Drata MCP Server
for AI Agents

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

The StackOne Drata 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.

Production-ready Drata MCP server with 57 extensible actions — plus built-in authentication, security, and optimized execution.

Start Free Book Demo Read Docs →

Drata MCP Server

Built by

StackOne

Coverage

57 Agent Actions

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

MCP Actions → Create Actions →

Authentication

Agent Tool Authentication

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

Agent Auth →

Security

Agent Protection

Every Drata 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 Drata call.

Tools Discovery →

What is the Drata MCP Server?

A Drata MCP server lets AI agents read and write Drata data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Drata MCP server ships with 57 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, and optimized agent context. Connect it from MCP clients like Claude Desktop, Cursor, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.

All Drata MCP Tools and Actions

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

Controls

Create Control
Add a new control to the account
List Controls
Retrieve a list of all compliance controls with optional filtering
Get Control
Retrieve detailed information about a specific control
Update Control
Edit an existing control

Control Evidences

Upload Control Evidence
Upload external evidence document for a specific control
Get Control Evidence
Retrieve external evidence documents for a specific control

Control Notes

List Control Notes
Retrieve all notes associated with a specific control
Get Control Note
Retrieve a specific note associated with a control by note ID

Devices

List Devices
Retrieve a list of all devices in the inventory with filtering options
Get Device
Retrieve detailed information about a specific device

Evidences

List Evidence
Retrieve a list of all evidence in the evidence library with filtering and search options
Get Evidence
Retrieve detailed information about a specific evidence

Personnels

List Personnel
List personnel records with search terms and filters
Get Personnel
Get the full detail of a personnel record by ID

Trust Center Requests

List Trust Center Requests
List access requests with search and filter options
Get Trust Center Request
Get details of a specific Trust Center access request by ID

Users

List Users
List users with search terms and filters
Get User
Get the full detail of a user record by ID

Vendors

List Vendors
List vendors with search terms and filters
Get Vendor
Get a vendor by ID

Workspaces

List Workspaces
Retrieve a list of all workspaces (useful for finding Workspace IDs for POST/PUT requests)
Get Workspace
Retrieve detailed information about a specific workspace

Other (35)

Upload Personnel Document
Upload an evidence document for a specific user (e.g., security training certificate)
List Assets
Find assets by search terms and filters
Get Company Info
Retrieve comprehensive information about the company including settings, domains, and compliance configuration
Get Control Evidence Download URL
Generate download URL for a zip file containing all control evidence
Get Control Requirements
Retrieve all mapped requirements from a specific control
Get Control Owners
Retrieve control owners for a specific control
List Customer Requests
Get customer request list with filters
Get Device Apps
Retrieve a list of apps associated with a specific device
List Device Documents
Retrieve a list of documents for a specific device with optional type filtering
Get Device Document Download URL
Generate a download URL for a specific device document
Get Evidence Download URL
Generate a pre-signed download URL for an evidence file
List Monitoring Tests
Retrieve a list of all automated monitoring tests with filtering and search options
Get Monitoring Test Details
Retrieve detailed information about a specific monitor
Get Monitoring Test Failures
Retrieve failed test results for a specific monitor
Get Personnel By Email
Get the full detail of a personnel record by email address
List Policies
List all policies with their metadata
Get Policy
Get a policy by ID
Get Policy Version Download URL
Get signed download URL for a specific policy version
Get Policy Download URL
Get signed download URL for policy's current published version
Get Policy PDF Download URL
Get signed download URL for policy's current published PDF version
List Policy Associated Controls
Get controls associated with a policy
List Trust Center Controls
Get monitoring controls information from Trust Center
List Trust Center Reports
Generate Trust Center reports for a specific date range and report type
List Trust Center Private Documents
List private documents with optional name filter
Get Trust Center Private Access
Get private access information for Trust Center
List Infrastructure User Identities
List infrastructure user identities by username or email
List Version Control User Identities
List user version control identities for the target client type
Get User By Email
Get the full detail of a user record by email address
List User Policies
List policy acknowledgements for a user
List User Documents
List documents for a specific user with optional filters
Get User Document Download URL
Get signed download link for a user document
Get Vendors Statistics
Get vendor statistics with inclusion and exclusion filters
List Vendor Questionnaires
List questionnaires for a specific vendor
Get Questionnaire Answers
Get answers for a specific questionnaire and vendor
Get Questionnaires Sent By Vendor
Get all questionnaires sent to a specific vendor

Set Up Your Drata MCP Server in Minutes

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

MCP Clients

Agent Frameworks

Claude Desktop-

JSON

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>"
      ]
    }
  }
}

More Security MCP Servers

137+ actions

109+ actions

69+ actions

67+ actions

53+ actions

37+ actions

Okta

32+ actions

All Security MCP Servers →

Drata MCP Server 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

Drata MCP Server FAQ

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

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

How does Drata authentication work for AI agents?

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

Are Drata MCP tools vulnerable to prompt injection?

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

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

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

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

When should I NOT use a Drata MCP server?

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

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

The StackOne Drata 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

Drata MCP Serverfor AI Agents