Live 51 Actions

Okta MCP Server
for AI Agents

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

The StackOne Okta 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 Okta MCP server and give it 51 MCP tools out of the box. Auth, tool execution, and security all managed.

Start Free Book Demo Read Docs →

Okta MCP Server

Built by

StackOne

Coverage

51 Agent Actions

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

MCP Actions → Build Actions →

Authentication

Agent Tool Authentication

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

Agent Auth →

Security

Agent Protection

Every Okta 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 Okta call.

Tools Discovery →

What is the Okta MCP Server?

A Okta MCP server lets AI agents read and write Okta data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Okta MCP server ships with 51 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 Okta MCP Tools

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

Devices

List Devices
Lists all devices with pagination support and flexible search options
Get Device
Retrieves a device by its ID
Delete Device
Permanently deletes a device. Device must be in DEACTIVATED status first.

Groups

Create Group
Adds a new group with OKTA_GROUP type to your org
List Groups
Lists all groups with pagination support
Get Group
Retrieves a specific group by ID from your org
Update Group
Replaces the profile for a group of OKTA_GROUP type
Delete Group
Deletes a group of OKTA_GROUP or APP_GROUP type from your org

Policys

Create Policy
Creates a new policy of the specified type. The returned policy ID can be used with get_policy, replace_policy, delete_policy, and policy rule actions.
Get Policy
Retrieves a specific policy by ID. Use list_policies to obtain the policyId.
Delete Policy
Deletes a policy by ID

Policy Rules

Create Policy Rule
Creates a new rule for a policy. Use list_policies to obtain the policyId. The created rule ID is returned in the response.
Delete Policy Rule
Deletes a policy rule. Use list_policy_rules to obtain the ruleId.

Realms

Create Realm
Creates a new Realm
List Realms
Lists all Realms with pagination support
Get Realm
Retrieves a Realm by its ID
Update Realm
Replaces the realm profile by its ID
Delete Realm
Deletes a Realm by its ID

Users

Create User
Creates a new user in your Okta org with or without credentials
List Users
Lists all users in your org with pagination and flexible query options
Get User
Retrieves a user from your Okta org by ID, login, or shortname
Update User
Updates a user's profile or credentials with partial update semantics
Delete User
Permanently deletes a user from your Okta organization

User Types

Create User Type
Creates a new user type in your Okta organization
List User Types
Lists all user types in your Okta organization
Get User Type
Retrieves a user type by ID
Update User Type
Partially updates an existing user type
Delete User Type
Permanently deletes a user type

Other (23)

Add User To Group
Assigns a user to a group with OKTA_GROUP type
Clone An Existing Policy
Clones an existing ACCESS_POLICY to create a copy
Create A Policy Simulation
Simulates a policy evaluation to test access outcomes
List Group Members
Lists all users that are a member of a group
List Policies
Lists all policies of a given type
List All Apps Mapped To A Policy
Lists all applications mapped to an ACCESS_POLICY. Use list_policies with type ACCESS_POLICY to obtain the policyId.
List All Resources Mapped To A Policy
Lists all resources mapped to a policy. Use list_policies to obtain the policyId.
Retrieve A Policy Resource Mapping
Retrieves a specific policy resource mapping. Use list_policy_mappings to obtain the mappingId.
List All Policy Rules
Lists all rules for a specific policy. Use list_policies to obtain the policyId first.
Retrieve A Policy Rule
Retrieves a specific rule for a policy
Get User Info
Retrieves information about the currently authenticated user from the OAuth 2.0 UserInfo endpoint.
List User Blocks
Lists information about how a user is blocked from accessing their account
Remove User From Group
Unassigns a user from a group with OKTA_GROUP type
Activate Device
Activates a device by setting its status to ACTIVE
Deactivate Device
Deactivates a device by setting its status to DEACTIVATED
Replace Policy
Replaces a policy with the provided data. Use list_policies or create_policy to obtain the policyId.
Activate Policy
Activates a policy by setting its status to ACTIVE
Deactivate Policy
Deactivates a policy by setting its status to INACTIVE
Replace Policy Rule
Replaces a policy rule with the provided data. Use list_policy_rules to obtain the ruleId.
Activate Policy Rule
Activates a policy rule. Use list_policy_rules to obtain the ruleId.
Deactivate Policy Rule
Deactivates a policy rule. Use list_policy_rules to obtain the ruleId.
Replace User
Replaces a user's profile, credentials, or both using strict-update semantics
Replace User Type
Fully replaces an existing user type

Set Up Your Okta MCP Server in Minutes

One endpoint. Any framework. Your agent is talking to Okta 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>"
      ]
    }
  }
}

Check More Security MCP Servers

Cloudflare

150+ actions

OneLogin

110+ actions

Auth0

78+ actions

JumpCloud

76+ actions

Sentinel XS

69+ actions

Microsoft Entra ID

68+ actions

Drata

64+ actions

All Security MCP Servers →

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

Okta MCP Server FAQ

Does StackOne have a Okta MCP server?

Yes. StackOne offers a hosted Okta MCP server with 51 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.

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

A Okta MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Okta. A Okta 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 Okta at runtime. StackOne provides both.

How does Okta authentication work for AI agents?

Okta 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 Okta account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via origin_owner_id.

Are Okta MCP tools vulnerable to prompt injection?

Yes — Okta 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 Okta agent and how do I avoid it?

Context bloat happens when Okta tool schemas and API responses eat your Okta agent's memory, preventing it from reasoning effectively. A single Okta 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 Okta agent can access?

Yes — you can limit which actions your Okta 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 Okta MCP server?

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

When should I NOT use a Okta MCP server?

Skip a Okta MCP server if your integration is purely software-to-software — direct Okta 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 Okta actions at runtime.

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

The StackOne Okta 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

Okta MCP Serverfor AI Agents