Skip to content

Connectors · Developer & infrastructure

Elasticsearch MCP server for AI agents.

actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to Elasticsearch and the rest of your systems. It gives your agent 711 Elasticsearch actions (363 reads, 256 writes and 92 that wait for a confirmation) and holds the Elasticsearch credential itself, so the agent never does. It paces Elasticsearch's limits and records every call.

100,000 free calls a month. No card, no email, no password: press Start a free sandbox on the next screen and keep the key it shows you.

claude mcp add --transport http actionlake https://connect.actionlake.com/mcp
the first call
do {  action: "elasticsearch.cat.nodes",  intent: "check which Elasticsearch account is connected"}# Get node information · read · 1 upstream call
  • 711actionsin one signed file
  • 363readlook, never change
  • 256writecreate and update
  • 92wait for a yesdestructive, confirmed first

Set up

Connect Elasticsearch in three steps.

  1. 01

    Add actionlake to Claude.

    Run the command once in Claude Code; its consent page can create a free sandbox: 100,000 calls a month, no card. In the Claude app, add a custom connector with the URL below and paste your key on the consent page. Creating a new sandbox from the Claude app is not yet tested by us.

    https://connect.actionlake.com/mcp
  2. 02

    Connect Elasticsearch.

    API key. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead. actionlake stores what you paste write-only, sealed under your tenant's key.

    • api_keyElasticsearch API key, the base64 `encoded` value (Kibana > Stack Management > API keys > Create API key, or POST…
    • hostWhere your Elasticsearch lives: your host
    account { op: "connections.requirements", service: "elasticsearch" }
    # free: exactly what to paste, and what is found for you
  3. 03

    Make the first call. Check before a write.

    Ask in plain words; Claude picks the action. Before anything changes, check validates the call and prices it, for free.

    do    { action: "elasticsearch.cat.nodes" }# get node information · read · 1 upstream callcheck { action: "elasticsearch.nodes.reload_secure_settings", input: { … } }# free: inputs, permissions, cost and confirmations, nothing sent

Elasticsearch at a glance

Sign-in
API key. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead.
You provide
api_key
Setup fields
host
Limits we pace to
600 calls a minute, per connection
API covered
Elasticsearch REST API 9.x (elasticsearch-specification main), at your Elasticsearch instance's API base URL, which you enter when connecting
Built from
Elasticsearch's documentation, read 22 October 2026OpenAPI spec (GitHub)
Service file
Version 1.0.0, signed (Ed25519)
Cached reads
Not cached: every read goes to the vendor
Shared entities
2, so ask can line Elasticsearch up with your other systems
Data
Processed and stored in Sydney, Australia. No US region yet

Capabilities

What an AI agent can do in Elasticsearch.

711 actions in 39 areas. Every one carries its effect, so a key can allow the reads and hold the rest.

  • 363readlook, never change
  • 256writecreate and update
  • 92destructivewait for a confirmation
  1. Indices

    97

    55 read · 32 write · 10 destructive

    Create an index · Roll over to a new index · Roll over to a new index · Create a data stream

  2. ML

    90

    43 read · 32 write · 15 destructive

    Predict future behavior of a time series · Add scheduled events to the calendar · Send data to an anomaly detection job for analysis · Clear trained model deployment cache

  3. Security

    78

    30 read · 34 write · 14 destructive

    Activate a user profile · Bulk create or update roles · Bulk update API keys · Clone an API key

  4. Core

    61

    39 read · 14 write · 8 destructive

    Create a new document in the index · Create or update a document in an index · Get multiple documents · Get multiple documents

  5. Inference

    49

    5 read · 41 write · 3 destructive

    Perform streaming chat completion inference on the service · Perform completion inference on the service · Perform dense embedding inference on the service · Perform inference on the service

  6. Cat

    45

    45 read · 0 write · 0 destructive

    Get node information · Get node attribute information · Get thread pool statistics · Get thread pool statistics

  7. Connector

    30

    4 read · 23 write · 3 destructive

    Create a connector · Check in a connector · Get a connector · Get all connectors

  8. Cluster

    20

    14 read · 4 write · 2 destructive

    Get the pending cluster tasks · Get component templates · Explain the shard allocations · Get component templates

31 more areas · 241 actions
  • Esql 19
  • Nodes 18
  • Ingest 16
  • Snapshot 16
  • Watcher 16
  • Transform 15
  • CCR 14
  • Ilm 12
  • Search application 11
  • Rollup 10
  • SLM 10
  • Query rules 8
  • License 7
  • Searchable snapshots 7
  • Synonyms 7
  • Enrich 6
  • SQL 6
  • Async search 5
  • Eql 4
  • Fleet 4
  • Logstash 4
  • Migration 4
  • Tasks 4
  • Text structure 4
  • Dangling indices 3
  • Streams 3
  • Features 2
  • Simulate 2
  • Xpack 2
  • Graph 1
  • SSL 1

Top actions

The Elasticsearch API, shaped for agents.

The ids your agent types, what each does, and the one name it shares with other systems. 68 of Elasticsearch's 68 action names are shared with at least one other connector, so an agent learns them once.

ActionWhat it doesEffectSame name in
elasticsearch.cat.nodesGet node informationGet node informationreadinfra.instance.list18 connectors
elasticsearch.nodes.infoGet node informationGet node informationreadinfra.instance.list18 connectors
elasticsearch.nodes.reload_secure_settingsReload the keystore on nodes in the clusterReload the keystore on nodes in the clusterwriteinfra.instance.update15 connectors
elasticsearch.cat.indicesGet index informationGet index informationreadinfra.search_index.list5 connectors
elasticsearch.cat.snapshotsGet snapshot informationGet snapshot informationreadinfra.snapshot.list12 connectors
elasticsearch.cat.snapshots_by_repositoryGet snapshot informationGet snapshot informationreadinfra.snapshot.list12 connectors
elasticsearch.cat.indices_by_indexGet index informationGet index informationreadinfra.search_index.list5 connectors
elasticsearch.core.index_documentCreate or update a document in an indexCreate or update a document in an indexwritecontent.record.create15 connectors
elasticsearch.core.create_documentCreate a new document in the indexCreate a new document in the indexwritecontent.record.create15 connectors
elasticsearch.snapshot.deleteDelete snapshotsDelete snapshotsdestructiveinfra.snapshot.delete9 connectors
elasticsearch.cat.tasksGet task informationGet task informationreadautomation.background_job.list34 connectors
elasticsearch.tasks.listGet all tasksGet all tasksreadautomation.background_job.list34 connectors

Try it

Prompts to paste into Claude.

Each one names the Elasticsearch actions it will call, so you know what it reads and what it changes before you send it.

  1. Readread

    Get node information in Elasticsearch and tell me what stands out.

    callselasticsearch.cat.nodes

  2. Writewrite

    Reload the keystore on nodes in the cluster in Elasticsearch. Show me exactly what you will send before you save it.

    callselasticsearch.nodes.reload_secure_settings

Governance for Elasticsearch

Destructive actions wait for a yes.

92 Elasticsearch actions are destructive. The first 10:

  • Delete snapshotselasticsearch.snapshot.delete
  • Delete indiceselasticsearch.indices.delete
  • Delete documentselasticsearch.core.delete_by_query
  • Delete a documentelasticsearch.core.delete_document
  • Delete a dangling indexelasticsearch.dangling_indices.delete_dangling_index
  • Clear a scrolling searchelasticsearch.core.clear_scroll
  • Delete an aliaselasticsearch.indices.delete_alias
  • Delete pipelineselasticsearch.ingest.delete_pipeline
  • Delete a legacy index templateelasticsearch.indices.delete_template
  • Delete data streamselasticsearch.indices.delete_data_stream

A destructive action runs only with confirm: true. Under the human policy the agent cannot confirm for itself: the run stops until a named person approves, in the console or from a signed link in an email. The cap on a key is refused before the call is sent, never after.

doelasticsearch.snapshot.deleteconfirm_policy: human

Delete snapshots?

intent: the user asked me to delete snapshots

run suspended · waiting for a named person · key elasticsearch-agent cannot confirm itself
In the console, or from an emailed signed link.
a key for this connector
account {  op: "keys.create", name: "elasticsearch-agent",  allowed_actions: ["elasticsearch.*"], cap_calls: 2000,  confirm_policy: "human_for_writes",  approval_rules: [    { match: "elasticsearch.snapshot.delete", approver: "[email protected]" },    { match: "elasticsearch.indices.delete", approver: "[email protected]" },    { match: "elasticsearch.core.delete_by_query", approver: "[email protected]" }  ]}
Illustrative. Scoped to Elasticsearch only, capped at 2,000 upstream calls, every write confirmed, and the destructive ones approved by a named person.

Cost

What Elasticsearch costs on actionlake.

Every Elasticsearch action is one upstream call, the only thing actionlake bills. Searching, check, cost, account and any call Elasticsearch refused with 401, 403, 429 or a 5xx are free. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000.

  • 1upstream call per actionall 711 Elasticsearch actions
  • 711actions pageeach page of a long list is one call
  • 0reads can be cacheda cache hit costs nothing
  • 100,000calls a month, freepaid plans from US$49 a month for 250,000

See pricing

Action index

Every Elasticsearch action.

711 actions by area: the id your agent calls, what it does, and its effect.

Indices97
  • elasticsearch.indices.createCreate an indexwrite
  • elasticsearch.indices.create_data_streamCreate a data streamwrite
  • elasticsearch.indices.rolloverRoll over to a new indexwrite
  • elasticsearch.indices.rollover_by_new_indexRoll over to a new indexwrite
  • elasticsearch.indices.add_blockAdd an index blockwrite
  • elasticsearch.indices.analyzeGet tokens from text analysisread
  • and 91 more in this area
ML90
  • elasticsearch.ml.clear_trained_model_deployment_cacheClear trained model deployment cachewrite
  • elasticsearch.ml.forecastPredict future behavior of a time serieswrite
  • elasticsearch.ml.post_calendar_eventsAdd scheduled events to the calendarwrite
  • elasticsearch.ml.post_dataSend data to an anomaly detection job for analysiswrite
  • elasticsearch.ml.close_jobClose anomaly detection jobswrite
  • elasticsearch.ml.delete_calendarDelete a calendardestructive
  • and 84 more in this area
Security78
  • elasticsearch.security.activate_user_profileActivate a user profilewrite
  • elasticsearch.security.bulk_put_roleBulk create or update roleswrite
  • elasticsearch.security.bulk_update_api_keysBulk update API keyswrite
  • elasticsearch.security.clone_api_keyClone an API keywrite
  • elasticsearch.security.authenticateAuthenticate a userread
  • elasticsearch.security.bulk_delete_roleBulk delete rolesdestructive
  • and 72 more in this area
Core61
  • elasticsearch.core.create_documentCreate a new document in the indexwrite
  • elasticsearch.core.index_documentCreate or update a document in an indexwrite
  • elasticsearch.core.index_document_by_idCreate or update a document in an indexwrite
  • elasticsearch.core.mgetGet multiple documentsread
  • elasticsearch.core.mget_by_indexGet multiple documentsread
  • elasticsearch.core.bulkBulk index or delete documentswrite
  • and 55 more in this area
Inference49
  • elasticsearch.inference.chat_completion_unifiedPerform streaming chat completion inference on the servicewrite
  • elasticsearch.inference.completionPerform completion inference on the servicewrite
  • elasticsearch.inference.embeddingPerform dense embedding inference on the servicewrite
  • elasticsearch.inference.inferencePerform inference on the servicewrite
  • elasticsearch.inference.inference_by_task_typePerform inference on the servicewrite
  • elasticsearch.inference.deleteDelete an inference endpointdestructive
  • and 43 more in this area
Cat45
  • elasticsearch.cat.nodeattrsGet node attribute informationread
  • elasticsearch.cat.nodesGet node informationread
  • elasticsearch.cat.thread_poolGet thread pool statisticsread
  • elasticsearch.cat.thread_pool_by_thread_pool_patternsGet thread pool statisticsread
  • elasticsearch.cat.aliasesGet aliasesread
  • elasticsearch.cat.aliases_by_nameGet aliasesread
  • and 39 more in this area
Connector30
  • elasticsearch.connector.check_inCheck in a connectorwrite
  • elasticsearch.connector.getGet a connectorread
  • elasticsearch.connector.listGet all connectorsread
  • elasticsearch.connector.postCreate a connectorwrite
  • elasticsearch.connector.deleteDelete a connectordestructive
  • elasticsearch.connector.putCreate or update a connectorwrite
  • and 24 more in this area
Cluster20
  • elasticsearch.cluster.allocation_explainExplain the shard allocationsread
  • elasticsearch.cluster.get_component_templateGet component templatesread
  • elasticsearch.cluster.get_component_template_by_nameGet component templatesread
  • elasticsearch.cluster.pending_tasksGet the pending cluster tasksread
  • elasticsearch.cluster.delete_component_templateDelete component templatesdestructive
  • elasticsearch.cluster.delete_voting_config_exclusionsClear cluster voting config exclusionsdestructive
  • and 14 more in this area
Esql19
  • elasticsearch.esql.async_queryRun an async ES|QL querywrite
  • elasticsearch.esql.async_query_getGet async ES|QL query resultsread
  • elasticsearch.esql.get_queryGet a specific running ES|QL query informationread
  • elasticsearch.esql.queryRun an ES|QL queryread
  • elasticsearch.esql.async_query_deleteDelete an async ES|QL querydestructive
  • elasticsearch.esql.async_query_stopStop async ES|QL querywrite
  • and 13 more in this area
Nodes18
  • elasticsearch.nodes.infoGet node informationread
  • elasticsearch.nodes.info_by_metricGet node informationread
  • elasticsearch.nodes.info_by_node_idGet node informationread
  • elasticsearch.nodes.info_by_node_id_and_metricGet node informationread
  • elasticsearch.nodes.clear_repositories_metering_archiveClear the archived repositories meteringdestructive
  • elasticsearch.nodes.get_repositories_metering_infoGet cluster repositories meteringread
  • and 12 more in this area
Ingest16
  • elasticsearch.ingest.delete_pipelineDelete pipelinesdestructive
  • elasticsearch.ingest.get_pipelineGet pipelinesread
  • elasticsearch.ingest.get_pipeline_by_idGet pipelinesread
  • elasticsearch.ingest.processor_grokRun a grok processorread
  • elasticsearch.ingest.delete_geoip_databaseDelete GeoIP database configurationsdestructive
  • elasticsearch.ingest.delete_ip_location_databaseDelete IP geolocation database configurationsdestructive
  • and 10 more in this area
Snapshot16
  • elasticsearch.snapshot.createCreate a snapshotwrite
  • elasticsearch.snapshot.getGet snapshot informationread
  • elasticsearch.snapshot.statusGet the snapshot statusread
  • elasticsearch.snapshot.status_by_repositoryGet the snapshot statusread
  • elasticsearch.snapshot.status_by_repository_and_snapshotGet the snapshot statusread
  • elasticsearch.snapshot.cleanup_repositoryClean up the snapshot repositorywrite
  • and 10 more in this area
Watcher16
  • elasticsearch.watcher.activate_watchActivate a watchwrite
  • elasticsearch.watcher.execute_watchRun a watchwrite
  • elasticsearch.watcher.execute_watch_by_idRun a watchwrite
  • elasticsearch.watcher.query_watchesQuery watchesread
  • elasticsearch.watcher.ack_watchAcknowledge a watchwrite
  • elasticsearch.watcher.ack_watch_by_action_idAcknowledge a watchwrite
  • and 10 more in this area
Transform15
  • elasticsearch.transform.get_node_statsGet node statsread
  • elasticsearch.transform.get_transformGet transformsread
  • elasticsearch.transform.get_transform_by_transform_idGet transformsread
  • elasticsearch.transform.get_transform_statsGet transform statsread
  • elasticsearch.transform.delete_transformDelete a transformdestructive
  • elasticsearch.transform.preview_transformPreview a transformread
  • and 9 more in this area
CCR14
  • elasticsearch.ccr.followCreate a followerwrite
  • elasticsearch.ccr.follow_infoGet follower informationread
  • elasticsearch.ccr.follow_statsGet follower statsread
  • elasticsearch.ccr.get_auto_follow_patternGet auto-follow patternsread
  • elasticsearch.ccr.get_auto_follow_pattern_by_nameGet auto-follow patternsread
  • elasticsearch.ccr.delete_auto_follow_patternDelete auto-follow patternsdestructive
  • and 8 more in this area
Ilm12
  • elasticsearch.ilm.explain_lifecycleExplain the lifecycle stateread
  • elasticsearch.ilm.get_lifecycleGet lifecycle policiesread
  • elasticsearch.ilm.get_lifecycle_by_policyGet lifecycle policiesread
  • elasticsearch.ilm.get_statusGet the ILM statusread
  • elasticsearch.ilm.delete_lifecycleDelete a lifecycle policydestructive
  • elasticsearch.ilm.migrate_to_data_tiersMigrate to data tiers routingwrite
  • and 6 more in this area
Search application11
  • elasticsearch.search_application.getGet search application detailsread
  • elasticsearch.search_application.get_behavioral_analyticsGet behavioral analytics collectionsread
  • elasticsearch.search_application.get_behavioral_analytics_by_nameGet behavioral analytics collectionsread
  • elasticsearch.search_application.post_behavioral_analytics_eventCreate a behavioral analytics collection eventwrite
  • elasticsearch.search_application.searchRun a search application searchread
  • elasticsearch.search_application.deleteDelete a search applicationdestructive
  • and 5 more in this area
Rollup10
  • elasticsearch.rollup.get_jobsGet rollup job informationread
  • elasticsearch.rollup.get_jobs_by_idGet rollup job informationread
  • elasticsearch.rollup.get_rollup_capsGet the rollup job capabilitiesread
  • elasticsearch.rollup.get_rollup_caps_by_idGet the rollup job capabilitiesread
  • elasticsearch.rollup.rollup_searchSearch rolled-up dataread
  • elasticsearch.rollup.delete_jobDelete a rollup jobdestructive
  • and 4 more in this area
SLM10
  • elasticsearch.slm.execute_lifecycleRun a policywrite
  • elasticsearch.slm.execute_retentionRun a retention policywrite
  • elasticsearch.slm.get_lifecycleGet policy informationread
  • elasticsearch.slm.get_lifecycle_by_policy_idGet policy informationread
  • elasticsearch.slm.delete_lifecycleDelete a policydestructive
  • elasticsearch.slm.get_statsGet snapshot lifecycle management statisticsread
  • and 4 more in this area
Query rules8
  • elasticsearch.query_rules.get_ruleGet a query ruleread
  • elasticsearch.query_rules.get_rulesetGet a query rulesetread
  • elasticsearch.query_rules.list_rulesetsGet all query rulesetsread
  • elasticsearch.query_rules.testTest a query rulesetread
  • elasticsearch.query_rules.delete_ruleDelete a query ruledestructive
  • elasticsearch.query_rules.delete_rulesetDelete a query rulesetdestructive
  • and 2 more in this area
License7
  • elasticsearch.license.getGet license informationread
  • elasticsearch.license.postUpdate the licensewrite
  • elasticsearch.license.post_start_basicStart a basic licensewrite
  • elasticsearch.license.post_start_trialStart a trialwrite
  • elasticsearch.license.deleteDelete the licensedestructive
  • elasticsearch.license.get_basic_statusGet the basic license statusread
  • and 1 more in this area
Searchable snapshots7
  • elasticsearch.searchable_snapshots.cache_statsGet cache statisticsread
  • elasticsearch.searchable_snapshots.cache_stats_by_node_idGet cache statisticsread
  • elasticsearch.searchable_snapshots.clear_cacheClear the cachewrite
  • elasticsearch.searchable_snapshots.clear_cache_by_indexClear the cachewrite
  • elasticsearch.searchable_snapshots.mountMount a snapshotwrite
  • elasticsearch.searchable_snapshots.statsGet searchable snapshot statisticsread
  • and 1 more in this area
Synonyms7
  • elasticsearch.synonyms.delete_synonymDelete a synonym setdestructive
  • elasticsearch.synonyms.get_synonymGet a synonym setread
  • elasticsearch.synonyms.get_synonym_ruleGet a synonym ruleread
  • elasticsearch.synonyms.get_synonyms_setsGet all synonym setsread
  • elasticsearch.synonyms.delete_synonym_ruleDelete a synonym ruledestructive
  • elasticsearch.synonyms.put_synonymCreate or update a synonym setwrite
  • and 1 more in this area
Enrich6
  • elasticsearch.enrich.execute_policyRun an enrich policywrite
  • elasticsearch.enrich.get_policyGet an enrich policyread
  • elasticsearch.enrich.get_policy_by_nameGet an enrich policyread
  • elasticsearch.enrich.statsGet enrich statsread
  • elasticsearch.enrich.delete_policyDelete an enrich policydestructive
  • elasticsearch.enrich.put_policyCreate an enrich policywrite
SQL6
  • elasticsearch.sql.clear_cursorClear an SQL search cursorwrite
  • elasticsearch.sql.get_asyncGet async SQL search resultsread
  • elasticsearch.sql.get_async_statusGet the async SQL search statusread
  • elasticsearch.sql.queryGet SQL search resultsread
  • elasticsearch.sql.delete_asyncDelete an async SQL searchdestructive
  • elasticsearch.sql.translateTranslate SQL into Elasticsearch queriesread
Async search5
  • elasticsearch.async_search.getGet async search resultsread
  • elasticsearch.async_search.statusGet the async search statusread
  • elasticsearch.async_search.submitRun an async searchwrite
  • elasticsearch.async_search.submit_by_indexRun an async searchwrite
  • elasticsearch.async_search.deleteDelete an async searchdestructive
Eql4
  • elasticsearch.eql.deleteDelete an async EQL searchdestructive
  • elasticsearch.eql.getGet async EQL search resultsread
  • elasticsearch.eql.get_statusGet the async EQL statusread
  • elasticsearch.eql.searchGet EQL search resultsread
Fleet4
  • elasticsearch.fleet.global_checkpointsGet global checkpointsread
  • elasticsearch.fleet.msearchRun multiple Fleet searchesread
  • elasticsearch.fleet.msearch_by_indexRun multiple Fleet searchesread
  • elasticsearch.fleet.searchRun a Fleet searchread
Logstash4
  • elasticsearch.logstash.delete_pipelineDelete a Logstash pipelinedestructive
  • elasticsearch.logstash.get_pipelineGet Logstash pipelinesread
  • elasticsearch.logstash.get_pipeline_by_idGet Logstash pipelinesread
  • elasticsearch.logstash.put_pipelineCreate or update a Logstash pipelinewrite
Migration4
  • elasticsearch.migration.deprecationsGet deprecation informationread
  • elasticsearch.migration.deprecations_by_indexGet deprecation informationread
  • elasticsearch.migration.get_feature_upgrade_statusGet feature migration informationread
  • elasticsearch.migration.post_feature_upgradeStart the feature migrationwrite
Tasks4
  • elasticsearch.tasks.cancelCancel a taskdestructive
  • elasticsearch.tasks.cancel_by_task_idCancel a taskdestructive
  • elasticsearch.tasks.getGet task informationread
  • elasticsearch.tasks.listGet all tasksread
Text structure4
  • elasticsearch.text_structure.find_field_structureFind the structure of a text fieldread
  • elasticsearch.text_structure.find_message_structureFind the structure of text messagesread
  • elasticsearch.text_structure.find_structureFind the structure of a text fileread
  • elasticsearch.text_structure.test_grok_patternTest a Grok patternread
Dangling indices3
  • elasticsearch.dangling_indices.delete_dangling_indexDelete a dangling indexdestructive
  • elasticsearch.dangling_indices.import_dangling_indexImport a dangling indexwrite
  • elasticsearch.dangling_indices.list_dangling_indicesGet the dangling indicesread
Streams3
  • elasticsearch.streams.logs_disableDisable a named streamwrite
  • elasticsearch.streams.logs_enableEnable a named streamwrite
  • elasticsearch.streams.statusGet the status of streamsread
Features2
  • elasticsearch.features.get_featuresGet the featuresread
  • elasticsearch.features.reset_featuresReset the featuresdestructive
Simulate2
  • elasticsearch.simulate.ingestSimulate data ingestionread
  • elasticsearch.simulate.ingest_by_indexSimulate data ingestionread
Xpack2
  • elasticsearch.xpack.infoGet informationread
  • elasticsearch.xpack.usageGet usage informationread
Graph1
  • elasticsearch.graph.exploreExplore graph analyticsread
SSL1
  • elasticsearch.ssl.certificatesGet SSL certificatesread

This index shows a sample of each area. All 711 actions, with their inputs and prices, are in the catalogue, which a free sandbox key can search.

Questions

The Elasticsearch MCP server, answered.

Is there an Elasticsearch MCP server for Claude?

Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 711 Elasticsearch actions across indices, ML, security and core, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by Elasticsearch.

What do I need to connect Elasticsearch?

Elasticsearch API key, the base64 `encoded` value (Kibana > Stack Management > API keys > Create API key, or POST…. Plus your host. The free call account { op: "connections.requirements", service: "elasticsearch" } lists exactly what to paste.

Can an AI agent delete or change things in Elasticsearch?

Only if its key allows it, and only with an explicit confirmation. 92 Elasticsearch actions are destructive, including delete snapshots, delete indices and delete documents. Each runs only with confirm: true. Under the human confirm policy, or an approval rule on the key, the run waits until a named person approves it.

Will an AI agent use up my Elasticsearch API limit?

actionlake paces every call to the limits in the Elasticsearch service file: 600 calls a minute per connection.

What does an Elasticsearch action cost?

One upstream call, the only unit actionlake bills. A list that pages bills one call per page (711 Elasticsearch actions page). Cache hits, searches, dry runs and calls Elasticsearch refused with 401, 403, 429 or a 5xx are free. The Free plan includes 100,000 calls a month with no card. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000.

Which Elasticsearch API does it cover?

The Elasticsearch REST API 9.x (elasticsearch-specification main) at your Elasticsearch instance's API base URL, which you enter when connecting. It is built from Elasticsearch's documentation as read on 22 October 2026. 711 actions in 39 areas, each one in the signed service file (version 1.0.0).

Does actionlake keep my Elasticsearch data, and where?

actionlake processes and stores data in Sydney, Australia; there is no US region yet. Elasticsearch responses are not cached. Each run's request and response is kept, sealed, for your plan's trace window: 1 day on Free, 3 days on Starter, 7 days on Pro, 14 days on Team, 30 days on Business and 30 days on Enterprise. Your Elasticsearch credential is sealed under your tenant's key, never logged and never returned. Your traffic is not used to train models.

Which AI clients can use it?

Claude Code, tested by us end to end, and the Claude app as a custom connector, tested by us with an existing key. Other MCP clients that support remote servers over Streamable HTTP (MCP revisions 2025-06-18 and 2025-11-25) and OAuth dynamic client registration, or a bearer header, should connect the same way; we have not tested them. Or plain REST, under the same action names.

Give your agent Elasticsearch today.

Start free - 100,000 calls/month, no card. No signup. Hard caps on every key. Cached answers are free.