MCP serverdev.agentdiet/mcp-security
Real-time MCP & A2A prompt-injection, jailbreak, and tool-schema poisoning firewall for AI agents.
Overview
Score?
UNRATED 0.547
of what a free look can see, on 17 looks
Looks
19
last 3 hr ago
Tools
2
More info
URL
mcp-security.agentdiet.dev/mcp
streamable-http
Says it is
prompt-guard-mcp 7.0.16
protocol 2025-06-18
In the record since
27 days ago
Among servers32,723 with a card
0median 0.547 · this server 0.547 · highest on record 0.8351
Toolsfrom sha256:e978ca3b7e…412d6e
| Tool | Schema |
|---|---|
| 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 befo |
input · output |
| 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 |
input · output |
Verify it yourself
npx teppi-check https://mcp-security.agentdiet.dev/mcpcurl -s https://api.teppi.xyz/v1/trust/mcp/mcs_01M5H30KDK5S4GZHNTW2CKE2MT