agentmods.dev

mcpb

mcpb is a skill for Claude Code, Codex from zircote/mcp-bundle. It costs 40 tokens per session (3,324 once invoked), scanned A, original, MIT.

A skill that packages an MCP server into an MCPB bundle, a distributable package with a standard manifest and directory layout. It can also validate the package and add continuous-integration workflows.

In plain words
What is it for?
Use it to detect an existing Node.js or Python MCP server, create its bundle files, validate the result, and connect packaging to CI/CD.
Why use it?
It turns an MCP server project into a checked package that can be built and maintained consistently.

Skill for Claude CodeCodex

Part of the mcp-bundle plugin — 1 skill shipped together

not rated 3 5mo ago A scan 40 tokens original MIT
View the source file zircote/mcp-bundle
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.

agentmods
npx agentmods add skills/zircote/mcp-bundle/mcpb
Any agent
npx skills add zircote/mcp-bundle --skill mcpb
Clone the repo
git clone --depth 1 https://github.com/zircote/mcp-bundle

Made for: Claude Code, Codex.

Or install mcp-bundle, the plugin that ships this one along with the rest of its 1 skill.

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 mcpb

README.md
[![agentmods](https://agentmods.dev/badge/skills/zircote/mcp-bundle/mcpb.svg)](https://agentmods.dev/skills/zircote/mcp-bundle/mcpb)
Your own site
<a href="https://agentmods.dev/skills/zircote/mcp-bundle/mcpb"><img src="https://agentmods.dev/badge/skills/zircote/mcp-bundle/mcpb.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,324 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00040 $0.03324
Opus 5 $0.00020 $0.01662
Sonnet 5 $0.00008 $0.00665
Haiku 4.5 $0.00004 $0.00332

Measured 4d ago against content hash 475314640148, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcpb 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 4d 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.

skills/mcpb/SKILL.md · 361 lines

How it starts

The opening of the file, as written. The whole thing — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCPB Bundle Generator

You are an expert at creating MCPB (MCP Bundle) packages following the official specification from https://github.com/anthropics/mcpb.

Trigger Patterns

This skill activates when the user asks to:

  • "create mcpb bundle"
  • "package mcp server"
  • "create mcp bundle"
  • "mcpb init"
  • "mcpb"

Execution Flow

Follow these steps in order. Do NOT skip steps. Ask clarifying questions only when values truly cannot be inferred.

Step 1: Detect MCP Server

Search the current project for an existing MCP server implementation.

Detection signals by language:

Node.js:

  • package.json containing @modelcontextprotocol/sdk in dependencies
  • Source files importing from @modelcontextprotocol/sdk
  • Usage of StdioServerTransport
  • Usage of Server class from @modelcontextprotocol/sdk/server

Python:

  • requirements.txt or pyproject.toml containing mcp package
  • Source files importing from mcp.server
  • Usage of stdio_server() or mcp.server.stdio
  • Decorators like @server.list_tools(), @server.call_tool()

Python UV:

  • pyproject.toml with mcp in dependencies
  • Source files using mcp.server.stdio.stdio_server()
  • No server/lib/ or server/venv/ directories (deps managed by UV)

Binary:

  • Cargo.toml with MCP-related dependencies
  • go.mod with MCP SDK references
  • Pre-compiled executables in server/ directory

Search strategy:

  1. Check package.json for @modelcontextprotocol/sdk in dependencies/devDependencies
  2. Check pyproject.toml or requirements.txt for mcp package
  3. Grep source files for MCP SDK imports: @modelcontextprotocol/sdk, from mcp, mcp.server
  4. Look for StdioServerTransport, stdio_server, transport setup patterns
  5. Identify all tool definitions (tool names, descriptions, input schemas)

If NO MCP server is detected: Ask the user: "No MCP server found in this project. Would you like me to:

  1. Scaffold a new MCP server with MCPB bundle structure
  2. Point me to the server entry file

Read the full file on GitHub · 361 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. 4d ago First seen · 361 lines · 40 tokens per session scan A 475314640148

Subscribe to this mod's changes

mcpb is a skill published in the GitHub repository zircote/mcp-bundle (3 stars, last pushed 5mo ago), licensed MIT. It adds 40 tokens to every session and 3,324 once invoked, about $0.0002 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 2026-08-31.

Building agentsCI and CDDevOps and cloudautomationclaude-codeclaude-code-plugindevtoolsgithub-actions
Related

Other skills, from other repositories

local-ci-dev

Run local CI via the in-tree dev build of local-ci (pnpm local-ci-dev) to verify changes to this repo before completing work. Runs pnpm local-ci-dev run --all in the background, watches the log for step failures, and retries failed runners after fixes. Use before reporting work as complete, or whenever the user asks…

redwoodjs/local-ci · 109 tokens

local-ci

Run GitHub Actions workflows locally with pause-on-failure for AI-agent-driven CI iteration.

redwoodjs/local-ci · 20 tokens

local-ci

Run GitHub Actions CI locally with Local CI to validate changes before pushing. Use when testing, running checks, or validating code changes.

redwoodjs/local-ci · 30 tokens

deploy-setup

Wire up a freshly scaffolded Starter Series project for its first release — detect the template, register required GitHub secrets, set up OIDC trusted publishing where applicable, and trigger the first CD run. Pairs with the create skill (you scaffold first, then run this).

starter-series/create-starter · 61 tokens

claudeconf

Set up or harden a project's quality and security pipeline — git hooks, CI, tests, and pre-merge gates. Researches and pins tools that fit the project's stack instead of using fixed choices, then wires a standard-tool harness you own. Use when initializing a repo, adding CI or pre-commit checks, hardening an existing…

nikolaypaskov/claudeconf-plugin · 78 tokens

aw-author

Author, validate, and improve GitHub Agentic Workflow (gh-aw) markdown files. Use when the user wants to create a new workflow, validate an existing workflow, improve a workflow, or debug workflow issues. Triggers on: "aw-author", "agentic workflow", "gh-aw workflow", "workflow markdown", "workflow frontmatter"…

zircote-plugins/github-agentic-workflows · 91 tokens