mcpbeat Sign in

InjectScan MCP Server

by agentgate-builder Your server? Claim it
answering

InjectScan is answering right now. Last checked 10 min ago. It exposes 3 tools.

Prompt-injection scanner for agents: risk score, categories and spans for text, pages, MCP tools

The linked repository no longer exists on GitHub — it was deleted or made private.

Uptime history 5 days of history
5 days agonow
100.0%
Uptime 24h
91 of 91 checks
3
Tools
read from the server
260 ms
Response time
average over 24h
open, no key
Access
streamable-http

What changed 16

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 23 October 2026. No other catalogue keeps this.

24 Oct 3 tool descriptions were rewritten scan_text, scan_tools, scan_url
23 Oct 3 tool descriptions were rewritten7 times that day scan_text, scan_tools, scan_url
23 Oct 3 tools changed the parameters they ask for4 times that day scan_text, scan_tools, scan_url
23 Oct 2 tools appeared scan_tools, scan_url
and 5 more, back to 23 October 2026

This one has been quiet for a while

Quiet is not dead — but it is worth knowing when it wakes up, or when someone else takes it over. We watch the repository and tell you either way.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 10 min ago.

run in your terminal
claude mcp add x402-prompt-injection-scan --transport http https://injectscan.agentgate.workers.dev/mcp
Settings → Connectors → Add custom connector, then paste this address
https://injectscan.agentgate.workers.dev/mcp
~/.codex/config.toml
[mcp_servers.x402-prompt-injection-scan]
url = "https://injectscan.agentgate.workers.dev/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "x402-prompt-injection-scan": {
      "url": "https://injectscan.agentgate.workers.dev/mcp"
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "x402-prompt-injection-scan": {
      "type": "http",
      "url": "https://injectscan.agentgate.workers.dev/mcp"
    }
  }
}

Available tools 3

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

scan
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 overrides, jailbreak personas, system-prompt extraction, fake delimiters, exfiltration URLs, tool hijacking, hidden Unicode and encoded payloads (deterministic rules). Use scan_url when you only have a link (it also checks hidden HTML) and scan_tools for MCP tool definitions. Text up to 100000 characters. Free: 30 calls/day per IP shared by scan_text, scan_url and scan_tools, with full results (max 10/min; invalid input is not counted). After that the tool returns an error with the x402 pay URL ($0.003 USDC on Base, Polygon, Arbitrum One or Solana per call at https://api.youraitools.co/injectscan/v1/scan) or prepaid credits. Returns risk_score (0-100), verdict (safe | suspicious | malicious), flagged, categories[] {category, score, description}, findings[] {rule, category, start, end, text} and free_tier usage. Read-only safety signal, not a guarantee.
scan_tools
Checks MCP / function-calling tool definitions for tool poisoning (hidden instructions, data-exfiltration requests, hijack attempts in names, descriptions and schemas) before your agent installs or calls them. Use scan_text for ordinary content and scan_url for web pages. Up to 100 tools per call. Free: 30 calls/day per IP shared by scan_text, scan_url and scan_tools, with full results (max 10/min; invalid input is not counted). After that the tool returns an error with the x402 pay URL ($0.003 USDC on Base, Polygon, Arbitrum One or Solana per call at https://api.youraitools.co/injectscan/v1/scan) or prepaid credits. Returns the worst risk_score/verdict, flagged, tools_scanned, tools_flagged and tools[] {index, name, risk_score, verdict, categories, findings[] {field, rule, text}}. Read-only safety signal, not a guarantee.
scan_url
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 it. Use scan_text if you already have the content and scan_tools for MCP tool definitions. Respects robots.txt and refuses private/internal hosts. Free: 30 calls/day per IP shared by scan_text, scan_url and scan_tools, with full results (max 10/min; invalid input is not counted). After that the tool returns an error with the x402 pay URL ($0.003 USDC on Base, Polygon, Arbitrum One or Solana per call at https://api.youraitools.co/injectscan/v1/scan) or prepaid credits. Returns risk_score (0-100), verdict (safe | suspicious | malicious), flagged, categories[] {category, score, description}, findings[] with location (visible or hidden), url, finalUrl, title, hidden_html {segments_checked, flagged} and page {status, contentType}. Read-only safety signal, not a guarantee.

Endpoints

URLTransportStateLatencyChecked
https://injectscan.agentgate.workers.dev/mcp streamable-http answering 142 ms 10 min ago

Alternatives to InjectScan

same job, measured the same way
InjectScan
by youraitools

Scan text for prompt injection: risk score, verdict, matched spans. Built by Crypto Money Maker

3 tools answering
A
Agent Security Scanner
by mikehzp

Scan AI agents for tool-calling vulnerabilities: prompt leaks, hijacking, injections, and more.

106 installs/wk local only
Injectshield
by bch1212

Prompt-injection firewall for AI agents — scan untrusted text before LLM calls.

9 installs/wk local only
Shadowgate MCP
by josephibra

Security firewall for AI agents — scans MCP calls for injection, secrets, and risks.

answering
AIShield Security Scanner
by lm203688

Scans MCP servers for tool poisoning, prompt injection and supply chain risks.

52 installs/wk 10 tools local only
prompt-protection
by mughalhere

Scan prompts, tool definitions and model output for injection, and guard agent tool calls.

543 installs/wk local only
Patronus Security
by patronus

Scan text, documents, websites, and MCP metadata for prompt injection and sensitive-data risks.

answering
ToolTrust Scanner
by agentsafe-ai

Scans MCP servers for prompt injection, data exfiltration, and privilege escalation.

29 installs/wk local only

InjectScan — questions

Answers built from our own checks of this server.

What can InjectScan do?
It exposes 3 tools, read directly from the server on our last check. Among them: scan_text, scan_tools, scan_url. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is InjectScan working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 260 ms. The bar chart above shows every period we have measured.
Is InjectScan still maintained?
The linked repository no longer exists on GitHub — it was deleted or made private. We show this because it changes what you can expect: an unmaintained server may keep answering for months and then stop without warning.
How do I connect InjectScan?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does InjectScan need an API key?
No. InjectScan completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 3 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is InjectScan?
It answers our handshake in 260 ms on average, which is faster than 64% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.