A

Agent Immune

MCP server · by denial-web

AI Agents Python v0.2.2

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

View source ↗ More servers

Install

Run one of the commands below, then add the client config underneath.

Pythonuvx agent-immune

Client configuration

Paste into Claude Desktop, Cursor (mcp.json), VS Code or any MCP client, then restart the client.

mcpServers{
  "mcpServers": {
    "agent-immune": {
      "command": "uvx",
      "args": [
        "agent-immune"
      ]
    }
  }
}

About this server

Agent Immune is listed in the AI Agents category of the MCPNav directory. It is distributed as Python and can be loaded by any client that speaks the Model Context Protocol.

Typical uses include giving your assistant scoped access to the corresponding service so it can answer questions and take actions with real data instead of guessing. Always review what a server can access before you enable it — see our MCP security guide.

Frequently asked questions

What is the Agent Immune MCP server?

Agent Immune is an MCP server by denial-web. AI agent security: prompt injection detection, semantic memory, output scanning, prompt hardening

How do I install Agent Immune?

Install it with: uvx agent-immune. Then add the JSON config to your client's MCP settings and restart the client.

Is Agent Immune free to use?

The MCP server itself is free to install. The source is public on https://github.com/denial-web/agent-immune. Any third-party API it calls (such as a search or maps API) may require its own key and billing.

Which clients support Agent Immune?

Any MCP-compatible client can use it, including Claude Desktop, Cursor, VS Code, Windsurf and custom agents.