TL;DR
Agent Immune is a Model Context Protocol (MCP) server. AI agent security: prompt injection detection, semantic memory, output scanning, prompt hardening Install with: uvx agent-immune. Source: https://github.com/denial-web/agent-immune. Compatible with MCP clients such as Claude Desktop, Cursor, Cline and Windsurf.
Agent Immune
AI agent security: prompt injection detection, semantic memory, output scanning, prompt hardening
Install Command
uvx agent-immuneFrequently Asked Questions
Agent Immune is a Model Context Protocol server that AI agent security: prompt injection detection, semantic memory, output scanning, prompt hardening
You can install it by running the install command: `uvx agent-immune`. It then becomes available to any MCP-compatible client such as Claude, Cursor, Cline, Windsurf.
The Agent Immune MCP Server is compatible with any client that speaks the Model Context Protocol — including Claude, Cursor, Cline, Windsurf.
Check the project license on its repository before use.
Reviews
0 reviews· 0.0 average
No reviews yet. Be the first to share your experience.
Leave a review
Rating
Details
- Agent Rank
- 0.0
- License
- Last Updated
- Aug 12, 2026
- Languages
- Python
Client Compatibility
Speaks the Model Context Protocol — works with any compatible client.