Imperium MCP Security — Prompt-Injection, Jailbreak & Tool Poisoning Firewall
Real-time MCP & A2A prompt-injection, jailbreak, and tool-schema poisoning firewall for AI agents.
Connect it
Settings → Connectors → Add custom connector
URL: https://mcp-security.agentdiet.dev/mcpSettings → Apps & Connectors → Advanced → Developer mode
Create connector with URL: https://mcp-security.agentdiet.dev/mcp{
"mcpServers": {
"mcp-security": {
"url": "https://mcp-security.agentdiet.dev/mcp"
}
}
}claude mcp add --transport http mcp-security https://mcp-security.agentdiet.dev/mcp{
"servers": {
"mcp-security": {
"type": "http",
"url": "https://mcp-security.agentdiet.dev/mcp"
}
}
}2 tools, pulled live
scan_prompt_injectionread-onlyScans 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 your remaining free trial quota or prepaid balance. WHEN NOT TO USE: Do not use for unrelated domains or binary media. PAR
get_agent_wallet_statusread-onlyInspect 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 balance. WHEN NOT TO USE: Do not use to process web content, execute marketplace tools, or submit payments; use the other too
Alternatives in Security
Compare →WMWHOOP — MissingMCPB
WHOOP recovery, strain, sleep and workouts in Claude via official WHOOP OAuth. Free, open source.
THThoughtspotB
MCP Server for ThoughtSpot - provides OAuth authentication and tools for querying data
SXSputnik X — AI-Agent-Native IntelligenceB
Sputnik X: 16 free MCP tools and EU Trade via authenticated REST and x402.
MAC Address LookupB
Find the organization behind a MAC address or OUI prefix in the IEEE registries. No auth, no key.
DEDecionisB
Authorize consequential AI agent actions before execution
HSHelixar SecurityB
Security tools for AI agents: scan MCP servers, validate HDP delegation chains, audit releases.