Skip to main content

Elasticsearch

Search and analytics engine for documents, indices, search, ES|QL, cat, cluster, tasks, and ingest pipelines.

Set up​

Elasticsearch connects with credentials from your Elasticsearch account. Have these values ready:

  • Deployment endpoint
  • API key
  1. Go to Organization > Connectors and find Elasticsearch.
  2. Click Enable and choose which tools to allow.
  3. Each member enters their own values the first time they use it.

To use one account for the whole organization, turn on Share one connection with everyone. Every member's agents then act as that account, with exactly the access it has.

Tools​

Elasticsearch offers 59 tools. Admins choose which ones agents can use. See Tool permission groups.

Read (34)​

View and search information without changing it.

ToolWhat it does
analyze_textAnalyze text with POST /{index}/_analyze to see the tokens an analyzer produces, by named analyzer or by field.
cat_aliasesList index aliases and the indices they point to via GET /_cat/aliases.
cat_countShow the total document count across the cluster via GET /_cat/count.
cat_healthShow a one-line cluster health summary via GET /_cat/health (status, node and shard counts).
cat_indicesList indices with health, status, document counts, and store size via GET /_cat/indices.
cat_nodesList cluster nodes with resource usage (heap, CPU, load, role) via GET /_cat/nodes.
cat_shardsList shards with their index, state, document count, and node placement via GET /_cat/shards.
cluster_healthRetrieve the full cluster health document via GET /_cluster/health (status, node counts, shard counts).
cluster_statsRetrieve aggregate cluster statistics via GET /_cluster/stats (index, document, shard, and node totals).
countCount documents matching an optional Lucene query with GET /{index}/_count.
esql_queryRun an ES|QL query with POST /_query.
explain_documentExplain whether and why a specific document matches a query with POST /{index}/_explain/{id}, returning the relevance score breakdown.
get_aliasesRetrieve the aliases attached to an index with GET /{index}/_alias, keyed by index name.
get_cluster_infoRetrieve the cluster info document via GET / — the node name, cluster name, cluster UUID, and Elasticsearch version.
get_cluster_settingsRetrieve persistent and transient cluster settings via GET /_cluster/settings.
get_documentRetrieve a document and its metadata by ID with GET /{index}/_doc/{id}.
get_document_sourceRetrieve only the stored _source body of a document by ID with GET /{index}/_source/{id}, without the surrounding metadata.
get_field_capsDescribe which indices a field exists in and its search/aggregation capabilities with POST /{index}/_field_caps.
get_indexRetrieve an index's definition (aliases, mappings, settings) with GET /{index}, keyed by index name.
get_index_statsRetrieve statistics for an index (document counts, store size, operation counters) with GET /{index}/_stats.
get_index_templateRetrieve a composable index template by name with GET /_index_template/{name}, including its index patterns, settings, and mappings.
get_mappingRetrieve an index's field mappings with GET /{index}/_mapping, keyed by index name.
get_pipelineRetrieve an ingest pipeline definition by ID via GET /_ingest/pipeline/{id}.
get_settingsRetrieve an index's settings (shards, replicas, refresh interval, etc.) with GET /{index}/_settings, keyed by index name.
get_taskRetrieve the status and result of a single task via GET /_tasks/{task_id}.
get_term_vectorsRetrieve term vectors and term statistics for a document's fields with POST /{index}/_termvectors/{id}.
list_index_templatesList all composable index templates with GET /_index_template.
list_pipelinesList all ingest pipelines via GET /_ingest/pipeline.
list_tasksList running tasks across the cluster via GET /_tasks, grouped by node.
mget_documentsFetch multiple documents in one request with POST /{index}/_mget, by ids or per-document docs specs.
multi_searchRun several searches in one request with POST /{index}/_msearch.
searchRun a search with POST /{index}/_search using the Query DSL, with size/from or search_after pagination, sort, aggregations, and _source filtering.
terms_enumEnumerate matching terms in a keyword field with POST /{index}/_terms_enum, optionally filtered by a prefix string.
validate_credentialValidate the configured Elasticsearch API key and deployment endpoint by calling the cluster info endpoint (GET /, requires cluster monitor privilege).

Write (5)​

Create or send data.

ToolWhat it does
add_aliasAdd an alias to an index with PUT /{index}/_alias/{name}, optionally filtered or as the write index.
create_documentCreate a new document at a given ID with POST /{index}/_create/{id}.
create_indexCreate a new index with PUT /{index}, optionally with mappings, settings, and aliases.
open_point_in_timeOpen a point-in-time with POST /{index}/_pit to run consistent paginated searches against a fixed view. keep_alive is required (e.g. '1m').
refresh_indexRefresh an index with POST /{index}/_refresh to make recent writes searchable immediately.

Delete or overwrite (20)​

Remove or replace existing data.

ToolWhat it does
bulkPerform many index/create/update/delete actions in one request with POST /{index}/_bulk.
cancel_taskCancel a running, cancellable task via POST /_tasks/{task_id}/_cancel.
close_indexClose an index with POST /{index}/_close, blocking reads and writes until reopened.
close_point_in_timeClose a point-in-time context with DELETE /_pit to free its resources.
delete_aliasRemove an alias from an index with DELETE /{index}/_alias/{name}.
delete_by_queryDelete all documents matching a Query DSL query with POST /{index}/_delete_by_query.
delete_documentDelete a document by ID with DELETE /{index}/_doc/{id}.
delete_indexPermanently delete an index and all its documents with DELETE /{index}.
delete_index_templateDelete a composable index template by name with DELETE /_index_template/{name}.
delete_pipelineDelete an ingest pipeline by ID via DELETE /_ingest/pipeline/{id}.
index_documentIndex (create or overwrite) a document at a given ID with PUT /{index}/_doc/{id}.
open_indexOpen a closed index with POST /{index}/_open so it accepts reads and writes again.
put_index_templateCreate or replace a composable index template with PUT /_index_template/{name}, applying its settings/mappings to indices matching index_patterns.
put_pipelineCreate or replace an ingest pipeline via PUT /_ingest/pipeline/{id} with an ordered list of processors.
reindexCopy documents from one index to another with POST /_reindex, given source and dest specs.
update_by_queryUpdate all documents matching a query with POST /{index}/_update_by_query, applying an optional script.
update_cluster_settingsUpdate persistent and/or transient cluster settings via PUT /_cluster/settings.
update_documentPartially update a document by ID with POST /{index}/_update/{id}, using a partial doc merge, a script, or an upsert.
update_mappingAdd fields to an index's mapping or change its dynamic mode with PUT /{index}/_mapping.
update_settingsUpdate an index's dynamic settings with PUT /{index}/_settings, e.g. number_of_replicas or refresh_interval.
⌘J