Agent Immune MCP Server

by denial-web Your server? Claim it

local only

Agent Immune runs on your own machine — the client starts it, so there is no endpoint to ping. 96 installs a week from pypi. Last commit 7 Apr 2026.

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

Installs per day peak 43 · avg 17 · -18% w/w

a month agotoday

Installs / week

pypi · agent-immune

Stars

0 open issues

7 Apr 2026

Last commit

from GitHub

Apache-2.0

License

Python

What the code does

We read the source, 5 d ago · rules 995398eba69f

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Unsafe deserialization src/agent_immune/memory/bank.py:451, [пакет] src/agent_immune/memory/bank.py:451

        payload = pickle.loads(data)  # noqa: S301

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add agent-immune -- uvx agent-immune

~/Library/Application Support/Claude/claude_desktop_config.json

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

~/.codex/config.toml

[mcp_servers.agent-immune]
command = "uvx"
args = ["agent-immune"]

.cursor/mcp.json

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

.vscode/mcp.json

{
  "servers": {
    "agent-immune": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "agent-immune"
      ]
    }
  }
}

Alternatives to Agent Immune

same job, measured the same way

GuardianShield

by sparkvibe-io

AI security layer: code scanning, PII detection, prompt injection, secrets, CVEs

84 installs/wk local only

Shellward

by jnmetacode

AI agent security: 7 MCP tools for injection detection, PII scanning, command safety, DLP.

404 installs/wk local only

Agent Security

by mdfifty50-boop

Security scanning and threat detection for AI agents

61 installs/wk local only

MCP Safeguard

by cognivators

MCP server security scanner: detects prompt injection, credential leaks, SSRF, tool poisoning.

195 installs/wk local only

AI Firewall MCP

by akhilucky

Multi-agent LLM security layer detecting prompt injection and jailbreaks.

125 installs/wk local only

Agent-Shield

by startekenterprises-ai

Security scanner for AI agents: prompt injection, leaked secrets, PII, and SSRF-risk URL detection.

answering

Sentinel Scan

by ventrova

MCP security scanner: detect tool poisoning, prompt injection & rug-pulls - 10 OWASP heuristics.

61 installs/wk local only

Agent Security Scanner MCP

by sinewaveai

Security layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities.

418 installs/wk local only

Agent Immune — questions

Answers built from our own checks of this server.

Why is there no uptime for Agent Immune?

Agent Immune runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package agent-immune was installed 96 times last week.

How do I connect Agent Immune?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls agent-immune straight from pypi; nothing to host, nothing to sign up for.

How many people use Agent Immune?

The pypi package agent-immune was installed 96 times in the last week. Week over week that is -18%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Agent Immune open source?

Yes — it is published under the Apache-2.0 licence, written in Python and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.