Imperium MCP Security — Prompt-Injection, Jailbreak & Tool Poisoning Firewall
by mcp-security.agentdiet.dev in Security & trust
Real-time MCP & A2A prompt-injection, jailbreak, and tool-schema poisoning firewall for AI agents.
https://mcp-security.agentdiet.dev/mcp- Tools
- 2
- open to any client
- Uptime
- 100%
- last 30 days
- Response time
- 361 ms
- 362 ms slowest 5%
- Last check
- Passed
- 2 h ago, next in 4 h
Reliability
Status and outage history · Atom feed · Watch with other listings
How to connect
Add it to any MCP client that supports remote servers.
{
"mcpServers": {
"imperium-mcp-security-prompt-injection-jailbreak-tool-poison": {
"type": "http",
"url": "https://mcp-security.agentdiet.dev/mcp"
}
}
}2 tools
- scan_prompt_injection
Scans untrusted web pages, emails, MCP responses, or A2A payloads for hidden prompt injections and returns sanitized text. WHEN TO USE: Call `scan_prompt_injection` when your task requires deterministic `prompt-guard` analysis for `text`; use `get_agent_wallet_status` to check…
- get_agent_wallet_status
Inspect an agent's account ledger: remaining free trial calls (out of 5), prepaid USD balance, cumulative spend, total API calls, and total LLM tokens saved. WHEN TO USE: Call before a batch of paid tool executions or after completing a Stripe or USDC top-up to confirm your…
Security scan
No findings
We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.
Recent checks
| When | Result | HTTP | Time |
|---|---|---|---|
| 2 h ago | Passed | 200 | 361 ms |
| 11 h ago | Passed | 200 | 362 ms |
| 22 h ago | Passed | 200 | 328 ms |