loading…
Search for a command to run...
loading…
Side-by-side comparison of two Model Context Protocol servers. Pick the right one for Claude Desktop, Claude Code, or Cursor.
Full-stack security for AI agents — static analysis + MCP runtime interception. 31 rules detect prompt injection, data exfiltration, backdoors, tool poisoning,
A very streamlined mcp client that supports calling and monitoring stdio/sse/streamableHttp, and can also view request responses through the /logs page. It also
| Feature | AgentShield | llm-analysis-assistant |
|---|---|---|
| Pricing | Free | Free |
| Installs | — | — |
| Rating | — | — |
| Verified | — | |
| Hosted | — | — |
| Tools | — | — |
| Category | ai | ai |
| Author | elliotllliu | xuzexin-hz |
| Repo | elliotllliu/agent-shield | xuzexin-hz/llm-analysis-assistant |
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.
A very streamlined mcp client that supports calling and monitoring stdio/sse/streamableHttp, and can also view request responses through the /logs page. It also supports monitoring and simulation of ollama/openai interface.
Looking for something else? Browse all MCPs or check trending this week.