ToolDNS: Scalable AI Tool Discovery via DNS-Based Semantic Resolution

Short summary

ToolDNS proposes retrofitting semantic AI tool discovery onto the existing DNS infrastructure, embedding functional intent and organizational trust into a hierarchical namespace. It reduces per-query search space by 95.26% while matching state-of-the-art retrieval accuracy across a benchmark of 33,688 real-world tools spanning MCP, A2A, RESTful, and Skill protocols. Its UDP-native design cuts discovery latency by orders of magnitude versus HTTP-based registries.

• •ToolDNS maps semantic tool discovery onto DNS with O(log N) name resolutions
• •Benchmark of 33,688 real-world tools across MCP, A2A, RESTful, and Skill protocols released
• •Reduces search space by 95.26% while matching SOTA retrieval accuracy with UDP-native low latency

Generated with AI, which can make mistakes.