Agent 运行时全栈拦截: allow/deny tool calls, Ed25519 receipts, blocks RCE, theft, SSRF, injection. stdio.
Cross-referenced across 55 tracked directories
#17632
Popularity Rank
2 / 55
Listed In
Emerging
Adoption Stage
9/4/2026
Created
2
GitHub Stars
11/1/2026
Last Commit
Recently added to the ecosystem
Cross-Posting Opportunities
Could also be listed in these directories:
Score: 96/100
0 dependency vulnerabilities found
GitHub Actions
13 security recon tools for AI agents — DNS, SSL, HTTP, email, ports, ASN. Health Score 0-100.
rudraneel93
Security, cost, and health audit for MCP infrastructure
ThreatCluster
MCP server for the ThreatCluster threat-intelligence API: incident clusters, entity profiles, CVEs and ransomware leak-site victims as tools for Claude, Cursor, VS Code and any MCP client
...moreChristophEnglisch
MCP server implementation for Keycloak user management. Enables AI-powered administration of Keycloak users and realms through the Model Context Protocol (MCP). Seamlessly integrates with Claude Desktop and other MCP clients for automated user operations.
...more