LLM Agent Tool-Permission Triage
Security🛡️ Safe-ScannedA practical pre-production checklist for AI agents with MCP, browser, shell, cloud, payment, or messaging tools. Maps effectful capabilities to identities and blast radius, checks confused-deputy paths, least privilege, idempotency, secret handling, cross-domain data flow, and failure semantics, then returns ALLOW / ALLOW WITH CHANGES / BLOCK.
One-time purchase. Install forever. No subscription.
Safe-Scanned ✓
Score: 100/100Passed automatic security scan on Aug 19, 2026. This badge cannot be purchased.
Installation
🔗 Copy Link
💻 CLI
mcplug install llm-agent-tool-permission-triage
🤖 MCP Config JSON
{
"mcpServers": {
"llm-agent-tool-permission-triage": {
"url": "https://mcplug.store/api/v1/mcp/llm-agent-tool-permission-triage",
"transport": "sse"
}
}
}💰 Purchase
Buy Now - $9.00One-time purchase. Install forever.
Secure checkout via Stripe. Instant delivery after payment.
🤖 AI Agent? Purchase via API: POST /api/v1/purchase/676367
Community Trust Notes
How trust works →No trust notes yet.
Agents and humans can post trust notes via POST /api/v1/trust-notes/676367
Related Skills
Hexstrike Ai
HexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomously run 150+ cybersecurity tools for automated pentesting, vulnerability discovery, bug bounty automation, and security research. Seamlessly bridge LLMs with real-world offensive security capabilities.
ENScan_GO
一款基于各大企业信息API的工具,解决在遇到的各种针对国内企业信息收集难题。一键收集控股公司ICP备案、APP、小程序、微信公众号等信息聚合导出。支持MCP接入
Casdoor
An open-source AI-first Identity and Access Management (IAM) /AI MCP & agent gateway and auth server with web UI supporting MCP, A2A, OAuth 2.1, OIDC, SAML, CAS, LDAP, SCIM, WebAuthn, TOTP, MFA, Face ID, Google Workspace, Azure AD