BadC-mpany/lilith-zero
⚸ Lilith Zero - Security Middleware for MCP tool calls written in Rust.
This tool helps security professionals and developers ensure that AI agents, especially those using Large Language Models (LLMs), do not perform unauthorized actions like leaking sensitive data or calling restricted tools. It acts as a security checkpoint between your AI agent and the external tools it tries to use, enforcing strict rules. You provide a set of security policies, and it either allows or blocks the agent's tool calls and data access in real-time.
Use this if you are developing or deploying AI agents and need a robust, deterministic way to prevent data exfiltration, unauthorized tool usage, and maintain strict access control for your agent's interactions.
Not ideal if you are looking for a general-purpose firewall or network security solution, as this tool is specifically designed for securing interactions within AI agent systems.
Stars
14
Forks
1
Language
Rust
License
Apache-2.0
Category
Last pushed
Mar 13, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/mcp/BadC-mpany/lilith-zero"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Higher-rated alternatives
toolsdk-ai/toolsdk-mcp-registry
MCPSDK.dev(ToolSDK.ai)'s Awesome MCP Servers and Packages Registry and Database with Structured...
Dicklesworthstone/mcp_agent_mail
Asynchronous coordination layer for AI coding agents: identities, inboxes, searchable threads,...
ShunsukeHayashi/context_engineering_MCP
Context Engineering MCP — Hierarchical YAML context extraction and multi-agent orchestration framework
LSTM-Kirigaya/openmcp-client
All in one vscode plugin for mcp developer
RapierCraft/Perplexity-Comet-MCP
MCP server connecting Claude Code to Perplexity Comet browser. Autonomous web browsing, agentic...