io.github.viridis-security/injection-detector
up checked
Unclaimed · Unverified
Agent searches it appeared in, last 30 days: 0. Run this server? Claim the listing: verified label, uptime alerts and analytics.
Publisher-provided description
Formally-verified injection/exfiltration detector for AI agents (MCP-02).
Summary by lookupd
Screens untrusted input and agent traces for prompt injection, exfiltration, and out-of-policy tool calls before an agent acts on them.
Install
Claude Code, remote (streamable-http)
claude mcp add --transport http injection-detector https://mcp.viridis-security.com/mcp
Codex, remote (streamable-http)
codex mcp add injection-detector --url https://mcp.viridis-security.com/mcp
Cursor, remote (streamable-http) → .cursor/mcp.json
{
"mcpServers": {
"injection-detector": {
"url": "https://mcp.viridis-security.com/mcp"
}
}
}Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.
Tools (2 tools)
Publisher-provided text
detect_injectionScreen untrusted input for prompt/tool injection, exfiltration, and obfuscation before an agent consumes it. Returns a verdict (clean|suspicious|attack), probabdetect_trace_tool_policyAnalyze 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. Return
Details
- Version: 0.1.0
- Transports: streamable-http
- Uptime (7 days): 100%
- Median latency: 214 ms
- First indexed:
- Last seen in registry:
- Repository: https://github.com/viridis-security/mcp-services-sdk
Badge for your README
Shows this live status and links here; updates hourly.
[](https://lookupd.com/servers/io.github.viridis-security/injection-detector)
- 62071 servers
- Last crawl: 2026-11-11T16:39:06.253Z
- API base:
https://api.lookupd.com - MCP URL:
https://api.lookupd.com/mcp