trytoolscout.org publishes an Agentic Resource Discovery manifest at /.well-known/ard.json, declaring what an AI agent can call on this domain. Everything below is read from that file. First seen by our crawler on 07 September 2026.
| Declared resource | Type |
|---|---|
| ToolScout Software Recommendation Agentanswers in 350msv1.0.0 Read-only agent that ranks software against a described job and optional budget, team and priority constraints. endpoint: https://trytoolscout.org/.well-known/agent-card.jsonidentifier: urn:air:trytoolscout.org:a2a:software-recommendation-agentpublished to be found for: find software for customer support · which AI assistant should my team use · recommend marketing software for a small company software recommendations agent a2a recommend_software | application/a2a-agent-card+json |
| ToolScout MCP Software Recommendationsanswers in 360msv1.0.0 Deterministic software recommendations for a job, persona, budget, team and priority. Affiliate relationships do not influence ranking. endpoint: https://trytoolscout.org/mcpidentifier: urn:air:trytoolscout.org:mcp:software-recommendationspublished to be found for: what software should I use for my small sales team · recommend a CRM under 25 dollars per month · best SEO tools for an agency · workflow automation software for a small business software recommendations decision-support mcp recommend_tools | application/mcp-server-card+json |
| ToolScout Recommendation APIanswers in 371msv1.0.0 Public read-only recommendation API for deterministic ToolScout software matching. endpoint: https://trytoolscout.org/openapi.jsonidentifier: urn:air:trytoolscout.org:openapi:recommendation-apipublished to be found for: software recommendation API · API that ranks SaaS tools for a use case · programmatic software discovery software recommendations api openapi recommend_tools | application/vnd.oai.openapi+json;version=3.1 |
https://trytoolscout.org/.well-known/ard.json, this publisher's own file. Identifiers are reproduced exactly as published.
Of the resources listed, 3 have been probed for reachability.
"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.