Live 50 Actions

Elastic Cloud MCP Server
for AI Agents

Q: What AI frameworks and AI clients does the StackOne Elastic Cloud MCP server support?

The StackOne Elastic Cloud MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.

Connect your AI agent to StackOne's Elastic Cloud MCP server and give it 50 MCP tools out of the box. Auth, tool execution, and security all managed.

Start Free Book Demo Read Docs →

Elastic Cloud MCP Server

Built by

StackOne

Coverage

50 Agent Actions

Create, read, update, and delete across Elastic Cloud — and extend your agent's capabilities with custom actions.

MCP Actions → Build Actions →

Authentication

Agent Tool Authentication

Per-user OAuth in one call. Your Elastic Cloud MCP server gets session-scoped tokens with zero credentials stored on your infra.

Agent Auth →

Security

Agent Protection

Every Elastic Cloud tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.

Prompt Injection Defense →

Performance

Max Agent Context. Min Cost.

Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Elastic Cloud call.

Tools Discovery →

What is the Elastic Cloud MCP Server?

A Elastic Cloud MCP server lets AI agents read and write Elastic Cloud data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Elastic Cloud MCP server ships with 50 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, observability, and agent execution runtime. Connect it from MCP clients like Claude Desktop, Claude Code, Cursor, Goose, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.

All Elastic Cloud MCP Tools

Every action from Elastic Cloud's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.

Accounts

Get Account
Get the current account information.
Update Account
Update the current account trust settings.

Deployments

Create Deployment
Create a new Elastic Cloud deployment.
List Deployments
Get a list of all deployments in the Elastic Cloud organization.
Get Deployment
Get detailed information about a specific deployment.
Search Deployments
Search for deployments using Elasticsearch-style queries.
Update Deployment
Update an existing Elastic Cloud deployment.

The Tags For A Deployments

Get The Tags For A Deployment
Get the tags associated with a deployment.
Set The Tags For A Deployment
Set tags on a deployment (replaces all existing tags).

Extensions

Create Extension
Create a new custom extension (plugin or bundle).
List Extensions
Get a list of all custom extensions (plugins and bundles).
Get Extension
Get details of a specific extension.
Update Extension
Update an extension's metadata.
Delete Extension
Delete a custom extension.

Elasticsearch Keystores

Get Elasticsearch Keystore
Get the keystore items for an Elasticsearch resource.
Update Elasticsearch Keystore
Add or remove items from the Elasticsearch keystore.

Organizations

List Organizations
Get a list of all organizations the current user belongs to.
Get Organization
Get details of a specific organization.

Organization Members

List Organization Members
Get a list of all members in an organization.
Remove Organization Members
Remove one or more members from an organization.

Organization Invitations

Send Organization Invitations
Send invitations to join an organization.
List Organization Invitations
Get a list of pending invitations for an organization.

Remote Clusters

Get Remote Clusters
Get the certificate-based remote clusters configured for an Elasticsearch resource.
Set Remote Clusters
Configure certificate-based remote clusters for an Elasticsearch resource.

Role Assignments

Add Role Assignments
Add role assignments to a user.
Remove Role Assignments
Remove role assignments from a user.

Traffic Filter Rulesets

Create Traffic Filter Ruleset
Create a new traffic filter ruleset.
List Traffic Filter Rulesets
Get a list of all traffic filter rulesets.
Get Traffic Filter Ruleset
Get details of a specific traffic filter ruleset.
Update Traffic Filter Ruleset
Update an existing traffic filter ruleset.
Delete Traffic Filter Ruleset
Delete a traffic filter ruleset.

Ruleset Associations

Create Ruleset Association
Link a traffic filter ruleset to a deployment.
Delete Ruleset Association
Unlink a traffic filter ruleset from a deployment.

Other (17)

Create Snapshot Repository For Elasticsearch Resource
Link a snapshot repository from a source deployment.
Get Deployment Templates
Get a list of available deployment templates for a specific region.
Get Deployment Elasticsearch Resource
Get information about an Elasticsearch resource within a deployment.
Get Deployment Kibana Resource
Get information about a Kibana resource within a deployment.
Get Upgrade Assistant Status
Get the upgrade readiness status for a deployment.
Get Trusted Environments
Get the trusted environments for the organization.
List Attached Snapshot Repositories
Get the snapshot repositories attached to an Elasticsearch resource.
Get Stack Versions
Get a list of available Elastic Stack versions.
Get Associated Deployments
Get the deployments associated with a traffic filter ruleset.
Get Associated Rulesets
Get the traffic filter rulesets associated with a specific deployment.
Remove Snapshot Repository From Elasticsearch Resource
Remove a snapshot repository from an Elasticsearch resource.
Shut Down Deployment
Shut down an Elastic Cloud deployment and all its resources.
Restore Shut Down Deployment
Restore a previously shut down Elastic Cloud deployment.
Start Resource Instances
Start all instances of a deployment resource.
Stop Resource Instances
Stop all instances of a deployment resource.
Cancel Pending Plan
Cancel the pending plan for a deployment resource.
Restart Deployment Elasticsearch Resource
Restart the Elasticsearch resource within a deployment.

Set Up Your Elastic Cloud MCP Server in Minutes

One endpoint. Any framework. Your agent is talking to Elastic Cloud in under 10 lines of code.

MCP Clients

Agent Frameworks

Claude Desktop-

JSON

Claude Desktop Docs

{
  "mcpServers": {
    "stackone": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://api.stackone.com/mcp?x-account-id=<account_id>",
        "--header",
        "Authorization: Basic <YOUR_BASE64_TOKEN>"
      ]
    }
  }
}

Platform Resources

MCP Code Mode: Keeping Tool Responses Out of Agent Context

Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.

11 min

Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery

Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.

10 min

Indirect Prompt Injection Defense for MCP Tools: A Technical Guide

MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.

12 min

MCP vs A2A: Architecture, Security, and When to Use Each

MCP vs A2A: what each protocol standardizes, how they differ, their shared security risks including indirect prompt injection, and when to use one, both, or a hybrid architecture.

12 min

MCP vs API: What 200+ Connector Builds Taught Us

MCP wraps APIs, it doesn't replace them. After building 200+ connectors that serve both, here's when each approach wins.

14 min read

Elastic Cloud MCP Server FAQ

Does StackOne have a Elastic Cloud MCP server?

Yes. StackOne offers a hosted Elastic Cloud MCP server with 50 pre-built actions, and every action is tested and QA'd by StackOne. Connect it to Claude, Cursor, and any other MCP client, or to any agent framework through the AI Action SDK. It ships with managed agent authentication, prompt injection defense, and tool discovery with server-side execution that preserve your agent's context window and keep reasoning performance.

Elastic Cloud MCP server vs direct API integration — what's the difference?

A Elastic Cloud MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Elastic Cloud. A Elastic Cloud MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling Elastic Cloud at runtime. StackOne provides both.

How does Elastic Cloud authentication work for AI agents?

Elastic Cloud authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Elastic Cloud account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via origin_owner_id.

Are Elastic Cloud MCP tools vulnerable to prompt injection?

Yes — Elastic Cloud MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.

What is the context bloat of a Elastic Cloud agent and how do I avoid it?

Context bloat happens when Elastic Cloud tool schemas and API responses eat your Elastic Cloud agent's memory, preventing it from reasoning effectively. A single Elastic Cloud query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.

Can I limit which actions my Elastic Cloud agent can access?

Yes — you can limit which actions your Elastic Cloud agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.

Can I create custom agent actions for my Elastic Cloud MCP server?

Yes — you can create custom agent actions for your Elastic Cloud MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Elastic Cloud's API, generate production-ready connector YAML, test against the live API, and validate before you ship.

When should I NOT use a Elastic Cloud MCP server?

Skip a Elastic Cloud MCP server if your integration is purely software-to-software — direct Elastic Cloud API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call Elastic Cloud actions at runtime.

What AI frameworks and AI clients does the StackOne Elastic Cloud MCP server support?

The StackOne Elastic Cloud MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.

Put your AI agents to work

All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.

Start Free Book Demo

Elastic Cloud MCP Serverfor AI Agents