UNPKG

unpkg-mcp

A remote MCP server for UNPKG. It gives AI agents live npm and UNPKG data for direct UNPKG file lookups: https://unpkg.com/ @ / .

Agents often recall npm details incorrectly — versions that don't exist, file paths that were never published, Node entry points offered as browser modules. This server resolves versions, lists real package files, audits projects for UNPKG conversion, validates import maps, and checks packages for malware and CVEs, all from live data.

Deployed at https://mcp.unpkg.com (landing page at /, MCP endpoint at /mcp).

Tools

Package safety checks

Every package the server resolves can also be checked against Shield's security data, in two ways:

• Named packages. shield_check_packages takes exact package@version pairs and returns, for each one, a malware verdict with its review state (confirmed or provisional), the CVEs that affect that version, and the first patched version to upgrade to. Verdicts and CVE matches are computed for the exact version asked about — a clean result never comes from checking a different version.
• Inside audits. audit_dependencies attaches the same verdict and CVE data to every version it resolves, so a flagged package is visible in the audit result next to its conversion recommendation.

No account is needed for either: named-package checks are anonymous (25 per call), and audit enrichment works the same signed out. A provisional verdict is reported as provisional; it is not presented as confirmed malicious.

With a Shield login, the checks extend to your own estate: shield_domain_packages (with threats enabled) returns the packages observed on your verified domains annotated with verdicts and CVEs, ranked by each domain's traffic, so the packages that matter most surface first.

Example prompts:

• "Is lodash@4.17.20 safe to load? Check it for malware and CVEs, and tell me what to upgrade to."
• "Check the packages in this audit for known compromises or CVEs before we convert anything."
• *(Shield login)* "Which packages on my domains have CVEs or malware verdicts, worst first?"

Shield login

The general tools are anonymous. With a Shield account approved from the beta waitlist, your MCP client can also sign in via OAuth and the shield_* account tools unlock, scoped to your own organization.

Package-safety checks are not login-gated: shield_check_packages works anonymously for packages you name, and audit_dependencies includes verdicts and CVEs either way. Signing in adds your own domains, watchlist, and edge simulation.

Prompts, resources, and skill

• Prompts: audit_project_for_unpkg, convert_this_page, find_browser_package.
• Resources: the conversion playbook and version-specifier policy (unpkg://guidance/…), also served at GET /playbook.md.
• Skill: skill/unpkg/SKILL.md provides the same guidance to agents without MCP.

Connect a client

Clients connect by URL. Per-client configuration is in examples/clients.md and in the picker on the landing page at https://mcp.unpkg.com/.

Claude Code:

claude mcp add --transport http unpkg https://mcp.unpkg.com/mcp

For agents without MCP, copy skill/unpkg/ into the client's skills directory. At the project level, you can also paste examples/AGENTS.snippet.md into your project's AGENTS.md.

Try it out

With an agent connected, some useful prompts:

• "Resolve react@^18 with the UNPKG MCP — what's the resolved version and browser entry point? Now try a version of react that doesn't exist."
• "List the files in preact@10.26.4/dist, build a patch-policy URL for the module file, and verify it resolves."
• "Audit this project for UNPKG conversion."
• "Check this import map with the UNPKG MCP: …" (paste a map)
• "Is lodash@4.17.20 safe to load? Check it for malware and CVEs, and tell me what to upgrade to."
• "Based on the audit, estimate the migration impact for a site with 1M page views a month at $0.09/GB."

The server reports what it can verify and declines what it can't: import maps are validated as a system, audits keep framework-managed packages bundled, and estimates come back as ranges with assumptions rather than a single figure.

MCP Registry

server.json in this repo is the listing manifest for the official MCP Registry, under the namespace io.github.unpkg/unpkg-mcp.

Publishing (maintainers): install the mcp-publisher CLI from the MCP Registry project, then from this repo:

mcp-publisher login github

mcp-publisher publish

Note: the organization namespace requires an owner-level GitHub credential — the interactive device flow only grants your personal namespace. Use a classic PAT with read:org scope (see the MCP Registry authentication docs), and revoke it afterwards.

Releasing

The server is a remote endpoint, so most channels update themselves: connected clients see new tools as soon as the Worker deploys, Glama re-crawls this repo and the endpoint, skills.sh serves the skill from GitHub, and directory listings (awesome lists, mcp.so) are static entries that only change if the URL or description changes.

For a version release:

1. Bump the version everywhere it appears, keeping all of them equal: package.json, src/version.ts, server.json, plugin/.claude-plugin/plugin.json, plugin/plugin.json, and the plugin entry in .claude-plugin/marketplace.json. (Tests fail if any of these drift.)
2. Deploy the Worker (wrangler deploy).
3. Tag the release on GitHub (vX.Y.Z with release notes).
4. Republish the registry manifest: mcp-publisher publish. Downstream directories (PulseMCP, Smithery, and others) ingest from the official MCP Registry, so this is the step that updates them.
5. If the plugin changed, publish the new plugin version in the Claude developer portal; marketplace users get it via claude plugin marketplace update.

Claude plugin

This repo is also a Claude Code plugin (and its own plugin marketplace). The plugin lives in plugin/ and bundles the MCP server above with the unpkg skill, so one install gives Claude Code both:

claude plugin marketplace add unpkg/unpkg-mcp

claude plugin install unpkg@unpkg

Connecting the plugin is the same anonymous-by-default server at https://mcp.unpkg.com/mcp; Shield tools still sign in only when used.

Run it locally

pnpm install

pnpm dev # HTTP Worker on http://localhost:8787

• Landing page: http://localhost:8787/
• Health: http://localhost:8787/health
• MCP endpoint: http://localhost:8787/mcp
• Server card: http://localhost:8787/.well-known/mcp.json

For local client setup, use the same configurations as above with http://localhost:8787/mcp in place of the production URL.

Develop

pnpm test         # unit, golden-project, and MCP protocol tests

pnpm typecheck # tsc --noEmit pnpm build # wrangler deploy --dry-run (production bundle check)

Layout: src/clients/ (npm, UNPKG, and Shield API clients), src/domain/ (audit, import-map checking, estimation, guidance), src/server.ts (MCP wiring). Golden projects in test/fixtures/projects/ pin audit classification behavior.

Environment (wrangler.jsonc vars): UNPKG_ORIGIN, NPM_REGISTRY, SHIELD_API_ORIGIN, OAUTH_ISSUER, OAUTH_RESOURCE, OAUTH_ENABLED.

Estimating impact

audit_dependencies reports entry-file byte totals. estimate_migration_impact turns those, plus a traffic figure, into a bandwidth-offload range (and a dollar range when a $/GB rate is supplied). It does not forecast latency: where a site already serves from a capable CDN, latency is usually unchanged, and the practical gains are bundle size, cacheability, and how quickly patched versions reach users.