MCP server

Injection Detector

io.github.viridis-security/injection-detector

Checked 25 Oct 2026, 20:29 UTC · Connected to it and listed its tools

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

Source

At a glance

Type

MCP server

Publisher

viridis-security.com (verified by the MCP Registry)

Status

Working at last check

Tools

2

Token cost

About 501 tokens per request

Sets up in

Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok

Last checked

25 Oct 2026, 20:29 UTC

Connect it to your agent

Add to CursorAdd to VS CodeVS Code Insiders

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

claude mcp add --transport http injection-detector https://mcp.viridis-security.com/mcp

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.injection-detector]
url = "https://mcp.viridis-security.com/mcp"

Gemini CLI

{"mcpServers":{"injection-detector":{"httpUrl":"https://mcp.viridis-security.com/mcp"}}}

Cursor

{"mcpServers":{"injection-detector":{"url":"https://mcp.viridis-security.com/mcp"}}}

VS Code

{"servers":{"injection-detector":{"type":"http","url":"https://mcp.viridis-security.com/mcp"}}}

Antigravity

agy mcp add injection-detector https://mcp.viridis-security.com/mcp

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"injection-detector","server_url":"https://mcp.viridis-security.com/mcp","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"injection-detector","server_url":"https://mcp.viridis-security.com/mcp"}

Tools

• detect_injection ~274 tokens
  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 actio
• detect_trace_tool_policy ~227 tokens
  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-I

Browse

• GitHub tools
• Website monitoring
• GitHub and code hosting

Related MCP servers

• aaaa-nexus — Formally Verified AI Safety APIs
  Formally verified AI safety APIs. Pay-per-call via USDC (x402). 75+ endpoints, no signup.
• Agentexchange Monitor
  Check if an MCP server tool changed or hides injection patterns before you trust it.
• Prompt Injection Scanner
  Check text before your agent reads it: hidden instructions, invisible text and links that leak data.
• MYCELIX
  Free, no-key, read-only MCP endpoint verification and diagnostics.
• Verdict L402
  Ask if an action is safe before your agent runs it: injection, shell, MCP installs. Free samples.
• Skill Audit
  MCP server: static security scanner for MCP servers, agent skills & plugins. 17 attack patterns.
• Citiview Agent Market
  186 pay-per-call tools: search, LLMs, UK KYB, FRED, Census, maps, crypto. x402 USDC.
• Moltline Agent Governance
  Audit MCP configs and skill files for over-broad scope and injection risk. 6 of 8 free.

Badge for your README

[![AptLynx](https://aptlynx.net/badge/io.github.viridis-security/injection-detector.svg)](https://aptlynx.net/servers/io.github.viridis-security/injection-detector)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents