Power Strip Security
Server Details
Prompt-injection shield for agents: read pages, scan content, audit MCP servers and skills. x402.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 4 tools
Each tool targets a clearly distinct input type: agent skills/instruction files, MCP servers, content already in hand, and URLs to fetch. The descriptions explicitly cross-reference each other to route ambiguous cases, so an agent can reliably select the right tool.
All names are snake_case and verb-led, with predictable action+target structure: audit_agent_skill, audit_mcp_server, check_prompt_injection, read_url. The two audit tools share a prefix appropriately because they share a purpose.
Four tools are well-scoped for a narrow security-auditing service, covering skills, MCP servers, existing content, and URL fetching without redundancy. Each tool has a distinct role and none feels like filler.
The surface covers the main lifecycle: pre-load skill inspection, pre-connect MCP inspection, prompt-injection scanning for existing text, and safe URL fetching with injection reporting. Minor gaps exist around batch/file handling and validating returned fingerprints, but core workflows are covered.
Publisher details
- Operator
- Power Strip Security · Publisher source
- Operator website
- https://api.powerstripsecurity.workers.dev/
- Vendor relationship
- First-party
- Documentation
- https://api.powerstripsecurity.workers.dev/llms.txt
- Trust center
- Not available
- Restrictions
- Paid per call with x402 (USDC on Base mainnet), no account or API key. The first 10 calls per wallet are free; prepaid credit packs are also available. · Publisher source
Available Tools
4 toolsaudit_agent_skillAudit an agent skill or AGENTS.mdARead-onlyInspect
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.
Inputs: url, files, pinned.
audit_mcp_serverAudit an MCP server for tool poisoningARead-onlyInspect
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.
Inputs: url, tools, pinned, instructions.
check_prompt_injectionScan content for prompt injectionARead-onlyInspect
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.
Inputs: content (required), url, format, return_text.
read_urlRead a web page or PDF safelyARead-onlyInspect
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.
Inputs: url (required), format.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Safety tools for AI agents: safe page reader, prompt-injection, secrets, PII and MCP server scans
Security scanner for AI agents and MCP servers: injection, jailbreak, tool abuse.
Security firewall for AI agents — scans MCP calls for injection, secrets, and risks.
Agent security pre-checks: prompt-injection scan, MCP tool-poisoning scan, x402 endpoint check.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceProvides a security scanner for AI agent skills and MCP servers, detecting threats like prompt injection, identity hijacking, and memory poisoning.96 npm2MIT
- AlicenseNot gradedqualityBmaintenanceMCP security scanner for AI agents - detects prompt injection, secrets, PII, and vets MCP servers before installation1Apache 2.0
- AlicenseNot gradedqualityCmaintenanceMCP server that provides tools to scan text and URLs for prompt injection attacks, protecting AI agents from adversarial inputs.1MIT
- AlicenseNot gradedqualityDmaintenanceAudit any MCP server for tool-poisoning, prompt-injection, and data-exfiltration risk before connecting an agent.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.