Skip to content

Pugi

io.pugi/pugipugi.iostreamable-httpv1.0.0Scanned

AI product team: builds and publishes websites from a brief, logos, security checks.

12 tools: 2 can delete or cancel things, 1 do something that can't be undone, 6 change things and 3 only read.

Tools: 2 delete, 1 irreversible, 6 write, 3 read.
  • Reads private data · 1
  • Reads text others write · 8
  • Can send data out · 3
  • 3 findings

Sign-in required, no OAuth metadata. Remote posture

Anlyon alternative

9 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

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.

12 tools

Deletes or cancels 2Claude Code: deny
  • editChanges a website in its existing project.Reads text others writeNo findings

    Why it is in this group

    • The name "edit" says "edit": a word for a change.
    • The server marks it destructive (destructiveHint: true).

    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
    Changes a website in its existing project. Progress shows in the build card.

    Annotations the server declares

    • title: Change a site Pugi built
    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: true
  • publishPublishes a built website at its public address.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "publish" says "publish": a word for a change that another call does not undo.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe name "publish" says "publish": it sends or publishes something to other people.
    Description, as the server wrote it
    Publishes a built website at its public address.

    Annotations the server declares

    • title: Publish a built site
    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: true
Can't be undone 1Claude Code: ask
  • publish_statusGet publish status.Can send data out1 finding

    Why it is in this group

    • The name "publish_status" says "publish": a word for a change that another call does not undo.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • outboundThe name "publish_status" says "publish": it sends or publishes something to other people.

    Findings

    • Warn

      The server marks "publish_status" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "publish_status" says "publish": a word for a change that another call does not undo.

      What this check looks for
    Description, as the server wrote it
    Get publish status.

    Annotations the server declares

    • title: Get publish status
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Changes things 6Claude Code: ask
  • build_siteBuilds a website from a brief and returns a job_id.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.

    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
    Builds a website from a brief and returns a job_id. A build takes several minutes; the call may return while it is still running. In hosts that render the build card (MCP Apps or ChatGPT widget), the card tracks progress automatically: do not poll job_status. In hosts without a build card (Claude Code or API), call job_status with the job_id until the job is finished, stopped or failed. Review the view-only preview_url before publishing. One build at a time per account.

    Annotations the server declares

    • title: Build a website from a brief
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • scan_repoChecks a public GitHub repository for leaked secrets, vulnerable dependencies and risky code.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.

    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
    Checks a public GitHub repository for leaked secrets, vulnerable dependencies and risky code.

    Annotations the server declares

    • title: Check a GitHub repository for security issues
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • scan_urlChecks a public website for HTTPS, security headers and exposed secrets.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
    Checks a public website for HTTPS, security headers and exposed secrets.

    Annotations the server declares

    • title: Check a website for security issues
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
Only reads 3Show 3 read-only tools
  • get_balanceShows account plan, masked email, balance and daily allowance.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "get_balance" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "show" and "email": it reads mail.
    • untrusted-inputThe description's first sentence says "show" and "email": it reads inbound email, which other people can write.
    Description, as the server wrote it
    Shows account plan, masked email, balance and daily allowance.

    Annotations the server declares

    • title: Get credit balance
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • job_statusReturns the state of a build or edit job (running, finished, stopped or failed), a short progress line and, when available, a view-only preview_url.Reads text others writeNo findings

    Why it is in this group

    • The name "job_status" says "status": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "return" and "url": it reads web pages, which anyone can write.
    Description, as the server wrote it
    Returns the state of a build or edit job (running, finished, stopped or failed), a short progress line and, when available, a view-only preview_url. In hosts that render the build card (MCP Apps or ChatGPT widget), the card tracks progress automatically: do not poll job_status. In hosts without a build card (Claude Code or API), call job_status with the job_id until the job is finished, stopped or failed. Preview links expire after 15 minutes; call again for a fresh link.

    Annotations the server declares

    • title: Get the status of a build
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false

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.

24 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 private-data tool breaks every one.

Reads private data1
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write8
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out3
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__pugi__get_balance"
    ]
  }
}

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.

Sign-in required, no OAuth metadata

Looked at Oct 24, 2026, 16:19 UTC, unchanged since Oct 24, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
401
tools/list served without credentials
no
Tools that change things, listed without credentials
0
Protocol version
not observed
WWW-Authenticate on 401
no
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • WarnThe whole server

    The endpoint asks for credentials (HTTP 401) but publishes no RFC 9728 protected resource metadata: no resource_metadata in WWW-Authenticate and no document at /.well-known/oauth-protected-resource.

    Matched text

    https://api.pugi.io/api/agent/v1/mcp: initialize answered HTTP 401, without a WWW-Authenticate header

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

3 warn
  • The server marks "buy_credits_link" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "buy_credits_link" says "link": a word for a change.

    What this check looks for
  • The server marks "publish_status" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "publish_status" says "publish": a word for a change that another call does not undo.

    What this check looks for
  • The server marks "select_logo" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "select_logo" says "select": a word for a change.

    What this check looks for

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 pugi https://api.pugi.io/api/agent/v1/mcp
claude mcp add --transport http pugi https://api.pugi.io/api/agent/v1/mcp

Run 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.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__pugi__get_balance",
      "mcp__pugi__catalog_search",
      "mcp__pugi__job_status"
    ],
    "ask": [
      "mcp__pugi__buy_credits_link",
      "mcp__pugi__scan_url",
      "mcp__pugi__make_logo",
      "mcp__pugi__publish_status",
      "mcp__pugi__scan_repo",
      "mcp__pugi__build_site",
      "mcp__pugi__select_logo"
    ],
    "deny": [
      "mcp__pugi__edit",
      "mcp__pugi__publish"
    ]
  }
}

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 pugi. Review it before you use it.

Capability tags behind 9 rules
  • mcp__pugi__get_balance private-data, untrusted-input
  • mcp__pugi__scan_url untrusted-input, outbound
  • mcp__pugi__make_logo untrusted-input
  • mcp__pugi__publish_status outbound
  • mcp__pugi__scan_repo untrusted-input
  • mcp__pugi__build_site untrusted-input
  • mcp__pugi__edit untrusted-input
  • mcp__pugi__job_status untrusted-input
  • mcp__pugi__publish untrusted-input, outbound

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://anlyon.dev/api/v1/servers/io.pugi/pugi/verify?hash=4729afec627f7e4b271fdad0c7aef390bfcb3a920b4f2806f9536b27704bf1c5" | jq -e '.changed == false'

Pinned hash 4729afec627f, from Oct 29, 2026, 00:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://anlyon.dev/servers/io.pugi/pugi/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

anlyon.dev badge for io.pugi/pugi
[![anlyon.dev](https://anlyon.dev/badge/io.pugi/pugi.svg)](https://anlyon.dev/servers/io.pugi/pugi)

Source: MCP Registry. Synced Oct 29, 2026, 00:18 UTC.