llmpulse.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 resource | Type |
|---|---|
| LLM Pulse MCP Serveranswers in 205msv1.0.0 Model Context Protocol server exposing LLM Pulse brand-visibility, share-of-voice, citation and sentiment analytics across ChatGPT, Perplexity, Gemini and Google AI Overviews. Authenticates with OAuth 2.1 (every plan) or a Bearer API key (Scale and above). endpoint: https://api.llmpulse.ai/api/v1/mcp/server-cardidentifier: urn:air:llmpulse.ai:server:mcppublished to be found for: how visible is my brand in ChatGPT compared to competitors · what is my share of voice across AI models this month · which sources do AI assistants cite when answering about my industry · show the sentiment of AI answers that mention my brand ai-visibility geo brand-monitoring analytics mcp ask_support assign_prompt_tags create_annotation trust identity: https://api.llmpulse.ai/api/v1/mcp | application/mcp-server-card+json |
| LLM Pulse REST API v1answers in 188msv1.0.0 RESTful API for LLM Pulse AI-visibility analytics: metrics (timeseries, summary, share of voice), dimensions, citation intelligence, answers, sentiments and recommendations. Bearer token auth. endpoint: https://api.llmpulse.ai/openapi.jsonidentifier: urn:air:llmpulse.ai:api:rest-v1published to be found for: pull my brand visibility timeseries for the last 30 days · list the competitors tracked for a project · get the top cited domains across AI answers ai-visibility geo brand-monitoring analytics rest openapi | application/vnd.oai.openapi+json;version=3.0 |
https://llmpulse.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.
Of the resources listed, 2 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.