Real-World Observations
Fresh human-observable information about physical places and conditions.
Intended for AI agents that need information that may be unavailable, stale, or uncertain online: whether a trail is muddy, how long a line is, whether construction is blocking an entrance, or whether a venue is crowded right now.
MCP endpoint
https://mcp.loci-labs.ai/mcpStreamable HTTPNo authLoci Labs provides a Model Context Protocol interface for querying fresh observations about the physical world. It supports MCP 2026-07-28 (stateless, server/discover) and earlier revisions that use initialize.
{
"mcpServers": {
"loci-labs": {
"type": "streamable-http",
"url": "https://mcp.loci-labs.ai/mcp"
}
}
}Tool: search_real_world_observations
Search for fresh real-world observations about physical places, conditions, availability, crowds, lines, closures, construction, weather effects, events, inventory visible in person, accessibility, or other facts that may be stale, uncertain, or unavailable on the public web. Use this when answering the user's question would benefit from a recent observation made by a person physically present at or near the relevant location.
- question
- Required. What you want to know, e.g. “Is the playground muddy right now?”
- location
- Place name, address, venue, or coordinates as text.
- freshness
- “right now”, “within 30 minutes”, “today”, “within 24 hours”.
- observation_type
- crowd, condition, availability, closure, construction, weather impact, accessibility, inventory, event status, other.
- context
- Optional extra context. Please do not include personal or sensitive information.
Preview status
During the current preview, requests may return that no sufficiently recent observation is available. Responses never claim an observation exists when one does not.