Agentglass is answering right now. Last checked 14 min ago. It exposes 1 tools.
Scan any public URL for hidden instructions aimed at AI agents (prompt injection). Free, no auth.
Nothing serious here today
Today is the operative word: we check Agentglass every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 14 min ago.
claude mcp add agentglass --transport http https://agentglass.net/mcp{
"mcpServers": {
"agentglass": {
"url": "https://agentglass.net/mcp"
}
}
}[mcp_servers.agentglass]
url = "https://agentglass.net/mcp"{
"mcpServers": {
"agentglass": {
"url": "https://agentglass.net/mcp"
}
}
}{
"mcpServers": {
"agentglass": {
"url": "https://agentglass.net/mcp"
}
}
}Available tools 1
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
scan_job_page
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://agentglass.net/mcp | streamable-http | answering | 444 ms | 14 min ago |
Alternatives to Agentglass
same job, measured the same wayScan a page for hidden prompt-injection payloads targeting AI agents.
Prompt-injection firewall for AI agents — scan untrusted text before LLM calls.
HSM-backed vault secrets for AI agents (JIT fetch) plus prompt-injection and threat scanning.
Operating contracts for AI agents. Structured instructions compiled into system prompts.
Email safety for AI agents: scan inbound for prompt-injection/phishing + outbound for secret leaks.
Scan prompts, tool definitions and model output for injection, and guard agent tool calls.
Scan AI agents for tool-calling vulnerabilities: prompt leaks, hijacking, injections, and more.
Scan prompts for injection attacks, redact PII, and audit LLM SDK usage from any MCP client
Agentglass — questions
Answers built from our own checks of this server.