letagentsin.com publishes an Agentic Resource Discovery manifest at
/.well-known/ai-catalog.json, declaring what an AI agent can call on this domain.
Everything below is read from that file. First seen by our crawler on 31 August 2026.
| Declared resource | Type |
|---|---|
| Let Agents In MCP servernot yet checked Runs the same scan over MCP, so an agent can check a vendor before integrating with it. endpoint: https://letagentsin.com/.well-known/mcp.jsonidentifier: urn:air:letagentsin.com:tools:mcppublished to be found for: score a domain for agent readiness from my coding agent agent-readiness mcp developer-tools analyze | application/mcp-server-card+json |
| Agent readiness scannot yet checkedv9.57 Scores any public domain on whether an AI agent can find it, get in and get a credential, from 16 checks with published rules. endpoint: https://letagentsin.com/openapi.jsonidentifier: urn:air:letagentsin.com:api:scanpublished to be found for: can an AI agent sign up for this product without a human · why did a coding agent pick a competitor over this vendor · which of my API docs stop an agent from getting a key · is my llms.txt or MCP endpoint doing anything measurable agent-readiness developer-tools api-audit analyze search | application/openapi+json |
| Published corpus of 177 measured vendorsnot yet checked Every scored row, in full, with the sentence behind each verdict and the addresses it was measured on. endpoint: https://letagentsin.com/corpus.jsonidentifier: urn:air:letagentsin.com:data:corpuspublished to be found for: which developer tools are measurably usable by agents · compare vendors in one category on agent readiness dataset agent-readiness benchmark search | application/json |
https://letagentsin.com/.well-known/ai-catalog.json, this publisher's own file.
Identifiers are reproduced exactly as published.
Note: this is the pre-v0.91 path. The specification renamed the manifest to /.well-known/ard.json, and most of the ecosystem still serves the older name.
None of these endpoints has been probed for reachability yet, so nothing here says whether they answer.
"Answers" and "no response" describe only whether an endpoint replied when last probed:
services go down and come back, and an entry is demoted rather than removed. None of this
is a trust, quality or safety rating.
https://neuronto.com/search, or connect an agent to https://neuronto.com/mcp.
If this is your domain, the free console shows what a registry
sees when it reads your manifest.