Packkit
NPM · PACKKIT-MCP
Scaffold, compose, and upgrade modern multi-language projects as a native tool for AI agents.
Available components
Last scanned (2 hours ago)
Scores higher than 95% of npm servers
Category Developer Tools
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security98
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 32 of 103 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency97
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to PackkitLabs/packkit-mcp). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 79 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability76
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 821 tokens (~136/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management80
- Stability observed for 24 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 5 Nov 26 −2
- Stability: pass → 0.80 functional
- 30 Oct 26 0
- Stability: 0.97 → pass security
- 28 Oct 26 0
- Stability: pass → 0.93 functional
- 22 Oct 26 0
- Stability: 0.97 → pass security
- 21 Oct 26 0
- Stability: pass → 0.97 functional
- 17 Oct 26 +2
- Stability: 0.80 → pass security
- 16 Oct 26 −2
- Stability: pass → 0.80 functional
- 15 Oct 26 0
- Stability: 0.97 → pass security
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Analysed npm/packkit-mcp@1.2.1
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | npm |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | PackkitLabs/packkit-mcp |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/PackkitLabs/packkit-mcp/.github/workflows/release.yml@refs/heads/main |
| Rekor log index | 2497409116 |
| Predicate type | SLSA build provenance https://slsa.dev/provenance/v1 |
| Subject digest | sha512:554ef05b066bc0630f8e7d4bdb9164c77f334dafb8c8a63c050bf0f77b536f749eb520ff50e03e8b5600fe54c417e1e1c50a6c8d462c342fc67349afb |
Background: How many MCP packages publish verified provenance →
Dependencies 103 packages
| Packages resolved | 103 |
|---|---|
| Stale | 32 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
compose_fullstack ~257
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 <directory>/<name>.
| Name | Type | Req | Description |
|---|---|---|---|
| backend | object | yes | The service backend to generate: { generator, name, preset?, config? } |
| backendDir | string | – | Subdir for the backend (default apps/server) |
| directory | string | – | Parent directory to create <name>/ in when writing |
| dockerCompose | boolean | – | Emit a root docker-compose.yml (default true) |
| force | boolean | – | Overwrite colliding existing files when writing |
| frontend | object | yes | The static frontend to generate: { generator, name, preset?, config? } |
| frontendDir | string | – | Subdir for the frontend (default apps/web) |
| name | string | yes | Repo name (folder when writing; README heading) |
| write | boolean | – | Write files to disk (default false = preview only) |
No output schema declared.
No examples provided.
generate_project ~190
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 <directory>/<name>. Existing files are never overwritten unless force is set. Call list_presets / get_generator_schema first.
| Name | Type | Req | Description |
|---|---|---|---|
| config | object | – | Options from get_generator_schema (overrides the preset) |
| directory | string | – | Parent directory to create <name>/ in when writing (default: cwd) |
| force | boolean | – | Overwrite colliding existing files when writing (default false) |
| generator | string | yes | Generator id from list_generators |
| name | string | yes | Project/package name (also the folder name when writing) |
| preset | string | – | A preset (or alias) from list_presets |
| write | boolean | – | Write files to disk (default false = preview only) |
No output schema declared.
No examples provided.
get_generator_schema ~63
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.
| Name | Type | Req | Description |
|---|---|---|---|
| generator | string | yes | Generator id from list_generators |
No output schema declared.
No examples provided.
list_generators ~63
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.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_presets ~108
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.
| Name | Type | Req | Description |
|---|---|---|---|
| generator | string | yes | Generator id from list_generators (e.g. "javascript", "python", "go") |
| includeExperimental | boolean | – | Include experimental presets (default false) |
No output schema declared.
No examples provided.
plan_upgrade ~140
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.
| Name | Type | Req | Description |
|---|---|---|---|
| config | object | – | The options it was generated with |
| directory | string | yes | Path to the existing scaffolded project |
| generator | string | yes | Generator id from list_generators |
| name | string | yes | Project name (as originally generated) |
| preset | string | – | The preset it was generated from (if any) |
No output schema declared.
No examples provided.
How do I install the Packkit MCP server?
Packkit runs locally as an npm package, launched with npx -y packkit-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · packkit-mcp
claude mcp add packkitlabs-packkit-mcp -- npx -y packkit-mcp
What is the Packkit MCP server?
Packkit is an MCP server listed in the public MCP registry as io.github.PackkitLabs/packkit-mcp. Scaffold, compose, and upgrade modern multi-language projects as a native tool for AI agents. This page covers its npm package (packkit-mcp).
Is the Packkit MCP server safe to use?
Packkit scores 92 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Packkit MCP server expose?
Packkit exposes 6 tools: list_generators, list_presets, get_generator_schema, generate_project, plan_upgrade, compose_fullstack. Their descriptions and schemas cost roughly 821 tokens of context every time the server is loaded.
Is the Packkit MCP server still maintained?
Packkit is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the Packkit MCP server under?
Packkit declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.