Skip to main content Announcing Tool Policies: AI agent permissions down to the field Read the announcement
Live 33 Actions

Orca Security MCP Server
for AI Agents

Connect your AI agent to StackOne's Orca Security MCP server and give it 33 MCP tools out of the box. Auth, tool execution, and security all managed.

Orca Security logo
Orca Security MCP Server
Built by StackOne StackOne
DrataGPLocalyzeFlipMindtoolsScreenloop

Coverage

33 Agent Actions

Agents can read, write and run operations in Orca Security. Extend your agent's capabilities with custom actions.

Authentication

Agent Tool Authentication

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

Agent Auth →

Security

Agent Protection

Every Orca Security tool response scanned for prompt injection in milliseconds, with 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 Orca Security call.

Tools Discovery →

What is the Orca Security MCP Server?

A Orca Security MCP server lets AI agents read and write Orca Security data through the Model Context Protocol, Anthropic's open standard for connecting LLMs to external tools. StackOne's Orca Security MCP server ships with 33 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 Orca Security MCP Tools

Every StackOne action for Orca Security, ready for your agent. Read, write and run operations, scoped to exactly what you need.

Unified Organizations

  • List Unified Organizations

    List the Orca Security organization the connection belongs to.

  • Get Unified Organization

    Get the unified Orca Security organization of the connection by ID.

Unified Roles

  • List Unified Roles

    List the roles of an Orca Security organization.

  • Get Unified Role

    Get a unified Orca Security role by ID.

Unified Users

  • List Unified Users

    List unified users in an Orca Security organization.

  • Get Unified User

    Get a unified Orca Security user by ID.

Roles

  • List Roles

    List the roles of the Orca Security organization

  • Get Role

    Get the detail of a custom role in the Orca Security organization

Alerts

  • List Alerts

    List Orca security alerts, optionally filtered with a DSL expression and paged with a cursor.

  • Get Alert

    Retrieve a single Orca alert by its unique identifier.

  • Query Alerts

    Query Orca security alerts using the Orca DSL, with optional filters and cursor pagination.

Assets

  • List Assets

    List Orca cloud assets, optionally filtered and paged with an offset.

  • Get Asset

    Retrieve a single Orca cloud asset by its unique identifier.

  • Query Assets

    Query Orca cloud assets using the Orca DSL, with optional filters and cursor pagination.

Cloud Accounts

  • List Cloud Accounts

    List the cloud accounts connected to Orca, with filtering, sorting and cursor pagination.

  • Get Cloud Account

    Retrieve a single connected cloud account by its unique identifier.

Scans

  • Create Scan

    Launch an on-demand Orca security scan for one or more assets.

  • Get Scan

    Retrieve the status and progress of a specific Orca scan by its identifier.

Other (15)

  • Add Comment To Alert

    Attach a comment to one or more Orca alerts.

  • Get Group

    Get a group of the Orca Security organization

  • List Group Role Assignments

    List the role assignments of the groups in the Orca Security organization

  • List User Invitations

    List the invitations to the Orca Security organization, including expired ones

  • Get Current Organization

    Get the Orca Security organization of the connection

  • List User Role Assignments

    List the role assignments of the users in the Orca Security organization

  • List Users

    List the users of the Orca Security organization

  • List Alert Event Log

    Retrieve the event and change log for a specific Orca alert.

  • Query Inventory

    Query Orca cloud inventory using the Orca DSL, optionally returning a downloadable result link.

  • Query CVEs

    Query Orca CVE and vulnerability records using the Orca DSL, with cursor pagination.

  • Query Logs

    Query Orca log records using the Orca DSL, with cursor pagination.

  • Query Catalog

    Retrieve the catalog of predefined Orca queries available to the tenant.

  • Query Schema

    Retrieve the schema for an Orca query data type, or all available data-type schemas.

  • Update Alert Status

    Set the status of one or more Orca alerts in bulk.

  • Snooze Alerts

    Snooze one or more Orca alerts for a number of days.

Set Up Your Orca Security MCP Server in Minutes

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

Agent Frameworks

Claude Desktop
{
  "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 developer MCP Servers

Wiz

696+ actions

IONOS

501+ actions

Workiva

266+ actions

KnowBe4

259+ actions

HighLevel

251+ actions

WorkOS

234+ actions

SAP Concur

232+ actions

Orca Security MCP Server FAQ

Does StackOne have a Orca Security MCP server?
Yes. StackOne offers a hosted Orca Security MCP server with 33 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.
Orca Security MCP server vs direct API integration: what's the difference?
A Orca Security MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software work, where backend code calls Orca Security. A Orca Security MCP server is for AI agents that discover and call Orca Security at runtime, such as MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI. StackOne provides both.
How does Orca Security authentication work for AI agents?
Orca Security authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK to get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Orca Security account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via origin_owner_id.
Are Orca Security MCP tools vulnerable to prompt injection?
Yes. Orca Security MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content, such as 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. It runs regex patterns in ~1ms, then a MiniLM classifier in ~4ms. Accuracy is 88.7%, and it runs entirely on CPU.
What is the context bloat of a Orca Security agent and how do I avoid it?
Context bloat happens when Orca Security tool schemas and API responses eat your Orca Security agent's memory, preventing it from reasoning effectively. A single Orca Security query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery reduces it by loading only the tools relevant to each query.
Can I limit which actions my Orca Security agent can access?
Yes. You can limit which actions your Orca 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 Orca Security MCP server?
Yes. You can create custom agent actions for your Orca Security MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Orca Security's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Orca Security MCP server?
Skip a Orca Security MCP server if your integration is purely software-to-software, because direct Orca 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 Orca Security actions at runtime.
What AI frameworks and AI clients does the StackOne Orca Security MCP server support?
The StackOne Orca 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.