MCP server

Agentglass Official

net.agentglass/agentglass

Checked 26 Oct 2026, 08:29 UTC · Connected to it and listed its tools

Scan any public URL for hidden instructions aimed at AI agents (prompt injection). Free, no auth.

Website

At a glance

Type

MCP server

Publisher

agentglass.net (verified by the MCP Registry)

Status

Working at last check

Tools

1

Token cost

About 200 tokens per request

Sets up in

Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok

Last checked

26 Oct 2026, 08:29 UTC

Connect it to your agent

Add to CursorAdd to VS CodeVS Code Insiders

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

claude mcp add --transport http agentglass https://agentglass.net/mcp

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.agentglass]
url = "https://agentglass.net/mcp"

Gemini CLI

{"mcpServers":{"agentglass":{"httpUrl":"https://agentglass.net/mcp"}}}

Cursor

{"mcpServers":{"agentglass":{"url":"https://agentglass.net/mcp"}}}

VS Code

{"servers":{"agentglass":{"type":"http","url":"https://agentglass.net/mcp"}}}

Antigravity

agy mcp add agentglass https://agentglass.net/mcp

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"agentglass","server_url":"https://agentglass.net/mcp","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"agentglass","server_url":"https://agentglass.net/mcp"}

Tools

• scan_job_page ~200 tokens
  Scan a public URL, typically a job posting or application page, for hidden text, HTML comments, metadata and script content that try to instruct an AI agent (prompt injection). Returns a risk level (clean, notice, suspicious, high), a short verdict and the evidence, so the agent can decide whether t

Related MCP servers

• MYCELIX
  Free, no-key, read-only MCP endpoint verification and diagnostics.
• Prompt Injection Scanner
  Check text before your agent reads it: hidden instructions, invisible text and links that leak data.
• Cloakcheck
  Scan a page for hidden prompt-injection payloads targeting AI agents.
• Agent Utils (x402)
  Pay-per-call US public data for agents: recalls, weather, climate, SEC filings. x402 USDC on Base.
• ScorpTech x402 API
  112 x402 pay-per-call tools: web data, security/OSINT, SEC and public data, Solana/EVM lookups
• Preflight
  Scans an MCP server for security gaps before your agent connects. Free tier, no signup.
• Tech Risk
  MCP security scanner: tool-poisoning & prompt-injection audit (OWASP LLM01/08) + Base data
• AgentAegis
  Pay-per-call cybersecurity for AI agents: vuln scans, threat intel, compliance, code security.

Badge for your README

[![AptLynx](https://aptlynx.net/badge/net.agentglass/agentglass.svg)](https://aptlynx.net/servers/net.agentglass/agentglass)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents