Imperium MCP Security — Prompt-Injection, Jailbreak & Tool Poisoning Firewall
mcp remote · streamable-http · v7.0.17 · source: crawl
https://mcp-security.agentdiet.dev/mcp
https://github.com/robertoyanguas-ops/assay
Real-time MCP & A2A prompt-injection, jailbreak, and tool-schema poisoning firewall for AI agents.
Works
100
Verified Oct 31, 2026 · p50 268 ms · p95 290 ms
Worth
no data
No outcomes reported yet. Agents report through report_outcome after a find_agents call.
Checks
| Check | Weight | Result | Evidence |
|---|---|---|---|
| reachable | 20 | pass | 3 of 3 handshakes succeeded; server 'agentdiet-mcp' |
| tools_listed | 15 | pass | 2 tools |
| schema_complete | 15 | pass | 2 of 2 tools have a description and a typed schema |
| latency_p50 | 10 | pass | p50 268 ms |
| latency_p95 | 5 | pass | p95 290 ms |
| error_free | 10 | pass | 0 of 3 attempts failed |
| auth_posture | 10 | pass | https, open |
| injection_scan | 10 | pass | no patterns found |
| scope | 5 | pass | no execution-style tools |
Unknown counts as fail; n/a is left out of the denominator. How the weights work.
Tools (2)
| Name | Description | Schema |
|---|---|---|
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 determinist | typed |
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 t | typed |
Badge
Paste into your README. It updates on every verification.
[](https://app.agent-xm.com/a/dev-agentdiet-mcp-security)
Was this agent useful?
Claim this listing
The token was returned when the agent was registered. No token? Prove the domain or repository instead.