UNPKG MCP server
io.github.unpkg/unpkg-mcpunpkgstreamable-httpv1.0.0Scanned
Live npm and UNPKG data for AI agents: resolution, audits, import maps, malware/CVE checks.
14 tools: 7 change things and 7 only read.
- Reads private data · 1
- Reads text others write · 14
- Can send data out · 1
- 2 findings
Tools listed without sign-in. Remote posture
With Anlyon
7 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the UNPKG MCP server can do
The UNPKG MCP server is published by the GitHub account unpkg. It has 14 tools. It can create or change data (7 tools: build_file_url, audit_dependencies, verify_url, generate_importmap and 3 more), but cannot delete data. 7 tools only read.
1 tool reads private data (list_files); 14 tools bring in text other people can write (resolve_package, list_files, build_file_url and 11 more); 1 tool can send data out of your system (verify_url). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
The fixed checks matched 2 findings (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 21, 2026, version 1.0.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
14 tools
Changes things 7Claude Code: ask
audit_dependenciesClassify a project's runtime dependencies for conversion to direct UNPKG file lookups, in framework context when given.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Classify a project's runtime dependencies for conversion to direct UNPKG file lookups, in framework context when given. Read the project's package.json yourself and pass its dependencies map; this tool checks each package against live npm/UNPKG data and returns convert_now / convert_carefully / keep_bundled / needs_review with suggested URLs and an import map for the safe conversions. IMPORTANT: suitability is not usage. Before calling, scan the project's HTML/files for an existing import map and CDN URLs and pass them as existingImports; entries already on UNPKG come back as already_on_unpkg, not conversion candidates. If you did not scan, say so — currentUsage will be absent rather than falsely 'not detected'. Only pass runtime dependencies, never devDependencies.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
build_file_urlBuild a direct UNPKG file URL (the original file lookup) with a deliberate version policy, verifying the file exists when a path is given.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Build a direct UNPKG file URL (the original file lookup) with a deliberate version policy, verifying the file exists when a path is given.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
estimate_migration_impactOrder-of-magnitude estimate of bandwidth offloaded (and hosting dollars, if a $/GB is given) when bytes move from first-party hosting to UNPKG.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Order-of-magnitude estimate of bandwidth offloaded (and hosting dollars, if a $/GB is given) when bytes move from first-party hosting to UNPKG. Range-based with explicit assumptions and caveats; it cannot forecast latency or Core Web Vitals. Get unpkgBytesPerPageLoad from audit_dependencies' impact.convertNowEntryBytes plus any transitive files the caller chooses to include.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
generate_importmapResolve a set of bare specifiers to UNPKG file URLs and return a ready-to-paste import map.Reads text others write1 finding
Why it is in this group
- The name "generate_importmap" says "generate": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "generate_importmap" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "generate_importmap" says "generate": a word for a change.
Description, as the server wrote it Resolve a set of bare specifiers to UNPKG file URLs and return a ready-to-paste import map. Entry files are resolved live from each package.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
shield_check_packagesCheck exact package@version pairs against Shield intel: malware verdict (with review state) and CVEs affecting that version, including the first patched version.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Check exact package@version pairs against Shield intel: malware verdict (with review state) and CVEs affecting that version, including the first patched version. Works anonymously for packages you name (25 per call); Shield login raises the cap to 200. Domain data still requires login. Missing pairs were not scanned yet — absence is not a clean verdict.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
shield_simulate_requestPreview what Shield would do for one package@version request (optionally with referer/origin) under the logged-in user's effective pin/block rules, using the same rule-matching sem…Reads text others write1 finding
Why it is in this group
- The name "shield_simulate_request" says "request": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "shield_simulate_request" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "shield_simulate_request" says "request": a word for a change.
Description, as the server wrote it Preview what Shield would do for one package@version request (optionally with referer/origin) under the logged-in user's effective pin/block rules, using the same rule-matching semantics as the edge.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
verify_urlCheck that a UNPKG file URL actually resolves (follows redirects) before you put it in a project.Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Check that a UNPKG file URL actually resolves (follows redirects) before you put it in a project.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Only reads 7Show 7 read-only tools
check_importmapValidate an existing or proposed import map: every UNPKG URL resolves, files exist, versions are mutually consistent (including react/react-dom pairing and duplicate-version skew),…Reads text others writeNo findings
Why it is in this group
- The description's first verb is "validate": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Validate an existing or proposed import map: every UNPKG URL resolves, files exist, versions are mutually consistent (including react/react-dom pairing and duplicate-version skew), loose specs are flagged, and framework-managed packages are errors when a framework is given or detected. Run this after generate_importmap or an audit, before committing to a conversion.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
list_filesList the real files inside an exact or resolvable package version via UNPKG ?meta.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "list_files" says "list": a word for reading.
What it can reach
- private-dataThe name "list_files" says "list" and "file": it reads files.
- private-dataThe description's first sentence says "list" and "file": it reads files.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it List the real files inside an exact or resolvable package version via UNPKG ?meta. Use this before choosing a file path; never guess paths.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
resolve_packageResolve a package name plus exact version, dist-tag, or semver range to the version that exists on npm today, with its browser entry points.Reads text others writeNo findings
Why it is in this group
- The name "resolve_package" says "resolve": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "resolve" and "browser": it reads web pages, which anyone can write.
Description, as the server wrote it Resolve a package name plus exact version, dist-tag, or semver range to the version that exists on npm today, with its browser entry points. Use this instead of recalling versions from memory.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
search_packagesSearch npm for a need (e.g.Reads text others writeNo findings
Why it is in this group
- The name "search_packages" says "search": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Search npm for a need (e.g. 'date picker', 'markdown parser') and annotate each result with browser readiness for direct UNPKG file lookup: browser-ready ESM, CommonJS-only, or unclear, with the entry file and size when known. Ranking is npm's relevance order; readiness is annotated, never hidden, so a CJS-only result is visible as such rather than silently dropped.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
shield_domain_packagesList the caller's verified domains with package counts, or the packages Shield has observed on one domain.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "list": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it List the caller's verified domains with package counts, or the packages Shield has observed on one domain. With includeThreats, one domain's packages come back annotated with malware verdicts and CVEs, ranked by the domain's own traffic. Requires Shield login.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
shield_watchlist_statusReturn the logged-in org's monitored packages, blocklist entries, and pin policies as Shield currently holds them.Reads text others writeNo findings
Why it is in this group
- The name "shield_watchlist_status" says "status": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Return the logged-in org's monitored packages, blocklist entries, and pin policies as Shield currently holds them. Requires Shield login.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
shield_whoamiReturn the Shield account, organization, and entitlements for the OAuth login on this connection.Reads text others writeNo findings
Why it is in this group
- The name "shield_whoami" says "whoami": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Return the Shield account, organization, and entitlements for the OAuth login on this connection. Requires an approved Shield account; anonymous connections get an authorization_required error with reconnect instructions.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
14 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write14
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out1
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__unpkg__verify_url"
]
}
}Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 21, 2026, 19:22 UTC, unchanged since Nov 7, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 7
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://mcp.unpkg.com/.well-known/oauth-protected-resource/mcp
- Authorization servers
- https://shield.unpkg.com
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- no
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 7 tools that change things (7 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mcp.unpkg.com/mcp: tools/list returned 14 tools to an anonymous client, including build_file_url (write), audit_dependencies (write), verify_url (write), generate_importmap (write), estimate_migration_impact (write) and 2 more
Findings
Matches of fixed checks, with the text they matched.
The server marks "generate_importmap" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "generate_importmap" says "generate": a word for a change.
The server marks "shield_simulate_request" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "shield_simulate_request" says "request": a word for a change.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http unpkg https://mcp.unpkg.com/mcpclaude mcp add --transport http unpkg https://mcp.unpkg.com/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__unpkg__resolve_package",
"mcp__unpkg__list_files",
"mcp__unpkg__check_importmap",
"mcp__unpkg__search_packages",
"mcp__unpkg__shield_whoami",
"mcp__unpkg__shield_domain_packages",
"mcp__unpkg__shield_watchlist_status"
],
"ask": [
"mcp__unpkg__build_file_url",
"mcp__unpkg__audit_dependencies",
"mcp__unpkg__verify_url",
"mcp__unpkg__generate_importmap",
"mcp__unpkg__estimate_migration_impact",
"mcp__unpkg__shield_simulate_request",
"mcp__unpkg__shield_check_packages"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as unpkg. Review it before you use it.
Capability tags behind 14 rules
- mcp__unpkg__resolve_package untrusted-input
- mcp__unpkg__list_files private-data, untrusted-input
- mcp__unpkg__build_file_url untrusted-input
- mcp__unpkg__audit_dependencies untrusted-input
- mcp__unpkg__verify_url untrusted-input, outbound
- mcp__unpkg__generate_importmap untrusted-input
- mcp__unpkg__check_importmap untrusted-input
- mcp__unpkg__search_packages untrusted-input
- mcp__unpkg__estimate_migration_impact untrusted-input
- mcp__unpkg__shield_whoami untrusted-input
- mcp__unpkg__shield_simulate_request untrusted-input
- mcp__unpkg__shield_check_packages untrusted-input
- mcp__unpkg__shield_domain_packages untrusted-input
- mcp__unpkg__shield_watchlist_status untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.unpkg/unpkg-mcp/verify?hash=f14c1fe31d07907c8ed9e630707e332b596bea7231c67bd2787f19bd06713af3" | jq -e '.changed == false'Pinned hash f14c1fe31d07, from Nov 21, 2026, 09:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.unpkg/unpkg-mcp/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.unpkg/unpkg-mcp)Source: MCP Registry · repository. Synced Nov 7, 2026, 05:17 UTC.
UNPKG MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the UNPKG MCP server safe?
- No scan can promise that. What its definitions show: 14 tools, 7 of which can change, send or delete something, and 2 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the UNPKG MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the UNPKG MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the UNPKG MCP server have?
- 14 tools: 7 write, 7 read. build_file_url, audit_dependencies, verify_url, generate_importmap, estimate_migration_impact, shield_simulate_request, shield_check_packages, resolve_package and 6 more.
Does the UNPKG MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the UNPKG MCP server send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): verify_url.
Has the UNPKG MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 21, 2026.