injection-detector

About injection-detector

Use injection-detector with your agent

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

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

Frequently asked questions

What is injection-detector?

injection-detector is an MCP (Model Context Protocol) server by viridis-security in the Autonomous Agents category. Formally-verified injection/exfiltration detector for AI agents (MCP-02).

How do I connect injection-detector to Claude, Cursor, or another MCP client?

injection-detector is a remote MCP server — add its endpoint (https://mcp.viridis-security.com/mcp) to your client's MCP configuration (for example with "claude mcp add", or under "mcpServers" in Cursor's mcp.json) and restart the client.

Is injection-detector open source?

Yes — the source code is public at github.com/viridis-security/mcp-services-sdk.

Can AI agents pay to use injection-detector?

Not yet through Loomal — injection-detector is listed as a free directory entry. If its maintainer verifies ownership, they can set per-call USDC pricing that agents pay over x402, with settlement on Base.