# Power Strip Security (remote · api.powerstripsecurity.workers.dev)

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

- Trust score: 67/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `api.powerstripsecurity.workers.dev`: 67/100 (this document), [markdown](https://verifymcp.io/servers/albertbalestrini-power-strip-security/api.md), [page](https://verifymcp.io/servers/albertbalestrini-power-strip-security/api)
- npm · `power-strip-security-mcp`: 62/100, [markdown](https://verifymcp.io/servers/albertbalestrini-power-strip-security/power-strip-security-mcp.md), [page](https://verifymcp.io/servers/albertbalestrini-power-strip-security/power-strip-security-mcp)

## Channel facts

- Endpoint: `https://api.powerstripsecurity.workers.dev/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.2.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 64/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 989 tokens (~247/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 17/100
  - Stability observed for 5 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the Power Strip Security MCP server?

Power Strip Security is a hosted endpoint at https://api.powerstripsecurity.workers.dev/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http albertbalestrini-power-strip-security 'https://api.powerstripsecurity.workers.dev/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "albertbalestrini-power-strip-security": {
      "url": "https://api.powerstripsecurity.workers.dev/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "albertbalestrini-power-strip-security": {
      "type": "http",
      "url": "https://api.powerstripsecurity.workers.dev/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.albertbalestrini-power-strip-security]
url = "https://api.powerstripsecurity.workers.dev/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "albertbalestrini-power-strip-security": {
      "type": "remote",
      "url": "https://api.powerstripsecurity.workers.dev/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add albertbalestrini-power-strip-security --url 'https://api.powerstripsecurity.workers.dev/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  albertbalestrini-power-strip-security:
    url: "https://api.powerstripsecurity.workers.dev/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "albertbalestrini-power-strip-security": {
      "Transport": "http",
      "Url": "https://api.powerstripsecurity.workers.dev/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add albertbalestrini-power-strip-security -t streamable-http -u 'https://api.powerstripsecurity.workers.dev/mcp'
```

### Other

```json
{
  "mcpServers": {
    "albertbalestrini-power-strip-security": {
      "type": "http",
      "url": "https://api.powerstripsecurity.workers.dev/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-04 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 66, +1)

- [security] The server rewrote its instructions, which are the text every model session reads

### 2026-11-01 (score 65, 0)

- [security] Tool “audit_agent_skill” rewrote its description, which is the text the model reads
- [security] Tool “audit_mcp_server” rewrote its description, which is the text the model reads
- [security] Tool “check_prompt_injection” rewrote its description, which is the text the model reads
- [security] Tool “read_url” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 152 → 242
- [functional improvement] Tool coverage: 92% → 100%
- [functional improvement] Stability: unverified → 0.03
- [functional] Schema quality: good → excellent
- [cosmetic] “audit_agent_skill” reworded the description of “files”
- [cosmetic] “audit_agent_skill” reworded the description of “pinned”
- [cosmetic] “audit_agent_skill” reworded the description of “url”
- [cosmetic] “audit_mcp_server” reworded the description of “instructions”
- [cosmetic] “audit_mcp_server” reworded the description of “pinned”
- [cosmetic] “audit_mcp_server” reworded the description of “tools”
- [cosmetic] “audit_mcp_server” reworded the description of “url”
- [cosmetic] “check_prompt_injection” reworded the description of “content”
- [cosmetic] “check_prompt_injection” reworded the description of “format”
- [cosmetic] “check_prompt_injection” reworded the description of “return_text”
- [cosmetic] “check_prompt_injection” reworded the description of “url”
- [cosmetic] “read_url” reworded the description of “format”
- [cosmetic] “read_url” reworded the description of “url”

### 2026-10-31 (score 65)

First indexed and scored.

## MCP tools (4)

### `read_url` (~174 tokens)

Read a web page or PDF safely

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.

Input parameters:

- `format` (string): Output format of content: markdown (default) keeps links and headings; text is plain text without links
- `url` (string, required): Public http(s) URL of an HTML page, text file or PDF (up to 5 redirects)

### `check_prompt_injection` (~231 tokens)

Scan content for prompt injection

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.

Input parameters:

- `content` (string, required): The HTML or text to scan (max 256 KB)
- `format` (string): How to parse content: html (default) also strips hidden elements, comments and styles; use text for plain text such as an email body
- `return_text` (boolean): Include clean_text and wrapped_text (default true); false returns only the report, which is smaller
- `url` (string): Where the content came from (optional); used to resolve relative links in HTML

### `audit_mcp_server` (~214 tokens)

Audit an MCP server for tool poisoning

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.

Input parameters:

- `instructions` (string): Only with tools: the server's instructions from its initialize result
- `pinned` (object): Optional map of tool name to the fingerprint returned by a previous audit; any change is reported as tool-changed (high)
- `tools` (array): Instead of url: the tools array of a tools/list result, pasted as is
- `url` (string): Streamable HTTP endpoint of a public MCP server. Omit when pasting tools

### `audit_agent_skill` (~254 tokens)

Audit an agent skill or AGENTS.md

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.

Input parameters:

- `files` (array): The skill files with their relative paths, e.g. [{path: 'SKILL.md', content: '...'}, {path: 'scripts/setup.sh', content: '...'}] (max 50 files, 256 KB in total). Omit when using url
- `pinned` (object): Optional map of file path to the fingerprint returned by a previous audit; changed files are reported
- `url` (string): Instead of files: public URL of one raw text file, e.g. a SKILL.md on raw.githubusercontent.com (github.com/.../blob/... links are converted)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/albertbalestrini-power-strip-security/api#diagnostics

## Score history

- 2026-11-05: 67
- 2026-11-04: 67
- 2026-11-03: 66
- 2026-11-02: 66
- 2026-11-01: 65
- 2026-10-31: 65

## Common questions

### What is the Power Strip Security MCP server?

Power Strip Security is an MCP server listed in the public MCP registry as io.github.AlbertBalestrini/power-strip-security. Prompt-injection shield for agents: read pages, scan content, audit MCP servers and skills. x402. This page covers its hosted endpoint (https://api.powerstripsecurity.workers.dev/mcp).

### Is the Power Strip Security MCP server safe to use?

Power Strip Security scores 67 out of 100 on VerifyMCP. 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 Power Strip Security MCP server expose?

Power Strip Security exposes 4 tools: read_url, check_prompt_injection, audit_mcp_server, audit_agent_skill. Their descriptions and schemas cost roughly 873 tokens of context every time the server is loaded.

### Does the Power Strip Security MCP server require authentication?

No. We connected to Power Strip Security without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Power Strip Security MCP server still maintained?

Power Strip Security 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.

## Links

- Remote endpoint: https://api.powerstripsecurity.workers.dev/mcp
- Website: https://api.powerstripsecurity.workers.dev/
- Changelog RSS feed: https://verifymcp.io/servers/albertbalestrini-power-strip-security/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/albertbalestrini-power-strip-security/api.json
- HTML version of this page: https://verifymcp.io/servers/albertbalestrini-power-strip-security/api