Skip to content

Power Strip Security MCP server

io.github.AlbertBalestrini/power-strip-securityAlbertBalestrinistreamable-httpv0.2.0Scanned

Prompt-injection shield for agents: read pages, scan content, audit MCP servers and skills. x402.

4 tools: 3 change things and 1 only read.

Tools: 0 delete, 0 irreversible, 3 write, 1 read.
  • Reads private data · 0
  • Reads text others write · 4
  • Can send data out · 4
  • 1 finding

Tools listed without sign-in. Remote posture

With Anlyon

3 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.
Govern this server →

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 Power Strip Security MCP server can do

The Power Strip Security MCP server is published by the GitHub account AlbertBalestrini. It has 4 tools. It can create or change data (3 tools: check_prompt_injection, audit_mcp_server and audit_agent_skill), but cannot delete data. 1 tool only reads.

4 tools bring in text other people can write (read_url, check_prompt_injection, audit_mcp_server and 1 more); 4 tools can send data out of your system (read_url, check_prompt_injection, audit_mcp_server and 1 more).

The fixed checks matched 1 finding (credentials-mention). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.

Last scanned Nov 12, 2026, version 0.2.0.

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.

4 tools

Changes things 3Claude Code: ask
  • audit_agent_skillCheck an agent skill (SKILL.md with its scripts and references) or AGENTS.md, CLAUDE.md, .cursorrules before loading it: prompt injection, curl | bash, encoded commands, credential…Reads text others writeCan send data out1 finding

    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.

    Findings

    • Info

      The description mentions "credential".

      Matched text

      description: "...jection, curl | bash, encoded commands, credential theft, exfiltration, hardcoded keys, pe..."

      What this check looks for
    Description, as the server wrote it
    Check an agent skill (SKILL.md with its scripts and references) or AGENTS.md, CLAUDE.md, .cursorrules before loading it: prompt injection, curl | bash, encoded commands, credential theft, exfiltration, hardcoded keys, persistence. For MCP servers use audit_mcp_server. Give files or one url, not both. Returns level, findings (type, severity, file, line, snippet) and per-file fingerprints to send back as pinned. Costs US$0.005 in USDC on Base (x402); nothing is executed.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • audit_mcp_serverCheck an MCP server for tool poisoning before connecting: hidden instructions, sensitive-file access, exfiltration parameters, cross-tool shadowing, rug pulls.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 an MCP server for tool poisoning before connecting: hidden instructions, sensitive-file access, exfiltration parameters, cross-tool shadowing, rug pulls. For skills or AGENTS.md use audit_agent_skill. Give url (tools are listed read-only, never called) or the pasted tools, not both. Returns level, findings (type, severity, location, snippet) and per-tool fingerprints to send back as pinned. Costs US$0.01 in USDC on Base (x402); servers that cannot be listed are not charged.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • check_prompt_injectionScan HTML or text you already have (an email, a document, a tool result, a page fetched elsewhere) for prompt injection before it reaches your prompt.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
    Scan HTML or text you already have (an email, a document, a tool result, a page fetched elsewhere) for prompt injection before it reaches your prompt. To fetch a URL, use read_url instead; for MCP tool definitions or skill files, use audit_mcp_server or audit_agent_skill. Returns risk (0-1), level (low/medium/high), findings (type, snippet, position, confidence), clean_text and wrapped_text, which marks the rest as untrusted data. Costs US$0.002 in USDC on Base (x402). Max 256 KB.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
Only reads 1Show 1 read-only tool
  • read_urlFetch a public web page or PDF with hidden text and exfiltration links removed, plus a prompt-injection report.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "read_url" says "read": 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 name "read_url" says "read" and "url": it reads web pages, which anyone can write.
    • untrusted-inputThe description's first sentence says "fetch" and "web": it reads web pages, which anyone can write.
    • untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    Fetch a public web page or PDF with hidden text and exfiltration links removed, plus a prompt-injection report. Use it instead of fetching untrusted URLs yourself; for content you already have, use check_prompt_injection. Returns risk (0-1), level, findings, content and wrapped_text: put wrapped_text in your prompt, not the raw page. Costs US$0.005 in USDC on Base (x402); unreadable pages (robots.txt, login, CAPTCHA, JavaScript-only) return a reason and are not charged.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • 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.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write4
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out4
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or 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.

Tools listed without sign-in

Looked at Nov 15, 2026, 13:21 UTC, unchanged since Oct 31, 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
3
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
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 served tools/list without credentials, and the list has 3 tools that change things (3 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://api.powerstripsecurity.workers.dev/mcp: tools/list returned 4 tools to an anonymous client, including check_prompt_injection (write), audit_mcp_server (write), audit_agent_skill (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

1 info

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools4 changed.~4 changedView diff
  2. Tools2 added, 1 removed.+2 added−1 removedView diff

Install

Pinned to version 0.2.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http power-strip-security https://api.powerstripsecurity.workers.dev/mcp
claude mcp add --transport http power-strip-security https://api.powerstripsecurity.workers.dev/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": [],
    "ask": [
      "mcp__power-strip-security__read_url",
      "mcp__power-strip-security__check_prompt_injection",
      "mcp__power-strip-security__audit_mcp_server",
      "mcp__power-strip-security__audit_agent_skill"
    ],
    "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 power-strip-security. Review it before you use it.

Capability tags behind 4 rules
  • mcp__power-strip-security__read_url untrusted-input, outbound
  • mcp__power-strip-security__check_prompt_injection untrusted-input, outbound
  • mcp__power-strip-security__audit_mcp_server untrusted-input, outbound
  • mcp__power-strip-security__audit_agent_skill 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://radar.anlyon.com/api/v1/servers/io.github.AlbertBalestrini/power-strip-security/verify?hash=64f1bd61b1c317350a038945ab941d9f0a0f4e4c53c4fc69d9e672d978d00d2c" | jq -e '.changed == false'

Pinned hash 64f1bd61b1c3, from Nov 12, 2026, 19:18 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.AlbertBalestrini/power-strip-security/changes.xml

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

Badge

Anlyon Radar badge for io.github.AlbertBalestrini/power-strip-security
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.AlbertBalestrini/power-strip-security.svg)](https://radar.anlyon.com/servers/io.github.AlbertBalestrini/power-strip-security)

Source: MCP Registry. Synced Oct 31, 2026, 00:18 UTC.

Power Strip Security MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Power Strip Security MCP server safe?

No scan can promise that. What its definitions show: 4 tools, 3 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Power Strip Security MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Power Strip Security 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 Power Strip Security MCP server have?

4 tools: 3 write, 1 read. check_prompt_injection, audit_mcp_server, audit_agent_skill and read_url.

Does the Power Strip Security MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Power Strip Security MCP server send data to outside services?

4 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): read_url, check_prompt_injection, audit_mcp_server and audit_agent_skill.

Has the Power Strip Security MCP server changed its tools?

Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 12, 2026. Every change is on this page and in its Atom feed.