packkit-mcp
Officialpackkit-mcp lets AI agents scaffold and upgrade modern projects across languages (JavaScript/TypeScript, Python, Go) as native MCP tools.
Discover generators —
list_generatorslists every language target with maturity and capabilities; start here.Browse presets —
list_presetsshows a generator's presets (e.g.ts-lib,react-lib,py-cli), hiding experimental ones unlessincludeExperimental: true.Inspect options —
get_generator_schemareturns a generator's full option schema (options, choices, defaults) before you pass aconfig.Generate projects —
generate_projectpreviews a file tree, stack summary and deployment contract by default;write: truescaffolds to disk (never overwriting existing files unlessforceis set).Plan upgrades —
plan_upgradeproduces a baseline-aware three-way diff (template changes vs. your edits), writing nothing, for generators supporting baseline-upgrade.Compose fullstack repos —
compose_fullstackstitches a static frontend + HTTP service backend (e.g. React + FastAPI) from any generators into one repo withapps/web+apps/server, a deployment contract and docker-compose (preview by default).
Provides tools to scaffold and upgrade modern JavaScript projects (libraries, CLIs, services, SPAs, monorepos) using Packkit generators, including previewing file trees and planning upgrades.
Provides tools to scaffold and upgrade Python projects (libraries, CLIs) using Packkit generators, including previewing file trees and planning upgrades.
Provides tools to scaffold and upgrade modern TypeScript projects (libraries, CLIs, services, SPAs, monorepos) using Packkit generators, including previewing file trees and planning upgrades.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@packkit-mcp List the available project generators"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
packkit-mcp
The Packkit Model Context Protocol server —
let AI agents (Claude Desktop, Cursor, VS Code, …) scaffold and upgrade modern
projects as a native tool. It fronts every Packkit generator through the
@packkit/core protocol, so the same
tools work across languages:
JavaScript / TypeScript —
create-packkit(libraries, CLIs, services, SPAs, monorepos)Python —
create-packkit-py(library, CLI, worker, HTTP service)Go —
create-packkit-go(library, CLI, worker, HTTP service)
It also exposes a compose_fullstack tool that stitches a static frontend + a service
backend from any generators into one fullstack repo (e.g. React + FastAPI).
Adding a language later is one registry.register(...) line here — the tools don't change.
Install
Point your MCP client at the published package (no install needed — npx fetches it):
{
"mcpServers": {
"packkit": {
"command": "npx",
"args": ["-y", "packkit-mcp"]
}
}
}Related MCP server: packkit-mcp
Tools
Tool | What it does |
| List every generator (language target) with maturity + capabilities. Start here. |
| List a generator's presets (experimental hidden unless asked). |
| A generator's full option schema (options, choices, defaults). |
| Preview a project (file tree + stack + deployment contract), or |
| Baseline-aware three-way upgrade plan for an existing project — template changes vs your edits, writes nothing. |
The typical flow: list_generators → list_presets / get_generator_schema →
generate_project. All generation is protocol-driven; the server holds no
language-specific logic.
Develop
npm install
npm run smoke # boot the server over MCP stdio and exercise all three generators
npm run check # server.json sync check + smoke (what CI runs)Releases are automated with Changesets — see RELEASING.md.
License
MIT © DanMat
Available Tools
6 toolscompose_fullstackA
Compose two projects — a static frontend and an HTTP service backend, from ANY generators — into one fullstack repo (apps/web + apps/server) with a fullstack deployment contract and a docker-compose. Language-neutral: e.g. a "javascript" react-app frontend + a "python" py-service (or "go" go-service) backend. By default PREVIEWS; pass write: true to scaffold under /.
Inputs: name (required), backend (required), frontend (required), force, +5 more.
generate_projectA
Generate a project with a generator. By default it PREVIEWS (returns the file tree, stack summary and deployment contract without touching disk); pass write: true to scaffold the files under /. Existing files are never overwritten unless force is set. Call list_presets / get_generator_schema first.
Inputs: name (required), generator (required), force, write, +3 more.
get_generator_schemaA
Return a generator's full option schema — every option, its choices and defaults — as JSON. Read this before passing a config to generate_project so the options you set are valid for that generator.
Inputs: generator (required).
list_generatorsA
START HERE. Lists every Packkit generator (a language target — e.g. javascript, python, go) with its maturity and protocol capabilities. Pick the generator whose language matches what the user wants, then call list_presets and get_generator_schema for it before generating.
Inputs: no named parameters.
list_presetsA
List the presets a generator offers (e.g. ts-lib, react-lib, node-service for javascript; py-lib, py-cli for python), each with a description and maturity. Experimental presets are hidden unless includeExperimental is true. Choose a preset that matches the shape the user wants instead of guessing.
Inputs: generator (required), includeExperimental.
plan_upgradeA
Plan a re-scaffold of an existing project against the current templates: a three-way diff (baseline vs on-disk vs freshly generated) that separates template changes from the user's own edits, so nothing is clobbered. Reports the plan only — it writes nothing. Requires a generator that supports baseline-upgrade.
Inputs: name (required), directory (required), generator (required), config, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each tool has a clear role in the generation workflow: listing generators, listing presets, reading schemas, generating, planning upgrades, and composing fullstack apps. list_presets and get_generator_schema are close in purpose, but their descriptions make the distinction clear enough.
All six tools use a consistent verb_noun snake_case pattern: list_generators, list_presets, get_generator_schema, generate_project, plan_upgrade, compose_fullstack. There are no mixed naming conventions or vague verbs.
Six tools is well-scoped for a project generation server. Each tool covers a distinct stage of the workflow without redundancy or bloat.
The set covers discovery, configuration, generation, upgrade planning, and fullstack composition well. The one notable gap is that plan_upgrade only reports a plan with no corresponding apply/execute tool, leaving upgrade execution as a manual or indirect step.
Maintenance
Related MCP Connectors
A registry of AI agent tools — MCP servers, APIs, CLIs, SDKs — kept current by automated ingestion.
Your org's AI agents, tasks, runs, search, and brain files as MCP tools and resources.
MCP-first toolbox for agents: KV storage, auth, queue, and utility tools. Free in early access.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceAutomatically generates MCP tools, CLI, and web UI from TypeScript methods, enabling AI agents and chat clients to interact with custom capabilities defined once.252 npm100MIT

packkit-mcpofficial
AlicenseAqualityCmaintenanceLets AI agents scaffold modern npm packages, CLIs, HTTP services, and apps as a native tool. Three tools: inspect the full option/preset schema, preview the generated file tree for a config, and write the project to disk.3119 npm1MIT- AlicenseNot gradedqualityDmaintenanceEnables AI agents to generate complete, runnable MCP server projects from natural-language tool descriptions, including schema, implementation, tests, README, and license.MIT
- AlicenseNot gradedqualityAmaintenanceEnables AI assistants to research, plan, generate requirements, create starter projects, analyze codebases, and execute multi-step software development workflows through MCP tools.42 npmMIT