build-mcpb
anthropics/claude-plugins-official
Package an MCP server with its runtime into a single .mcpb file for distribution without requiring Node or Python.
What is build-mcpb?
MCPB bundles a local MCP server with its runtime into a zip archive that runs on the user's machine without toolchain dependencies. Use it when your server must access local files, desktop apps, or OS-level APIs; for cloud-only APIs, build a remote HTTP server instead.
- Bundle Node or Python MCP servers with dependencies into a single .mcpb file
- Package manifest.json with entry point, config schema, and platform compatibility
- Define install-time user configuration (directories, sensitive settings) via manifest
- Launch stdio MCP servers with environment variable substitution from user config
- Validate and sign bundles for distribution to Claude Desktop and other hosts
How to install build-mcpb
npx skills add https://github.com/anthropics/claude-plugins-official --skill build-mcpb- Node.js and npm (for building; not required on end-user machines)
- @anthropic-ai/mcpb CLI tool for packing and validation
- Standard MCP SDK (@modelcontextprotocol/sdk)
- Zod or similar for input schema validation
How to use build-mcpb
- 1.Create a manifest.json defining server type, entry point, mcp_config command/args/env, and user_config schema
- 2.Write your MCP server as a standard stdio server, reading config from environment variables set in manifest
- 3.Bundle dependencies: for Node use esbuild or copy node_modules; for Python vendor into a subdirectory
- 4.Run `npx @anthropic-ai/mcpb validate` to check manifest against schema
- 5.Run `npx @anthropic-ai/mcpb pack` to create the .mcpb zip archive
- 6.Test on a machine without your dev toolchain to verify all dependencies are bundled
- 7.Optionally sign with `npx @anthropic-ai/mcpb sign` before distribution
- 8.Distribute the .mcpb file; users drag it onto Claude Desktop or their MCP host to install
Use cases
- Distribute a local file browser that reads from user-approved directories without requiring Node installed
- Package a desktop app controller (e.g., Slack, Figma automation) that runs on the user's machine
- Ship a localhost service wrapper (e.g., local database, dev server) as a single installable file
- Create an OS-level tool (system info, process control) bundled with Python runtime for cross-platform use
- Distribute a file watcher or indexer that needs persistent local filesystem access
- MCP server authors building tools that require local filesystem or OS access
- Developers shipping desktop integrations that must run on user machines
- Teams distributing internal tools without requiring users to install Node or Python
- Anyone packaging a local stdio MCP server for end-user installation
build-mcpb FAQ
Use MCPB only if your server must run locally — reading files, controlling desktop apps, accessing localhost services, or OS APIs. If it only hits cloud APIs, build a remote HTTP server instead; MCPB adds packaging complexity with no user benefit.
No. MCPB has no manifest-level sandbox — the server runs with full user privileges. You must validate all paths, refuse directory traversal, allowlist spawns, and implement security in your tool handlers. See references/local-security.md.
The server will fail to start on machines without your dev toolchain. Always test on a clean machine without Node/Python installed before shipping.
Yes. MCPB servers can serve UI resources the same way remote MCP apps do. Widget authoring is covered in the build-mcp-app skill.
Define user_config in manifest.json with fields like rootDir (directory picker) or apiKey (sensitive keychain storage). The host's UI surfaces these; your server reads them from environment variables you specify in mcp_config.env.
Full instructions (SKILL.md)
Source of truth, from anthropics/claude-plugins-official.
name: build-mcpb description: This skill should be used when the user wants to "package an MCP server", "bundle an MCP", "make an MCPB", "ship a local MCP server", "distribute a local MCP", discusses ".mcpb files", mentions bundling a Node or Python runtime with their MCP server, or needs an MCP server that interacts with the local filesystem, desktop apps, or OS and must be installable without the user having Node/Python set up. version: 0.1.0
Build an MCPB (Bundled Local MCP Server)
MCPB is a local MCP server packaged with its runtime. The user installs one file; it runs without needing Node, Python, or any toolchain on their machine. It's the sanctioned way to distribute local MCP servers.
MCPB is the secondary distribution path. Anthropic recommends remote MCP servers for directory listing — see https://claude.com/docs/connectors/building/what-to-build.
Use MCPB when the server must run on the user's machine — reading local files, driving a desktop app, talking to localhost services, OS-level APIs. If your server only hits cloud APIs, you almost certainly want a remote HTTP server instead (see build-mcp-server). Don't pay the MCPB packaging tax for something that could be a URL.
What an MCPB bundle contains
my-server.mcpb (zip archive)
├── manifest.json ← identity, entry point, config schema, compatibility
├── server/ ← your MCP server code
│ ├── index.js
│ └── node_modules/ ← bundled dependencies (or vendored)
└── icon.png
The host reads manifest.json, launches server.mcp_config.command as a stdio MCP server, and pipes messages. From your code's perspective it's identical to a local stdio server — the only difference is packaging.
Manifest
{
"$schema": "https://raw.githubusercontent.com/anthropics/mcpb/main/schemas/mcpb-manifest-v0.4.schema.json",
"manifest_version": "0.4",
"name": "local-files",
"version": "0.1.0",
"description": "Read, search, and watch files on the local filesystem.",
"author": { "name": "Your Name" },
"server": {
"type": "node",
"entry_point": "server/index.js",
"mcp_config": {
"command": "node",
"args": ["${__dirname}/server/index.js"],
"env": {
"ROOT_DIR": "${user_config.rootDir}"
}
}
},
"user_config": {
"rootDir": {
"type": "directory",
"title": "Root directory",
"description": "Directory to expose. Defaults to ~/Documents.",
"default": "${HOME}/Documents",
"required": true
}
},
"compatibility": {
"claude_desktop": ">=1.0.0",
"platforms": ["darwin", "win32", "linux"]
}
}
server.type — node, python, or binary. Informational; the actual launch comes from mcp_config.
server.mcp_config — the literal command/args/env to spawn. Use ${__dirname} for bundle-relative paths and ${user_config.<key>} to substitute install-time config. There's no auto-prefix — the env var names your server reads are exactly what you put in env.
user_config — install-time settings surfaced in the host's UI. type: "directory" renders a native folder picker. sensitive: true stores in OS keychain. See references/manifest-schema.md for all fields.
Server code: same as local stdio
The server itself is a standard stdio MCP server. Nothing MCPB-specific in the tool logic.
import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
import { z } from "zod";
import { readFile, readdir } from "node:fs/promises";
import { join } from "node:path";
import { homedir } from "node:os";
// ROOT_DIR comes from what you put in manifest's server.mcp_config.env — no auto-prefix
const ROOT = (process.env.ROOT_DIR ?? join(homedir(), "Documents"));
const server = new McpServer({ name: "local-files", version: "0.1.0" });
server.registerTool(
"list_files",
{
description: "List files in a directory under the configured root.",
inputSchema: { path: z.string().default(".") },
annotations: { readOnlyHint: true },
},
async ({ path }) => {
const entries = await readdir(join(ROOT, path), { withFileTypes: true });
const list = entries.map(e => ({ name: e.name, dir: e.isDirectory() }));
return { content: [{ type: "text", text: JSON.stringify(list, null, 2) }] };
},
);
server.registerTool(
"read_file",
{
description: "Read a file's contents. Path is relative to the configured root.",
inputSchema: { path: z.string() },
annotations: { readOnlyHint: true },
},
async ({ path }) => {
const text = await readFile(join(ROOT, path), "utf8");
return { content: [{ type: "text", text }] };
},
);
const transport = new StdioServerTransport();
await server.connect(transport);
Sandboxing is entirely your job. There is no manifest-level sandbox — the process runs with full user privileges. Validate paths, refuse to escape ROOT, allowlist spawns. See references/local-security.md.
Before hardcoding ROOT from a config env var, check if the host supports roots/list — the spec-native way to get user-approved directories. See references/local-security.md for the pattern.
Build pipeline
Node
npm install
npx esbuild src/index.ts --bundle --platform=node --outfile=server/index.js
# or: copy node_modules wholesale if native deps resist bundling
npx @anthropic-ai/mcpb pack
mcpb pack zips the directory and validates manifest.json against the schema.
Python
pip install -t server/vendor -r requirements.txt
npx @anthropic-ai/mcpb pack
Vendor dependencies into a subdirectory and prepend it to sys.path in your entry script. Native extensions (numpy, etc.) must be built for each target platform — avoid native deps if you can.
MCPB has no sandbox — security is on you
Unlike mobile app stores, MCPB does NOT enforce permissions. The manifest has no permissions block — the server runs with full user privileges. references/local-security.md is mandatory reading, not optional. Every path must be validated, every spawn must be allowlisted, because nothing stops you at the platform level.
If you came here expecting filesystem/network scoping from the manifest: it doesn't exist. Build it yourself in tool handlers.
If your server's only job is hitting a cloud API, stop — that's a remote server wearing an MCPB costume. The user gains nothing from running it locally, and you're taking on local-security burden for no reason.
MCPB + UI widgets
MCPB servers can serve UI resources exactly like remote MCP apps — the widget mechanism is transport-agnostic. A local file picker that browses the actual disk, a dialog that controls a native app, etc.
Widget authoring is covered in the build-mcp-app skill; it works the same here. The only difference is where the server runs.
Testing
# Interactive manifest creation (first time)
npx @anthropic-ai/mcpb init
# Run the server directly over stdio, poke it with the inspector
npx @modelcontextprotocol/inspector node server/index.js
# Validate manifest against schema, then pack
npx @anthropic-ai/mcpb validate
npx @anthropic-ai/mcpb pack
# Sign for distribution
npx @anthropic-ai/mcpb sign dist/local-files.mcpb
# Install: drag the .mcpb file onto Claude Desktop
Test on a machine without your dev toolchain before shipping. "Works on my machine" failures in MCPB almost always trace to a dependency that wasn't actually bundled.
Reference files
references/manifest-schema.md— fullmanifest.jsonfield referencereferences/local-security.md— path traversal, sandboxing, least privilege
Related skills
More from anthropics/claude-plugins-official and the wider catalog.

claude-automation-recommender
Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to first set up Claude Code for a project, or wants to know what Claude Code features they should use.

claude-md-improver
Audit and improve CLAUDE.md files to optimize Claude Code's project context.

command-development
Create and manage slash commands with YAML frontmatter, dynamic arguments, and bash execution for Claude Code.

configure
Set up Discord bot token and configure channel access policy.

frontend-design
Distinctive visual design guidance for building UIs with intentional aesthetic choices, not templated defaults.

hook-development
Event-driven automation for Claude Code plugins with prompt-based and command hooks.