{"slug": "google-microsoft-back-draft-ai-agent-discovery-spec", "title": "Google, Microsoft Back Draft AI Agent Discovery Spec", "summary": "Eleven companies including Google, Microsoft, GitHub, and Hugging Face published the Agentic Resource Discovery (ARD) open specification on June 17, enabling AI agents to dynamically discover and verify tools, skills, and other agents across the web. The spec, licensed under Apache 2.0, moves agent-tool coordination from pre-wired connections to runtime search, with several contributors releasing same-day implementations. ARD aims to solve scaling issues as more companies publish AI capabilities, but its immediate impact is limited to publishers of callable tools and APIs, not typical content sites.", "body_md": "Eleven companies, including Google, Microsoft, GitHub, and Hugging Face, have published Agentic Resource Discovery (ARD). The [open specification](https://developers.googleblog.com/announcing-the-agentic-resource-discovery-specification/) sets out how AI agents find and verify tools, skills, and other agents across the web.\n\nThe contributors released the draft spec on June 17, along with reference implementations from several of them. ARD is licensed under Apache 2.0 and builds on the AI Catalog data model maintained by a working group under the Linux Foundation. The full list of contributors also includes Cisco, Databricks, GoDaddy, NVIDIA, Salesforce, ServiceNow, and Snowflake.\n\n## What Does ARD Solve?\n\nThe spec sets out to solve a coordination problem. Today, an agent has to be wired to each tool, MCP server, or API it uses ahead of time. As more companies publish their own capabilities, that pre-wiring stops scaling.\n\nARD moves discovery into a search step that happens at runtime. The shift mainly affects companies that publish tools and agents, not typical content sites for now.\n\n## How ARD Works\n\nARD relies on two pieces, which the spec calls catalogs and registries.\n\nAn organization publishes a catalog, an `ai-catalog.json`\n\nfile hosted at a well-known path on its own domain, that lists the tools, MCP servers, agents, or APIs it makes available.\n\nRegistries then crawl those catalogs, index them, and answer discovery requests from agents in plain language.\n\nBecause each catalog sits on its own publisher’s domain, the spec uses domain ownership to verify who published it.\n\nFor production use, publishers can attach trust metadata so an agent or registry can confirm the publisher’s cryptographic identity before connecting. Once a capability is selected, ARD hands off and the agent connects directly using the tool’s own protocol.\n\n## Same-Day Implementations\n\nSeveral contributors shipped working tools built on the spec the same day.\n\n[GitHub](https://github.blog/changelog/2026-06-17-agent-finder-for-github-copilot-now-available/) introduced agent finder, which lets Copilot discover matching MCP servers, skills, tools, and agents from a chosen registry, with users controlling what gets connected.\n\n[Hugging Face](https://huggingface.co/blog/agentic-resource-discovery-launch) released a Discover Tool that searches skills and MCP servers across ARD services. [Cisco](https://outshift.cisco.com/blog/ai-ml/agentic-resource-discover-specification-helps-agents-find-each-other) tied the spec to its AGNTCY Agent Directory, an open source project under the Linux Foundation.\n\nThe release continues a run of open specs aimed at the machine-readable layer of the web. Google published the [Open Knowledge Format](https://www.searchenginejournal.com/google-cloud-announces-the-open-knowledge-format/579253/), a spec for sharing organizational knowledge between AI systems, two days earlier. The pattern across these efforts is the same. Each asks you to publish a structured file under your own domain so AI systems can use what you expose, without anyone wiring the connection by hand.\n\n## Where Google Fits\n\nGoogle’s role centers on Agent Registry, part of its Gemini Enterprise Agent Platform.\n\nThe company said Agent Registry will host and search agentic resources and handle enterprise governance. Native ARD support in the platform is planned for the coming months, which Google said would let organizations connect internal registries to the wider network. That support is not live yet, and ARD is a specification rather than a Google Search feature.\n\n## Why This Matters\n\nThe split depends on what you publish. ARD is for publishers of callable capabilities, the APIs, MCP servers, and agents that software connects to. A company that publishes tools has a clear method for being found and trusted by agents. A typical content site has no clear action to take today.\n\nThe value of this effort is debated. Google’s John Mueller has argued that LLM systems can’t use files like llms.txt to distinguish one site from another, and advised focusing on current needs rather than future agent-oriented strategies. ARD targets tools and agents, not content, raising questions about building now for systems that may or may not generate traffic later.\n\n## Looking Ahead\n\nThe spec is a v0.9 draft, and the contributors are inviting changes through the project’s GitHub repository. Its reach depends on registries that can crawl and index catalogs at scale, and that ecosystem is still in its early stages. Google’s Agent Registry support is months out.\n\nIf that network develops, the advantage mainly goes to companies offering tools and agents that others need. The early [agentic-web features from Google](https://www.searchenginejournal.com/google-rolls-out-ai-mode-information-agents-to-ultra-subscribers/579085/) hint at this. The immediate concern is whether your current platforms and tools will adopt ARD and what they will require you to publish.", "url": "https://wpnews.pro/news/google-microsoft-back-draft-ai-agent-discovery-spec", "canonical_source": "https://www.searchenginejournal.com/google-microsoft-back-draft-ai-agent-discovery-spec/579894/", "published_at": "2026-06-18 19:48:40+00:00", "updated_at": "2026-06-18 20:14:03.132153+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "ai-infrastructure", "ai-research"], "entities": ["Google", "Microsoft", "GitHub", "Hugging Face", "Cisco", "NVIDIA", "Salesforce", "Linux Foundation"], "alternates": {"html": "https://wpnews.pro/news/google-microsoft-back-draft-ai-agent-discovery-spec", "markdown": "https://wpnews.pro/news/google-microsoft-back-draft-ai-agent-discovery-spec.md", "text": "https://wpnews.pro/news/google-microsoft-back-draft-ai-agent-discovery-spec.txt", "jsonld": "https://wpnews.pro/news/google-microsoft-back-draft-ai-agent-discovery-spec.jsonld"}}