opik MCP connected it lists the project's agentinsightsissue entities, then fills the gaps with list (filters, sort, a time…

comet-ml/opik-mcp · 174 tokens

cortex-explore-memory

Explore the memory system's state, find gaps in knowledge, assess coverage, and get diagnostic information. Use when the user asks 'what does my memory look like', 'show me memory stats', 'what am I missing', 'how good is my knowledge', 'memory health', 'show coverage', 'find gaps', 'what topics are weak', or when you…

cdeust/Cortex · 91 tokens

quick-capture

Use this skill to drop a new task into GSD Task Manager from any AI assistant that has the gsd-mcp-server connected.

vscarpenter/gsd-task-manager · 0 tokens

event-staffing-ordering

Order W-2 event staff for US/CA events through TempGuru.

Tempguru-co/tempguru-mcp · 22 tokens

chainstack

Work with the Chainstack MCP server to manage blockchain nodes and projects. Use when deploying nodes, migrating to Chainstack from another RPC provider such as QuickNode or Alchemy, checking platform status, searching Chainstack docs, contacting the Chainstack team, or interacting with the Chainstack platform API via…

chainstacklabs/mcp-server · 66 tokens

delegacion-local

Regla y catálogo para delegar pasos mecánicos (resumir, clasificar, extraer, boilerplate, mensaje de commit desde un diff, traducir texto o archivo, resumir salida de lint/tests/CI, explicar código, describir una imagen, verificar si el backend local está disponible) a modelos locales vía las tools local del MCP…

ZahiriNatZuke/local-delegate · 137 tokens

minecraft-dev-mcp: Skill for Claude Code