AgentShield
Rank #12,888glama/elliotllliu/agent-shield
Full-stack security for AI agents — static analysis + MCP runtime interception. 31 rules detect prompt injection, data exfiltration, backdoors, tool poisoning, and cross-file attack chains. Includes MCP proxy for real-time blocking, Python AST taint tracking, multi-language injection detection (8 languages), and AI-powered deep analysis. Free, offline, zero-config.
AgentShield is a Model Context Protocol (MCP) server published by elliotllliu. It ranks #12,888 of 76,851 servers tracked on MCP Toplist, and its repository has 15 GitHub stars. AgentShield is listed on Glama, with 2 release tags tracked from its GitHub repository. It was first listed on Mar 13, 2026 and most recently updated on Mar 15, 2026.
Ranks ahead of 63,963 of 76,851 servers on MCP Toplist.
Listed on 1 registry
elliotllliu
GitHub releases (2)
No registry surfaces explicit version metadata for this server. The list below shows release tags from the linked GitHub repository.
| Version | Published |
|---|---|
| v0.14.0 | Mar 15, 2026 |
| v0.9.0 | Mar 13, 2026 |
Frequently asked questions
- Who maintains AgentShield?
- AgentShield is maintained by elliotllliu, which publishes 1 MCP server (2 total versions) tracked on MCP Toplist.
- Is AgentShield listed on the Official MCP Registry?
- AgentShield is not on the Official MCP Registry. It is listed on Glama.
- How many versions does AgentShield have?
- No registry surfaces explicit version metadata for AgentShield; MCP Toplist tracks 2 release tags from its GitHub repository, most recently published on Mar 15, 2026.
- Where can I find the source code for AgentShield?
- The source code for AgentShield is hosted at github.com/elliotllliu/agent-shield.