Live 39 Actions

Duo Security MCP Server
for AI Agents

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

The StackOne Duo Security 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 Duo Security MCP server and give it 39 MCP tools out of the box. Auth, tool execution, and security all managed.

Start Free Book Demo Read Docs →

Duo Security MCP Server

Built by

StackOne

Coverage

39 Agent Actions

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

MCP Actions → Build Actions →

Authentication

Agent Tool Authentication

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

Agent Auth →

Security

Agent Protection

Every Duo Security 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 Duo Security call.

Tools Discovery →

What is the Duo Security MCP Server?

A Duo Security MCP server lets AI agents read and write Duo Security data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Duo Security MCP server ships with 39 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 Duo Security MCP Tools

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

Users

Create User
Create a new Duo user via POST /admin/v1/users
List Users
Retrieve a paginated list of Duo users via GET /admin/v1/users
Get User
Retrieve a specific Duo user by ID via GET /admin/v1/users/{user_id}
Update User
Update an existing Duo user via POST /admin/v1/users/{user_id}
Delete User
Permanently delete a Duo user via DELETE /admin/v1/users/{user_id}

Groups

Create Group
Create a new Duo group via POST /admin/v1/groups
List Groups
Retrieve a paginated list of Duo groups via GET /admin/v1/groups
Get Group
Retrieve a specific Duo group by ID via GET /admin/v1/groups/{group_id}
Update Group
Update an existing Duo group via POST /admin/v1/groups/{group_id}
Delete Group
Delete a Duo group via DELETE /admin/v1/groups/{group_id}

Administrators

Create Administrator
Create a new Duo administrator via POST /admin/v1/admins
List Administrators
Retrieve a paginated list of Duo administrators via GET /admin/v1/admins
Get Administrator
Retrieve a specific Duo administrator by ID via GET /admin/v1/admins/{admin_id}
Update Administrator
Update an existing Duo administrator via POST /admin/v1/admins/{admin_id}
Delete Administrator
Delete a Duo administrator via DELETE /admin/v1/admins/{admin_id}

Phones

Create Phone
Create a new Duo phone via POST /admin/v1/phones
List Phones
Retrieve a paginated list of Duo phones via GET /admin/v1/phones
Get Phone
Retrieve a specific Duo phone by ID via GET /admin/v1/phones/{phone_id}
Update Phone
Update an existing Duo phone via POST /admin/v1/phones/{phone_id}
Delete Phone
Delete a Duo phone via DELETE /admin/v1/phones/{phone_id}

Hardware Tokens

Create Hardware Token
Create a new Duo hardware token via POST /admin/v1/tokens
List Hardware Tokens
Retrieve a paginated list of Duo hardware tokens via GET /admin/v1/tokens
Get Hardware Token
Retrieve a specific Duo hardware token by ID via GET /admin/v1/tokens/{token_id}
Update Hardware Token
Update an existing Duo hardware token via POST /admin/v1/tokens/{token_id}
Delete Hardware Token
Delete a Duo hardware token via DELETE /admin/v1/tokens/{token_id}

Integrations

Create Integration
Create a new Duo integration via POST /admin/v1/integrations
List Integrations
Retrieve a paginated list of Duo integrations via GET /admin/v1/integrations
Get Integration
Retrieve a specific Duo integration by key via GET /admin/v1/integrations/{integration_key}
Update Integration
Update an existing Duo integration via POST /admin/v1/integrations/{integration_key}
Delete Integration
Delete a Duo integration via DELETE /admin/v1/integrations/{integration_key}

Authentication Logs

List Authentication Logs
Retrieve authentication log events via GET /admin/v2/logs/authentication

Administrator Logs

List Administrator Logs
Retrieve administrator action log events via GET /admin/v1/logs/administrator

Telephony Logs

List Telephony Logs
Retrieve telephony log events via GET /admin/v2/logs/telephony

Offline Enrollment Logs

List Offline Enrollment Logs
Retrieve offline enrollment log events via GET /admin/v1/logs/offline_enrollment

Activity Logs

List Activity Logs
Retrieve activity log events via GET /admin/v2/logs/activity

Bulk Create Users

Bulk Create Users
Create multiple Duo users in a single request via POST /admin/v1/users/bulk_create

Bulk Restore Users

Bulk Restore Users
Restore multiple Duo users from the Trash via POST /admin/v1/users/bulk_restore

Bulk Send Users To Trashs

Bulk Send Users To Trash
Send multiple Duo users to the Trash via POST /admin/v1/users/bulk_send_to_trash

Bulk Operations

Bulk Operations
Execute multiple Duo API operations in a single request via POST /admin/v1/bulk

Set Up Your Duo Security MCP Server in Minutes

One endpoint. Any framework. Your agent is talking to Duo Security 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

Duo Security MCP Server FAQ

Does StackOne have a Duo Security MCP server?

Yes. StackOne offers a hosted Duo Security MCP server with 39 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.

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

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

How does Duo Security authentication work for AI agents?

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

Are Duo Security MCP tools vulnerable to prompt injection?

Yes — Duo Security 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 Duo Security agent and how do I avoid it?

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

Yes — you can limit which actions your Duo Security 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 Duo Security MCP server?

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

When should I NOT use a Duo Security MCP server?

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

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

The StackOne Duo Security 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

Duo Security MCP Serverfor AI Agents