elasticsearch_healthLABSCO SUMMARY
Cluster work without composing the JSON yourself.
The reach is the useful part: the same session that checked cluster health can read a mapping, add a field, reindex into the new shape and query the result — steps that normally mean four hand-written request bodies.
What it is
A connector that gives an assistant the operational surface of Elasticsearch: it can list what indices exist, read and change their mappings, run a query DSL search, push data in, and manage index templates — with cluster health as the starting point.
What you get
- Cluster —
elasticsearch_healthfor cluster status, optionally with index-level detail - Indices —
list_indiceswith regex support,create_indexwith settings and mappings,reindexfrom one index to another with an optional query and script - Mappings —
get_mappingsfor an index,create_mappingto create or update the structure - Search and data —
searchwith a query DSL body,bulkfor loading data in - Templates —
create_index_template,get_index_template,delete_index_template
Requirements
An Elasticsearch instance and credentials: ES_HOST is required, and you must supply either ES_API_KEY or both ES_USERNAME and ES_PASSWORD. ES_CA_CERT points at a custom CA certificate for TLS. ES_HOST accepts a comma-separated list of node URLs, and the client handles failover and load balancing across them. Runs as npx -y @awesome-ai/elasticsearch-mcp. Since the same connection carries create, reindex and delete-template operations, give it credentials scoped to what you actually want an assistant to change.
Setup effort
One command plus a key — npx -y @awesome-ai/elasticsearch-mcp, then supply credentials
USE CASES
01
Getting oriented in a cluster you did not build
Check health, list the indices by pattern, and read the mappings of the ones that matter.
02
Answering a data question
Describe the question and let it build the query DSL against the right index rather than writing the body by hand.
03
Adding a field to an existing index
Read the current mapping, update it, and reindex into the new shape with a query or script to shape the data on the way.
04
Standing up a new index properly
Create it with shard, replica and mapping settings in one call instead of accepting the defaults and fixing them later.
05
Loading a batch of records
Push the documents in through the bulk path rather than one request per record.
06
Managing the pattern behind a log index
Create or inspect the index template so new daily indices come out with the settings you meant.
11 tools
Listed in project docs. Your client may show a different list.
list_indicescreate_indexreindexget_mappingscreate_mappingsearchbulkcreate_index_templateget_index_templatedelete_index_templateBEFORE YOU INSTALL
What to know first
Tools you get
11 tools named in the project's documentation.
Requires
- npx on PATH
- An Elasticsearch instance
- ES_HOST in your environment
- ES_API_KEY in your environment, or both ES_USERNAME and ES_PASSWORD
Where it runs
Both documented clients run the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
npx -y @awesome-ai/elasticsearch-mcpMCP Clients
Claude Desktop, Cursor
JSON
{
"mcpServers": {
"elasticsearch-mcp": {
"command": "npx",
"args": [
"-y",
"@awesome-ai/elasticsearch-mcp"
],
"env": {
"ES_HOST": "<YOUR_ES_HOST>",
"ES_API_KEY": "<YOUR_ES_API_KEY>"
}
}
}
}<YOUR_ES_HOST> is your cluster URL (comma-separate several nodes), and <YOUR_ES_API_KEY> is an Elasticsearch API key — or remove ES_API_KEY and set ES_USERNAME and ES_PASSWORD instead.
