Summary
Three read tools that answer what is in this cluster without opening Kibana.
Listing the indices and then reading one mapping gives an agent the shape of the data before it searches, which is the step that otherwise costs several failed queries. Everything in the set reads: there is no indexing, update or delete call here.
What it is
A Python server, built on FastMCP, that connects to an Elasticsearch cluster and exposes search, index listing and mapping inspection.
What you get
- Every index on the cluster, with the system indices left out (list_indices)
- The mapping for a named index, so you know which fields exist before you query them (get_index_mappings)
- A query-string search against an index (search_index)
Requirements
Python 3.8 or newer, uv or pip, and a reachable Elasticsearch cluster. Its address, plus a username and password, go in the environment.