OpenSearch

Live 69 Actions

OpenSearch Integration for AI Agents

Connect your AI agent to 69 OpenSearch actions via MCP, A2A, or SDK, with agent authentication, tool-calling execution, and security built-in.

Start Free Book Demo OpenSearch MCP Server

OpenSearch AI Agent Actions

69 production-ready actions for your agent to do more on OpenSearch.

Read the OpenSearch docs

69 Actions

List Indices (Cat) - Compact tabular listing of every index — health, status, docs count, disk usage, shards.

Cat Cluster Health - One-line summary of cluster health — status, node counts, shard counts.

Cat Nodes - Per-node overview — heap, CPU, load, disk, role, and cluster-manager status.

List Aliases (Cat) - Compact tabular alias listing — alias, index, filter, routing, is_write_index.

Get Cluster Health - Snapshot of cluster health — status (green/yellow/red), active/relocating shards, and pending tasks. The canonical connection-health check.

Get Cluster Statistics - Aggregated statistics across the whole cluster — nodes, shards, storage, JVM heap, and OS/process metrics.

Get Cluster State - Full cluster state — routing table, metadata, node roster, and index settings. Very large payload; filter via the `metric` + `index` path segments.

Get Cluster Settings - Return persistent, transient, and default cluster settings.

Update Cluster Settings - Set persistent or transient cluster settings. Persistent settings survive restarts; transient do not.

List Cluster Pending Tasks - Tasks queued on the cluster manager but not yet executed — useful to spot backlogs during allocation storms.

Get Saved Object - Fetch a single Dashboards saved object (dashboard, visualization, index-pattern, etc.) by type + id.

Find Saved Objects - Search and paginate Dashboards saved objects. The canonical enumeration endpoint for datasync discovery.

Create Saved Object - Create a new Dashboards saved object.

Update Saved Object - Update the attributes of an existing Dashboards saved object.

Delete Saved Object - Delete a Dashboards saved object by type + id.

Bulk Get Saved Objects - Fetch many saved objects in a single request.

Export Saved Objects - Export a set of saved objects (with dependencies) as an NDJSON bundle. Response body is raw NDJSON text (one JSON object per line, newline-terminated) — pass it verbatim to `dashboards_import_saved_objects` (after base64-encoding) or parse each line with `JSON.parse` client-side.

Import Saved Objects - Import an NDJSON bundle of saved objects (produced by export or hand-crafted).

Index Document (Auto-ID) - Add a document to an index and let OpenSearch generate the ID.

Create Or Update Document (Explicit ID) - Index a document at a specific ID; overwrites if the ID already exists unless op_type=create.

Get Document By ID - Fetch a single document (source + metadata) by its ID.

Check Document Exists - Existence check for a document — returns 200 if the document exists, 404 if not.

Get Document Source Only - Fetch only the _source field of a document, without _seq_no / _primary_term / _version metadata.

Partial Update Document - Apply a partial update to a document using the update DSL (doc merge, script, or upsert).

Delete Document - Delete a document by ID.

Bulk Index/Update/Delete (NDJSON) - Execute many index/update/delete operations in a single request. **Body must be NDJSON** (newline-delimited JSON), not standard JSON — each operation is metadata line + optional source line.

Bulk Operations Scoped To One Index - Same NDJSON bulk semantics as bulk_operations, but scoped to a single index in the URL — operations can omit `_index` in their metadata.

Multi-Get Documents - Fetch multiple documents by ID in one round-trip, optionally across different indices.

Delete Documents By Query - Delete all documents matching a query in one call.

Update Documents By Query - Apply a script or noop update to every document matching a query.

Reindex Documents - Copy documents from a source index (or remote cluster) to a destination index; the canonical datasync migration primitive.

Create Index - Create a new index with optional settings, mappings, and aliases.

Get Index Info - Return the settings, mappings, and aliases of one or more indices.

Check Index Exists - Existence check for an index — 200 if it exists, 404 if not.

Delete Index - Permanently delete an index and all its data.

Update Mapping - Add new fields to an index mapping. Cannot change existing field types.

Get Mapping - Return the mapping (field types) for one or more indices.

Get Index Settings - Return the settings for one or more indices (shard count, replicas, analysis, refresh interval).

Update Index Settings - Update dynamic index settings (replica count, refresh interval, allocation, etc.).

Refresh Index - Force a refresh so recently indexed documents become searchable immediately.

Flush Index - Persist in-memory transaction log to disk.

Force Merge Index - Merge index segments to reduce their count; heavy operation.

Open Index - Re-open a closed index so it becomes readable/writable.

Close Index - Close an index so it stops accepting reads/writes; frees cluster resources.

Clone Index - Copy an existing index to a new name — source must have the write-block set before calling.

Atomic Update Of Aliases - Apply multiple alias add/remove operations atomically.

Add Alias To Index - Attach a single alias to a single index (non-atomic — use update_aliases for atomic swaps).

Delete Alias From Index - Remove an alias from an index.

Get Alias Info - Return details of a specific alias on a specific index (or across a wildcard set).

List All Aliases - Return every alias across every index (or a filtered subset).

Search Index - Full-text and structured search over one or more indices using the Query DSL.

Search Across All Indices - Same as search but without an index in the URL — required when using a Point-in-Time reference.

Multi-Search (NDJSON) - Run several searches in one round-trip; body is NDJSON with alternating header + query lines.

Count Documents Matching Query - Return the count of documents matching a query, without returning the hits themselves.

Scroll (Deep Pagination — Legacy) - Fetch the next batch of a scroll context. Discouraged for new work — use PIT + search_after instead.

Clear Scroll Context - Release the memory held by one or more scroll contexts.

Create Point-in-Time - Freeze an index at a moment in time so subsequent searches see a consistent view.

Delete Point-in-Time - Release a PIT so its heap can be reclaimed.

List Snapshot Repositories - Return every registered snapshot repository on the cluster.

Get Snapshot Repository - Return details of a specific repository (type, settings).

Delete Snapshot Repository - Unregister a snapshot repository. Does NOT delete the snapshots themselves — files remain in the backend storage.

List Snapshots In Repository - List snapshots in the given repository — companion LIST for the create/get/delete snapshot actions.

Take Snapshot - Create a snapshot of one or more indices to the target repository.

Get Snapshot Details - Return details of one or more snapshots — status, indices, start/end times, shard counts.

Delete Snapshot - Delete a snapshot and reclaim its unique segments from the repository.

Restore Snapshot - Restore indices from a snapshot back into the cluster.

Get Task - Fetch the status of a running or completed task by task_id.

Cancel Task - Cancel a running task by task_id. Cancellation is cooperative — the task ends at the next check point.

Do More, Build Less

Integration Infrastructure for OpenSearch AI Agents

Multiple Interfaces

Access integrations via API, AI SDKs, MCP & A2A.

OpenSearch MCP server

Managed Authentication

Pre-built authentication UI.

Agent auth

Falcon Engine

Every OpenSearch action runs on Falcon.

Agent Execution Engine

StackOne Defender

88.7% prompt injection detection.

Prompt injection defense

Start Free Book a Demo

"What impressed us most about StackOne is its ambition and clarity. They're creating infrastructure that modern software and the entire AI agent ecosystem can rely on. The depth of secure integrations, the pace of delivery, and the team's foresight into AI's future uniquely position StackOne to redefine this category."

Luna Schmid, Partner at GV

"We've been impressed by how quickly and deeply StackOne integrates with complex enterprise systems -- and now, with their focus on agent-to-agent interoperability, they're unlocking even more powerful use cases for customers. StackOne delivers all of the above in a universal layer -- without compromise."