cosmic-mcp

All servers

agent-immune

io.github.denial-web/agent-immune ยท version 0.2.2

Community listing. Not installed or verified by cosmic-mcp. Read the source and its permissions before you run it.

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

https://github.com/denial-web/agent-immune

Quick facts

  • Listing: Community
  • Published Apr 7, 08:00 UTC
  • Transport: stdio
  • Package: pypi agent-immune 0.2.2
  • Listed by cosmic-mcp: Nov 9, 04:25 UTC

AI and LLMs Memory and knowledge Security

Setup snippets

Generated from the registry entry. cosmic-mcp has not run or reviewed this server; values in angle brackets are yours to fill in.

Run it locally (pypi)

uvx 'agent-immune==0.2.2'

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "agent-immune": {
      "args": [
        "agent-immune==0.2.2"
      ],
      "command": "uvx"
    }
  }
}

Claude Code

claude mcp add 'agent-immune' -- uvx 'agent-immune==0.2.2'

Cursor (.cursor/mcp.json)

{
  "mcpServers": {
    "agent-immune": {
      "args": [
        "agent-immune==0.2.2"
      ],
      "command": "uvx"
    }
  }
}

VS Code (.vscode/mcp.json)

{
  "servers": {
    "agent-immune": {
      "args": [
        "agent-immune==0.2.2"
      ],
      "command": "uvx",
      "type": "stdio"
    }
  }
}

Related servers

  • Harness Verified domain
    Start Claude Code and Codex agents the person can watch, wait for them and read their answers.
  • Anki MCP Server Verified domain
    MCP server for Anki flashcards: adaptive review, notes, media, and deck management via AnkiConnect.
  • docs-mcp Verified domain
    Remote MCP server for Tandem docs, install guides, SDKs, workflows, and agent setup help.
  • spotdb Verified domain
    Ephemeral data sandbox for AI workflows with guardrails and security
  • AgentPlaybooks Verified domain
    Vendor-neutral home for portable agents: skills, MCP tools, memory, canvas, and secret proxy.
  • Achromat Machine Operational Memory Verified domain
    Recall and calibrate policy-compliant tool-call arguments before execution. Does not run the tool.