Agentic Resource Discovery

Every tool an agent
can call, in one index.

Neuronto is a federated ARD registry. Ask it what can do a task and it searches its own catalogue and every other public ARD registry at once, then fuses the rankings into a single answer. It currently indexes 10,811 resources from 5,718 publishers, 10,146 verified to respond.

What is ARD?

ARD stands for Agentic Resource Discovery. It is an open specification for how AI agents find the tools, skills, agents and APIs they need, published in June 2026 by a working group including Google, Microsoft, Hugging Face, AWS, Cisco, GitHub, Nvidia, Salesforce and Snowflake.

An agentic resource is anything an AI client can call to get work done: an MCP server, an A2A agent, a skill, an API, a workflow. ARD answers one question, “what is available for this task?”, and then gets out of the way. It is a discovery layer, not a runtime, and it does not replace MCP or A2A: it tells an agent what exists, and the agent connects using the resource's own protocol.

Why agents need it

An agent can only use capabilities someone wired in beforehand, and every tool description competes for space in the context window. That does not survive an ecosystem of thousands of tools. ARD moves selection out of the context window and into a search service.

How discovery works

Publishers describe what they offer at /.well-known/ard.json on their own domain. Registries crawl those manifests and answer queries over them. Nobody has to be approved by a marketplace to be found.

What federation means

The specification defines three federation modes and makes auto the default: a registry queries its peers, merges their results and returns one set. Ask once, reach the whole federation.

Who it is for

Agent builders who want to stop hard-coding integrations. API and tool vendors who want to be discoverable without applying anywhere. Platform teams running discovery over their own internal services.

The index

Resources indexed
10,811
Publishers
5,718
Verified live
10,146
Registries federated
6

What is in the index

10,811 entries · 5,718 publishers

Every entry is a resource an AI client can actually call, held with its endpoint, its description, the queries its publisher says it serves, and which sources carry it. The whole index is queryable over the API with no key and no signup, and browsable page by page through GET /agents.

Kind of resourceEntriesWhat it is
mcp-server8,059MCP servers an agent can connect to and call as tools
skill2,060Skills and agent skill bundles
doc264Machine-readable documentation such as llms.txt
other178Resources whose type is outside the named set
openapi152REST APIs described by an OpenAPI document
a2a-agent58A2A agents with a published agent card
catalog15Nested catalogues pointing at further entries
registry11Other ARD registries, which is how federation is discovered
package6Published packages
plugin3Plugin manifests, including the OpenAI-era ai-plugin.json
graphql2GraphQL APIs
agent1Agent descriptors that are not A2A cards: ACP, OASF, AgentFacts
dataset1Published datasets
webmcp1Tools a web page exposes to a browser agent, W3C WebMCP

Where it comes from

Aggregated from every public ARD registry, the official MCP Registry, and our own crawl of the well-known discovery paths. The crawl reaches publishers no other index covers: the only other general crawler in the ecosystem stops at the top 100,000 domains, so anyone smaller is invisible everywhere else.

SourceEntries
Official MCP Registry4,718
WellKnown3,867
Our own crawl of the discovery paths1,125
Hugging Face Discover933
GitHub Agent Finder821
ardregistry606
Desvela178
submitted2

Publishers

PublisherEntriesVerified liveKinds
huggingface.co
mcp-server · registry · skill
9119093
github.com
skill
7327321
ora.ai
a2a-agent · mcp-server · skill
5935863
ai.smithery
mcp-server
2202201
registry.modelcontextprotocol.io
mcp-server
2192191
app.wishpool
mcp-server
12501
api.mcp.github.com
mcp-server
1121121
com.mcparmory
mcp-server
76661
io.github.csoai-org
mcp-server
71621
com.jojapi
mcp-server
49491
com.mambabuilt
mcp-server
47471
io.github.evozim
mcp-server
46461

Every public ARD registry, measured

Benchmarked 31 August 2026 with the specification's own conformance tool. Precision is top-1 over six queries with unambiguous answers; spread is the average gap between the best and worst score in a result set.

RegistryConformanceEntriesP@1 SpreadLatencyfederation: auto
NeurontoPASS10,811 6/678<200msyes
GitHub Agent FinderFAIL3446/6 32.51,970msno
WellKnownPASS1,2396/6 6.7401msno
Hugging Face DiscoverPASS4120/6 40.81,712msno
DesvelaPASS932/6 39.7213msno

Use it

ARD v0.91 · no key, no signup

Search the federation

curl -s https://neuronto.com/search \
  -H 'content-type: application/json' \
  -d '{"query":{"text":"scrape a website"},
       "federation":"auto"}'

Install as an MCP server

claude mcp add --transport http \
  neuronto https://neuronto.com/mcp

Publishing? Serve an ARD manifest at /.well-known/ard.json with representativeQueries on every entry. The crawler finds it. No submission form, no allowlist.