← Index

io.github.imran-siddique/agentos

io.github.imran-siddique/agentos·v1.0.1·Other
Quality Score
81
/100

Build and manage policy-compliant AI agents with safety enforcement and compliance checking

§01  Install
Claude Desktop (claude_desktop_config.json)
{
  "mcpServers": {
    "agentos": {
      "command": "npx",
      "args": [
        "-y",
        "agentos-mcp-server"
      ],
      "env": {
        "AGENTOS_POLICY_MODE": "<agentos_policy_mode>",
        "AGENTOS_LOG_LEVEL": "<agentos_log_level>"
      }
    }
  }
}
Cursor (.cursor/mcp.json)
{
  "mcpServers": {
    "agentos": {
      "command": "npx",
      "args": [
        "-y",
        "agentos-mcp-server"
      ],
      "env": {
        "AGENTOS_POLICY_MODE": "<agentos_policy_mode>",
        "AGENTOS_LOG_LEVEL": "<agentos_log_level>"
      }
    }
  }
}
Cline (cline_mcp_settings.json)
npx -y agentos-mcp-server
§02  Environment variables
AGENTOS_POLICY_MODE

Policy enforcement mode: strict (block all violations) or permissive (warn only)

AGENTOS_LOG_LEVEL

Log level: debug, info, warn, or error

§03  MCP Quality Score  ·  methodology
freshness
21
completeness
10
installability
25
documentation
15
stability
10
§04  Alternatives in Other