A
licenseNot graded
qualityD
maintenanceAutomated red-teaming and reliability-auditing for AI agents, exposed as an MCP server. It attacks and scores agents for prompt injection, tool misuse, exfiltration, and unreliable behavior.
2
MIT
canarymcp
by sheikhMashuk
Related Servers
Alternatives to canarymcp
No user-submitted related servers found.
Related Servers
- AlicenseBqualityDmaintenanceEnables deterministic security testing of AI agents that use tools by serving synthetic MCP environments with poisoned data, fake secrets, and privileged actions. Records agent tool calls and evaluates security invariants (e.g., canary leaks, forbidden access, approval binding) without an LLM judge or real systems.8MIT
- AlicenseAqualityCmaintenanceAn intentionally vulnerable MCP server for security training, enabling users to practice attacking and defending AI agents through realistic scenarios.2868MIT
- FlicenseNot gradedqualityDmaintenanceAn educational project that deliberately implements vulnerable MCP servers to demonstrate various security risks like prompt injection, tool poisoning, and code execution for training security researchers and AI safety professionals.1,364-
- AlicenseNot gradedqualityBmaintenanceEnables security testing of MCP-speaking agents by serving as a malicious MCP server that plants canaries and catches evidence of tool poisoning, exfiltration, and other hijack techniques, then reports resilience scores.2MIT
- AlicenseBqualityCmaintenanceEnables AI agents to defend against prompt injection by exposing decoy tools and transparently proxying real MCP servers to block injected calls.11MIT
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo recent community issues