{"version":1,"type":"story","url":"https://digestai.news/story/cartograph-reduces-ai-agent-tool-discovery-from-o-n-to-o-k","json":"https://digestai.news/story/cartograph-reduces-ai-agent-tool-discovery-from-o-n-to-o-k.json","markdown":"https://digestai.news/story/cartograph-reduces-ai-agent-tool-discovery-from-o-n-to-o-k.md","slug":"cartograph-reduces-ai-agent-tool-discovery-from-o-n-to-o-k","headline":"Cartograph reduces AI agent tool discovery from O(n) to O(k)","summary":"Cartograph is a federated Model Context Protocol (MCP) proxy that changes how AI agents find and call tools. Instead of traversing every catalog entry, the system exposes only a few proxy tools, lowering the search complexity from O(n) to O(k). The authors claim the approach is more efficient for large, distributed tool collections.\n\nThe proxy uses three mechanisms. First, operator‑attested capability cards are Ed25519‑signed descriptions generated by the deploying operator, not by the publisher. Second, Rift performs a three‑layer confusable‑cluster analysis—density clustering, query‑margin analysis, and token diagnosis—to group similar tools. Third, a two‑stage retrieval ranks servers before ranking individual tools. In a test with 22 servers and 374 tools, Cartograph exposed only three proxy tools.\n\nPerformance results show a recall@5 of 0.816 versus 0.592 for a Jaccard keyword baseline. The top‑5 discovery exchange uses 475 tokens instead of 42,450 tokens under full‑catalog accounting. Rift identified 49 confusable clusters, including four high‑risk clusters. Gateway measurements over ten trials added only 5 ms mean latency (0.8 %) compared to direct stdio MCP calls.","keyPoints":["Cartograph reduces tool discovery complexity from O(n) to O(k)","It exposes only three proxy tools in a 22‑server, 374‑tool deployment","Recall@5 improves from 0.592 to 0.816 with only 475 tokens used"],"whyItMatters":"Efficient tool discovery cuts latency and token costs for AI agents, enabling scalable integration of external services in larger deployments.","category":{"slug":"research","name":"Research","url":"https://digestai.news/category/research"},"entities":{"companies":[],"models":[],"people":[]},"firstPublishedAt":"2026-09-28T04:00:00Z","updatedAt":"2026-09-28T04:00:00Z","sourceCount":1,"hasPrimarySource":true,"sources":[{"outlet":"arXiv cs.CL","title":"Cartograph: Federated Tool Discovery with Operator-Attested Retrieval for AI Agents","url":"https://arxiv.org/abs/2609.30293","publishedAt":"2026-09-28T04:00:00Z","type":"primary","primary":true,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Cartograph reduces AI agent tool discovery from O(n) to O(k)\", 28 September 2026, https://digestai.news/story/cartograph-reduces-ai-agent-tool-discovery-from-o-n-to-o-k","publisher":"Digest AI","title":"Cartograph reduces AI agent tool discovery from O(n) to O(k)","datePublished":"2026-09-28T04:00:00Z","url":"https://digestai.news/story/cartograph-reduces-ai-agent-tool-discovery-from-o-n-to-o-k"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}