Agentglass

net.agentglassPublished by agentglass.netOfficial publisherv0.1.0Updated Oct 27, 2026

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

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingSecurity & Monitoring

Overview

AI-generated overview

Remote MCP server that scans a public URL, such as a job posting, for hidden text or scripts trying to prompt-inject an AI agent.

What you can do
  • Scan a public URL for hidden text, HTML comments, metadata and script content that try to instruct an AI agent
  • Get back a risk level (clean, notice, suspicious, high), a short verdict and the supporting evidence
  • Use the verdict to decide whether a page is safe for the agent to read or act on
When to use it
Useful when an assistant is about to read or act on untrusted public web pages, especially job postings and application pages that may contain instructions aimed at agents. It gives a quick risk signal before the agent trusts page content.
Requirements
A remote MCP endpoint at agentglass.net over streamable HTTP; no authentication, API keys or environment variables are declared.
Before you install
The scan is a heuristic risk signal, not a guarantee: a clean result does not prove a page is safe, and the agent still decides what to do with the content. The URL you submit is sent to a third-party service.

Installation

In SourceWeft

  1. Open Agentglass in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/net.agentglass%2Fagentglass/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

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

Tools

1

scan_job_page

Scan a page for hidden AI instructions

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 to continue or pause for human review.

ParametersurlrequiredtimeoutMs

Version history

1
  1. v0.1.0LatestSep 17, 2026

Score

83% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.