{
  "type": "mcp-server",
  "slug": "reins-mcp-server",
  "name": "Reins MCP Server",
  "author": "amcdonnell-dot",
  "description": "Audits Claude Code standing permission grants, scores each grant's prompt-injection blast radius, and generates deny-rule guardrails — local, read-only by default, zero network egress.",
  "github_url": "https://github.com/amcdonnell-dot/reins",
  "license": "MIT",
  "tier": "contributed",
  "tags": [
    "ai-agent-security",
    "permissions",
    "claude-code",
    "prompt-injection",
    "least-privilege",
    "governance",
    "python"
  ],
  "integrations": [
    "Anthropic"
  ],
  "domains": [
    "ai-security"
  ],
  "date_added": "2026-08-05",
  "last_reviewed": "2026-08-13",
  "works_with_tenable_hexa_mcp": false,
  "transport": "stdio",
  "runtime": "python",
  "auth_method": "none",
  "compatible_clients": [
    "Claude Code",
    "Claude Desktop"
  ],
  "tools_exposed": [
    {
      "name": "reins_audit",
      "description": "Audit standing permission grants across Claude Code settings sources, classified into 12 risk categories with redacted evidence"
    },
    {
      "name": "reins_explain",
      "description": "Deep-dive on a single grant: what it permits, why it was flagged, and remediation options"
    },
    {
      "name": "reins_blast_radius",
      "description": "Rank grants by worst-case prompt-injection blast radius (credential access, exfiltration, destruction, persistence, code integrity, privilege escalation)"
    },
    {
      "name": "reins_generate_policy",
      "description": "Generate permissions.deny rules, PreToolUse hook scripts, and a managed-settings baseline from findings (dry — never writes)"
    },
    {
      "name": "reins_snapshot",
      "description": "Save the current grant set as a baseline for drift detection"
    },
    {
      "name": "reins_drift",
      "description": "Diff live grants against the saved baseline; newly added grants are fully classified and scored"
    },
    {
      "name": "reins_revoke",
      "description": "Remove selected allow rules by audit-issued rule id — confirmation-gated, timestamped backups, atomic writes, read-only sources refused"
    }
  ],
  "resources_exposed": [],
  "prompts_exposed": [],
  "repo": {
    "found": true,
    "archived": false,
    "pushed_at": "2026-08-05T14:51:57Z",
    "stars": 0,
    "forks": 0,
    "open_issues": 0,
    "owner_type": "user",
    "language": "Python",
    "checked_at": "2026-11-05T20:35:15.821Z"
  },
  "url": "https://exchange.tenable.com/mcp-servers/reins-mcp-server",
  "json_url": "https://exchange.tenable.com/api/mcp-servers/reins-mcp-server.json",
  "markdown_url": "https://exchange.tenable.com/mcp-servers/reins-mcp-server.md",
  "source_url": "https://github.com/tenable/cyberagents-exchange/blob/main/mcp-servers/reins-mcp-server.md"
}