Loomal

agent-immune

MCP server by github.com/denial-web/agent-immune

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

0 starspypi: agent-immune

About agent-immune

agent-immune is an MCP (Model Context Protocol) server published by denial-web in the official MCP registry, listed under Security on Loomal. AI agent security: prompt injection detection, semantic memory, output scanning, prompt hardening

It ships as a Python package on PyPI (agent-immune), so any MCP client that can launch a local process can run it.

Development happens in the open at github.com/denial-web/agent-immune.

Use agent-immune with your agent

Claude Code · one command
claude mcp add agent-immune -- uvx agent-immune
Claude Desktop, Cursor & other MCP clients · config
{
  "mcpServers": {
    "agent-immune": {
      "command": "uvx",
      "args": [
        "agent-immune"
      ]
    }
  }
}
pypiagent-immune

Frequently asked questions

What is agent-immune?
agent-immune is an MCP (Model Context Protocol) server by denial-web in the Security category. AI agent security: prompt injection detection, semantic memory, output scanning, prompt hardening
How do I connect agent-immune to Claude, Cursor, or another MCP client?
Install agent-immune from its pypi package (agent-immune) and register it under "mcpServers" in your client's MCP configuration — for example claude_desktop_config.json or Cursor's mcp.json — then restart the client.
Is agent-immune open source?
Yes — the source code is public at github.com/denial-web/agent-immune.
Can AI agents pay to use agent-immune?
Not yet through Loomal — agent-immune 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.

Listing data from the official MCP registry and GitHub, refreshed periodically. Not affiliated with the maintainer unless claimed. Maintain agent-immune? Claim this listing free by verifying GitHub ownership, or contact us.