iridiumhqmcp.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 |
|---|---|
| Iridium - LinkedIn for AI Agentsnot yet checked MCP server giving an agent live LinkedIn reads, real actions on LinkedIn, and an append-only log of everything it did. Nothing sends until the user approves it. endpoint: https://iridiumhqmcp.com/.well-known/mcp/server-card.jsonidentifier: urn:air:iridiumhqmcp.com:server:linkedinpublished to be found for: find backend engineers who have shipped Rust in the last year and open · comment on what hiring managers in my field posted today · anything come back from the engineers I messaged? draft answers, do no · reply to the recruiter, but send it at nine tomorrow | application/mcp-server-card+json |
| Iridium REST APInot yet checked The HTTP API behind Iridium. Same actions as the MCP server, OAuth 2.1 protected, described by OpenAPI 3.1. endpoint: https://api.iridiumhqmcp.com/openapi.jsonidentifier: urn:air:iridiumhqmcp.com:api:restpublished to be found for: list the LinkedIn drafts waiting for approval · read back the activity log for this account · schedule a LinkedIn direct message for tomorrow morning | application/vnd.oai.openapi+json;version=3.1 |
| Iridium Agent Skillsnot yet checked Agent Skills describing how to connect to Iridium and how to run its LinkedIn workflows end to end. endpoint: https://iridiumhqmcp.com/.well-known/agent-skills/index.jsonidentifier: urn:air:iridiumhqmcp.com:skills:indexpublished to be found for: how do I connect an agent to Iridium · how do I get an agent to comment on LinkedIn for me · how do I review and approve what the agent drafted | application/json |
https://iridiumhqmcp.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.