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
- Go to Organization > Connectors and find Elasticsearch.
- Click Enable and choose which tools to allow.
- 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.
| Tool | What it does |
|---|---|
analyze_text | Analyze text with POST /{index}/_analyze to see the tokens an analyzer produces, by named analyzer or by field. |
cat_aliases | List index aliases and the indices they point to via GET /_cat/aliases. |
cat_count | Show the total document count across the cluster via GET /_cat/count. |
cat_health | Show a one-line cluster health summary via GET /_cat/health (status, node and shard counts). |
cat_indices | List indices with health, status, document counts, and store size via GET /_cat/indices. |
cat_nodes | List cluster nodes with resource usage (heap, CPU, load, role) via GET /_cat/nodes. |
cat_shards | List shards with their index, state, document count, and node placement via GET /_cat/shards. |
cluster_health | Retrieve the full cluster health document via GET /_cluster/health (status, node counts, shard counts). |
cluster_stats | Retrieve aggregate cluster statistics via GET /_cluster/stats (index, document, shard, and node totals). |
count | Count documents matching an optional Lucene query with GET /{index}/_count. |
esql_query | Run an ES|QL query with POST /_query. |
explain_document | Explain whether and why a specific document matches a query with POST /{index}/_explain/{id}, returning the relevance score breakdown. |
get_aliases | Retrieve the aliases attached to an index with GET /{index}/_alias, keyed by index name. |
get_cluster_info | Retrieve the cluster info document via GET / — the node name, cluster name, cluster UUID, and Elasticsearch version. |
get_cluster_settings | Retrieve persistent and transient cluster settings via GET /_cluster/settings. |
get_document | Retrieve a document and its metadata by ID with GET /{index}/_doc/{id}. |
get_document_source | Retrieve only the stored _source body of a document by ID with GET /{index}/_source/{id}, without the surrounding metadata. |
get_field_caps | Describe which indices a field exists in and its search/aggregation capabilities with POST /{index}/_field_caps. |
get_index | Retrieve an index's definition (aliases, mappings, settings) with GET /{index}, keyed by index name. |
get_index_stats | Retrieve statistics for an index (document counts, store size, operation counters) with GET /{index}/_stats. |
get_index_template | Retrieve a composable index template by name with GET /_index_template/{name}, including its index patterns, settings, and mappings. |
get_mapping | Retrieve an index's field mappings with GET /{index}/_mapping, keyed by index name. |
get_pipeline | Retrieve an ingest pipeline definition by ID via GET /_ingest/pipeline/{id}. |
get_settings | Retrieve an index's settings (shards, replicas, refresh interval, etc.) with GET /{index}/_settings, keyed by index name. |
get_task | Retrieve the status and result of a single task via GET /_tasks/{task_id}. |
get_term_vectors | Retrieve term vectors and term statistics for a document's fields with POST /{index}/_termvectors/{id}. |
list_index_templates | List all composable index templates with GET /_index_template. |
list_pipelines | List all ingest pipelines via GET /_ingest/pipeline. |
list_tasks | List running tasks across the cluster via GET /_tasks, grouped by node. |
mget_documents | Fetch multiple documents in one request with POST /{index}/_mget, by ids or per-document docs specs. |
multi_search | Run several searches in one request with POST /{index}/_msearch. |
search | Run a search with POST /{index}/_search using the Query DSL, with size/from or search_after pagination, sort, aggregations, and _source filtering. |
terms_enum | Enumerate matching terms in a keyword field with POST /{index}/_terms_enum, optionally filtered by a prefix string. |
validate_credential | Validate 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.
| Tool | What it does |
|---|---|
add_alias | Add an alias to an index with PUT /{index}/_alias/{name}, optionally filtered or as the write index. |
create_document | Create a new document at a given ID with POST /{index}/_create/{id}. |
create_index | Create a new index with PUT /{index}, optionally with mappings, settings, and aliases. |
open_point_in_time | Open 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_index | Refresh an index with POST /{index}/_refresh to make recent writes searchable immediately. |
Delete or overwrite (20)
Remove or replace existing data.
| Tool | What it does |
|---|---|
bulk | Perform many index/create/update/delete actions in one request with POST /{index}/_bulk. |
cancel_task | Cancel a running, cancellable task via POST /_tasks/{task_id}/_cancel. |
close_index | Close an index with POST /{index}/_close, blocking reads and writes until reopened. |
close_point_in_time | Close a point-in-time context with DELETE /_pit to free its resources. |
delete_alias | Remove an alias from an index with DELETE /{index}/_alias/{name}. |
delete_by_query | Delete all documents matching a Query DSL query with POST /{index}/_delete_by_query. |
delete_document | Delete a document by ID with DELETE /{index}/_doc/{id}. |
delete_index | Permanently delete an index and all its documents with DELETE /{index}. |
delete_index_template | Delete a composable index template by name with DELETE /_index_template/{name}. |
delete_pipeline | Delete an ingest pipeline by ID via DELETE /_ingest/pipeline/{id}. |
index_document | Index (create or overwrite) a document at a given ID with PUT /{index}/_doc/{id}. |
open_index | Open a closed index with POST /{index}/_open so it accepts reads and writes again. |
put_index_template | Create or replace a composable index template with PUT /_index_template/{name}, applying its settings/mappings to indices matching index_patterns. |
put_pipeline | Create or replace an ingest pipeline via PUT /_ingest/pipeline/{id} with an ordered list of processors. |
reindex | Copy documents from one index to another with POST /_reindex, given source and dest specs. |
update_by_query | Update all documents matching a query with POST /{index}/_update_by_query, applying an optional script. |
update_cluster_settings | Update persistent and/or transient cluster settings via PUT /_cluster/settings. |
update_document | Partially update a document by ID with POST /{index}/_update/{id}, using a partial doc merge, a script, or an upsert. |
update_mapping | Add fields to an index's mapping or change its dynamic mode with PUT /{index}/_mapping. |
update_settings | Update an index's dynamic settings with PUT /{index}/_settings, e.g. number_of_replicas or refresh_interval. |