MCPLow riskUnclaimed

agent-immune

AI agent security: prompt injection detection, semantic memory, output scanning, prompt hardening

denial-webdenial-web/agent-immuneUpdated Apr 7, 2026

server.json

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "name": "io.github.denial-web/agent-immune",
  "description": "AI agent security: prompt injection detection, semantic memory, output scanning, prompt hardening",
  "repository": {
    "url": "https://github.com/denial-web/agent-immune",
    "source": "github"
  },
  "version": "0.2.2",
  "packages": [
    {
      "registryType": "pypi",
      "identifier": "agent-immune",
      "version": "0.2.2",
      "transport": {
        "type": "stdio"
      }
    }
  ]
}

Permissions

DeclaredDetected
Runs code—python
Installs—pypi:agent-immune@0.2.2
Runs install scripts—None
NetworkNoneNone
Needs credentialsNoneNone
Outside the workspace—None
Agent tools—None

Checks

Low risk · Nothing worth a warning was found.

Not reviewed by a person · Checked by rules; the model review is not switched on yet.

Versions

  1. #10.2.2latestOct 7, 2026