Index / ARD publishers / decisionlog.ai

decisionlog.ai

decisionlog.ai 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 resourceType
Decision Log MCP Servernot yet checked
Authenticated MCP access for immutable decision capture, retrieval, provenance, supersession, candidates, and audit history.
endpoint: https://www.decisionlog.ai/.well-known/mcp.json
identifier: urn:air:decisionlog.ai:server:decision-log-mcp
published to be found for: What is the current decision for this domain? · Why was this decision made and what evidence supports it? · Submit this extracted decision as a candidate for human review.
decisions provenance supersession audit decision_log.search_decision decision_log.get_current_dec decision_log.create_candidat decision_log.get_supersessio
trust identity: https://www.decisionlog.ai/.well-known/mcp-registry-auth
application/mcp-server+json
Decision Log REST APInot yet checked
A typed REST façade generated from and delegated to the canonical Decision Log GraphQL schema.
endpoint: https://www.decisionlog.ai/openapi.json
identifier: urn:air:decisionlog.ai:api:decision-log-rest
published to be found for: Search for decisions related to an architecture choice. · Retrieve a decision with its provenance and sources. · Record an approved decision with an idempotent API call.
rest openapi decisions agents SearchDecisions GetCurrentDecision CreateDecisionCandidate GetSupersessionHistory
application/vnd.oai.openapi+json;version=3.1
Source: https://decisionlog.ai/.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.

Search this publisher's resources alongside every other indexed resource at 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.