Skip to main content
Glama

Search

search
Read-only

Find source media, remarks and journal blocks; for memories, experiences and preferences use get_travel_context. City/kind/date filters apply to media; trip applies to all results. Two independent parts: structured filters (trip, city, kind, date range) and an optional query word. The query is not a filter - it is the sort order. With a query you get the closest matches, ranked; without one you get everything the filters allow, in time order, with a cursor to page through all of it. For 'what did I eat this year' style questions, omit the query and set brief - you get a one-line catalogue to scan and group yourself, which no ranked search can do completely.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cityNoReverse-geocoded city, e.g. Kyoto. Exact match.
kindNoMaterial type. Setting it also leaves remarks out - words are not media.
briefNoReturn one compact line per item (id, local time, city, keywords) instead of full descriptions. Roughly a third of the tokens - use it whenever you are scanning rather than reading.
limitNoDefault 20, max 200.
queryNoWhat to look for, in the traveller's language. Omit it to enumerate rather than rank.
cursorNoFrom a previous response's next_cursor. Only meaningful without a query.
to_utcNoEpoch milliseconds UTC.
trip_idNoOne trip; omit for all of them.
from_utcNoEpoch milliseconds UTC.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

Score is being calculated.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources