MCP serverio.github.agentgate-builder/x402-prompt-injection-scan
Prompt-injection scanner for agents: risk score, categories and spans for text, pages, MCP tools
Overview
Score?
UNRATED 0.565
of what a free look can see, on 18 looks
Looks
19
last 3 hr ago
Tools
3
changed 25 days ago
More info
URL
injectscan.agentgate.workers.dev/mcp
streamable-http
Says it is
injectscan 0.1.4
protocol 2025-06-18
In the record since
27 days ago
Among servers32,723 with a card
0median 0.547 · this server 0.565 · highest on record 0.8351
Toolsfrom sha256:5d846c50cc…97347b · +2 −0 25 days ago
| Tool | Schema |
|---|---|
| scan_text Scans untrusted text for prompt injection before your agent reads or acts on it: web page text, emails, documents, tool results or another agent's message. Flags instruction overri |
input · no output |
| scan_tools added Checks MCP / function-calling tool definitions for tool poisoning (hidden instructions, data-exfiltration requests, hijack attempts in names, descriptions and schemas) before your |
input · no output |
| scan_url added Fetches a public web page and scans its visible text plus hidden HTML (comments, hidden elements, alt/aria/meta text) for prompt injection, before your agent browses or summarizes |
input · no output |
Verify it yourself
npx teppi-check https://injectscan.agentgate.workers.dev/mcpcurl -s https://api.teppi.xyz/v1/trust/mcp/mcs_01M5H30SNJWANSQXXY5SBSJK9B