---
id: 20260929-T0-11
title: "Cartograph：面向AI Agent的联邦工具发现与操作者认证检索"
title_en: "Cartograph: Federated Tool Discovery with Operator-Attested Retrieval for AI Agents"
url: https://ai.daily.yangsir.net/daily/20260929-T0-11
issue_date: 2026-09-29
publish_date: 2026-09-28T04:00:00.000Z
category: research
source_name: "arXiv cs.CL (NLP)"
source_url: https://arxiv.org/abs/2609.30293
---

# Cartograph：面向AI Agent的联邦工具发现与操作者认证检索

arXiv新论文提出Cartograph，一个联邦式MCP代理，解决AI Agent通过Model Context Protocol发现和调用工具时，连接目录增长导致加载全部工具定义成本过高的问题。Cartograph将Agent可见的工具发现从O(n)复杂度转变为更高效的检索方式，并引入操作者认证（operator-attested）机制以保证检索结果的可信度。这对构建大规模、多工具连接的Agent系统具有实用价值，可降低上下文开销并提升工具调用的准确性和安全性。

## English Version

**Cartograph: Federated Tool Discovery with Operator-Attested Retrieval for AI Agents**

A new arXiv paper introduces Cartograph, a federated MCP proxy that addresses the high cost of loading all tool definitions as connected catalogs grow when AI agents discover and call tools via the Model Context Protocol. Cartograph changes agent-visible tool discovery from O(n) to a more efficient retrieval approach and adds operator-attested retrieval to ensure trustworthiness. It has practical value for building large-scale, multi-tool agent systems, reducing context overhead and improving tool-call accuracy and security.

---

**来源**：[arXiv cs.CL (NLP)](https://arxiv.org/abs/2609.30293)

**详情页**：https://ai.daily.yangsir.net/daily/20260929-T0-11

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*