Skip to main content Announcing Tool Policies: AI agent permissions down to the field Read the announcement
Live 43 Actions

AirOps MCP Server
for AI Agents

Connect your AI agent to StackOne's AirOps MCP server and give it 43 MCP tools out of the box. Auth, tool execution, and security all managed.

AirOps logo
AirOps MCP Server
Built by StackOne StackOne
DrataGPLocalyzeFlipMindtoolsScreenloop

Coverage

43 Agent Actions

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

Authentication

Agent Tool Authentication

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

Agent Auth →

Security

Agent Protection

Every AirOps 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 AirOps call.

Tools Discovery →

What is the AirOps MCP Server?

A AirOps MCP server lets AI agents read and write AirOps data through the Model Context Protocol, Anthropic's open standard for connecting LLMs to external tools. StackOne's AirOps MCP server ships with 43 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 AirOps MCP Tools

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

Answers

  • List Answers

    List AI answers tracked for a Brand Kit

  • Get Answer

    Retrieve a tracked AI answer for a Brand Kit

Brand Kits

  • List Brand Kits

    List Brand Kits across workspaces

  • Get Brand Kit

    Retrieve a Brand Kit by ID

Citations

  • List Citations

    List cited URLs in AI answers for a Brand Kit

  • Get Citation

    Retrieve metrics for one cited URL for a Brand Kit

Competitors

  • List Competitors

    List competitors tracked for a Brand Kit

  • Get Competitor

    Retrieve a competitor tracked for a Brand Kit

Content Updates

  • Create Content Updates

    Record a page publish or refresh content update for a Brand Kit

  • List Content Updates

    List page content updates tracked for a Brand Kit

  • Get Content Update

    Retrieve a content update for a Brand Kit

Documents

  • Add Document

    Add a document to a Knowledge Base (memory store)

  • Update Document

    Update a document in a Knowledge Base (memory store)

  • Delete Document

    Delete a document from a Knowledge Base (memory store)

Personas

  • List Personas

    List personas defined for a Brand Kit

  • Get Persona

    Retrieve a persona defined for a Brand Kit

Prompts

  • List Prompts

    List AI prompts (questions) tracked for a Brand Kit

  • Get Prompt

    Retrieve a tracked AI prompt (question) for a Brand Kit

Tags

  • List Tags

    List prompt tags defined for a Brand Kit

  • Get Tag

    Retrieve a prompt tag defined for a Brand Kit

Topics

  • List Topics

    List prompt topics defined for a Brand Kit

  • Get Topic

    Retrieve a prompt topic defined for a Brand Kit

Other (21)

  • Upload Workspace File

    Upload a file to the workspace for use as an app input

  • List Agent Analytics

    List daily AI bot request counts for a Brand Kit tracked pages

  • List Apps

    List all apps (Workflows) in the workspace

  • Retrieve An App

    Retrieve an app (Workflow) by its UUID

  • Get Analytic

    Query Brand Kit AEO metrics such as mention rate, share of voice and citation rate

  • Retrieve An Execution

    Retrieve an execution by its UUID

  • List App Executions

    List executions for an app

  • Download Latest CSV

    Download the most recently generated CSV export of a Grid sheet

  • Search

    Semantically search a Knowledge Base (memory store)

  • Get Sentiment Theme Answer

    List AI answers with sentiment details for one sentiment theme

  • List Web Pages

    List tracked web pages with AEO, search and traffic metrics for a Brand Kit

  • Chat With Agent

    Send a message to an Agent app and wait for its reply

  • Async Chat With Agent

    Send a message to an Agent app without waiting for the reply

  • Destroy Content Updates

    Delete a content update from a Brand Kit

  • Execute

    Execute a published app synchronously and return its output

  • Async Execute

    Start an asynchronous execution of a published app

  • Webhook Async Execute

    Start an asynchronous app execution that posts its result to a webhook URL

  • Cancel An Execution

    Cancel a running execution

  • Retry An Execution

    Re-run a failed execution from its last failed step

  • Rate An Execution

    Rate an execution with feedback

  • Generate CSV

    Start generating a CSV export of a Grid sheet

AirOps AI Agent Use Cases

Connect your AI agent to AirOps and help your team scale the marketing operations they run by hand today.

Lead Nurture Sequences

Use StackOne to connect your AI agent to your marketing automation, CRM, and email tools to automate lead nurture email sequences.

View
HubSpotSalesforceActiveCampaignKlaviyoSendGridMailchimpLemlistGmail
Campaign Performance Reports

Use StackOne to connect your AI agent to your marketing automation, email, and analytics platforms to automate campaign performance reporting.

View
HubSpotMailchimpActiveCampaignKlaviyoSalesforceBrazeSendGridMarketo
Content Repurposing

Use StackOne to connect your AI agent to your document stores, email platforms, and messaging tools to automate content repurposing and distribution.

View
Google DriveConfluenceNotionMailchimpSendGridSlackGmailMicrosoft Teams

Set Up Your AirOps MCP Server in Minutes

One endpoint. Any framework. Your agent is talking to AirOps 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 marketing MCP Servers

AirOps MCP Server FAQ

Does StackOne have a AirOps MCP server?
Yes. StackOne offers a hosted AirOps MCP server with 43 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.
AirOps MCP server vs direct API integration: what's the difference?
A AirOps MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software work, where backend code calls AirOps. A AirOps MCP server is for AI agents that discover and call AirOps 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 AirOps authentication work for AI agents?
AirOps 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 AirOps account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via origin_owner_id.
Are AirOps MCP tools vulnerable to prompt injection?
Yes. AirOps 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 AirOps agent and how do I avoid it?
Context bloat happens when AirOps tool schemas and API responses eat your AirOps agent's memory, preventing it from reasoning effectively. A single AirOps 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 AirOps agent can access?
Yes. You can limit which actions your AirOps 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 AirOps MCP server?
Yes. You can create custom agent actions for your AirOps MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research AirOps's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a AirOps MCP server?
Skip a AirOps MCP server if your integration is purely software-to-software, because direct AirOps 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 AirOps actions at runtime.
What AI frameworks and AI clients does the StackOne AirOps MCP server support?
The StackOne AirOps 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.