LocalFree

Agent Immune MCP server

denial-web/agent-immune

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

0 GitHub stars
Source code

Install Agent Immune in Claude Code

Claude Code
claude mcp add agent-immune -- uvx agent-immune
mcp.json (Claude Desktop, Cursor, VS Code, Windsurf)
{
  "mcpServers": {
    "agent-immune": {
      "command": "uvx",
      "args": [
        "agent-immune"
      ]
    }
  }
}

Frequently asked questions

What does the Agent Immune MCP server do?

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

Is the Agent Immune MCP server free?

Yes, most likely. Open source and no paid account or API key is mentioned in the listing. Check the provider for current pricing.

Does Agent Immune run locally or remotely?

Local. Runs on your machine (stdio). You install it with npx, uvx, Docker or from source.

How do I add Agent Immune to Claude Code?

Run: claude mcp add agent-immune -- uvx agent-immune

More knowledge, memory & rag MCP servers

View all

Agent Memory

0

kira-autonoma/agent-memory-mcp

Agent memory MCP server with provenance tracking, decay-weighted recall, and feedback loops.

LocalFree

Agent evidence

0

probityai/agent-evidence-mcp

Offline, read-only tools that verify AI claims against evidence and replay conformance vectors.

LocalFree

Agent Memory SDK

0

TheProdSDE/agent-memory-sdk

Persistent agent memory with a decision layer: replay, restore, verify, or none — explainable.

LocalFree

Acta

Kylewilson04/acta-mcp

Verifiable agent memory with signed ledger receipts — verify every write offline.

LocalFree

AgentCommons.me

0

IvGolovach/agentcommons-mcp

Public working memory for AI agents: messages, shared pages, and resumable tasks.

LocalFree

Ace Context

Dw-Dwain/Ace-Context-MCP

Local-first memory for AI chats: save context in one chat, load it in any other via MCP.

LocalFree