mcpbeat

Injection Detector MCP Server

io.github.viridis-security/injection-detector
answering

Injection Detector is answering right now. Last checked 13 min ago. It exposes 2 tools. Last commit 30 May 2026.

Formally-verified injection/exfiltration detector for AI agents (MCP-02).

Uptime history 40 hours of history
40 hours agonow
100.0%
Uptime 24h
91 of 91 checks
2
Tools
read from the server
417 ms
Response time
average over 24h
0
Stars
last commit 30 May 2026

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 13 min ago.

run in your terminal
claude mcp add injection-detector --transport http https://mcp.viridis-security.com/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "injection-detector": {
      "url": "https://mcp.viridis-security.com/mcp"
    }
  }
}
~/.codex/config.toml
[mcp_servers.injection-detector]
url = "https://mcp.viridis-security.com/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "injection-detector": {
      "url": "https://mcp.viridis-security.com/mcp"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "injection-detector": {
      "url": "https://mcp.viridis-security.com/mcp"
    }
  }
}

Available tools 2

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

detect
detect_injection
Screen untrusted input for prompt/tool injection, exfiltration, and obfuscation before an agent consumes it. Returns a verdict (clean|suspicious|attack), probability, bits-at-risk (upper bound on adversarial capture per the Adversarial Landauer bound), matched canon patterns, and a recommended action (allow|sanitize|reject|escalate). Backed by Aristotle-verified theorems T-IB-02/T-IB-06/T-IB-01.
detect_trace_tool_policy
Analyze an agent trace for the Gray Swan Wave 16 class: untrusted retrieved/tool output causing a tool call outside the user-declared per-turn allowlist. Returns trace counts, unauthorized tool-call evidence, canon mapping VC-AI-TOOL-0001, and claim-boundary guardrails. Backed by T-IB-25/T-IB-29/T-IB-36.

Endpoints

URLTransportStateLatencyChecked
https://mcp.viridis-security.com/mcp streamable-http answering 427 ms 13 min ago

Injection Detector — questions

Answers built from our own checks of this server.

What can Injection Detector do?
It exposes 2 tools, read directly from the server on our last check. Among them: detect_injection, detect_trace_tool_policy. 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 Injection Detector 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 417 ms. The bar chart above shows every period we have measured.
How do I connect Injection Detector?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Injection Detector need an API key?
No. Injection Detector completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 2 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Injection Detector?
It answers our handshake in 417 ms on average, which is faster than 31% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.
Is Injection Detector open source?
Yes — it is published under the Apache-2.0 licence, written in Python and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.