Connect
Optimize
Secure
Airship MCP Server
for AI Agents
Production-ready Airship MCP server with 38 extensible actions — plus built-in authentication, security, and optimized execution.
Airship MCP Server
Built by 
StackOne
StackOne 
Coverage
38 Agent Actions
Create, read, update, and delete across Airship — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Airship MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Airship 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 Airship call.
Tools Discovery →What is the Airship MCP Server?
A Airship MCP server lets AI agents read and write Airship data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Airship MCP server ships with 38 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 Airship MCP Tools and Actions
Every action from Airship's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Attribute Lists
- Create Attribute List
Create a new attribute list
- List Attribute Lists
Retrieve all attribute lists
Segments
- Create Segment
Create a new audience segment
- List Segments
List all segments for the application
- Get Segment
Retrieve a specific segment by ID
- Update Segment
Update an existing segment
- Delete Segment
Delete a segment from the application
Static Lists
- Create Static List
Create a new static list
- List Static Lists
Retrieve all static lists
- Get Static List
Retrieve a specific static list by name
- Delete Static List
Delete a static list
Static List CSVs
- Upload Static List CSV
Upload CSV content to a static list
- Download Static List CSV
Download contents of a static list as CSV
Tag Lists
- Create Tag List
Create a new tag list
- Upload Tag List
Upload CSV data to a tag list
- List Tag Lists
List all tag lists for the application
- Delete Tag List
Delete a tag list
Schedules
- List Schedules
List all scheduled notifications
- Get Schedule
Retrieve a specific scheduled notification
Scheduled Notifications
- Create Scheduled Notification
Schedule a push notification for future delivery
- Update Scheduled Notification
Update an existing scheduled notification
- Delete Scheduled Notification
Cancel and delete a scheduled notification
Templates
- Create Template
Create a new message template
- List Templates
List all message templates for the application
- Get Template
Retrieve a specific template by ID
- Update Template
Update an existing message template
- Delete Template
Delete a message template
Other (11)
- Upload Attribute List CSV
Upload CSV data to an attribute list
- Get Attribute List Errors
Download errors from attribute list processing
- List Pipelines
List all automation pipelines
- List Deleted Pipelines
List all deleted pipelines
- List Filtered Pipelines
List pipelines with filter criteria
- Get Pipelines Limits
Get pipeline limits and counts
- Get Pipelines Constraints
Get cross-pipeline rate limit constraints
- Get Tag List Errors
Download errors from tag list processing
- Update Static List Metadata
Update metadata for a static list
- Pause Schedule
Pause a recurring scheduled notification
- Resume Schedule
Resume a paused scheduled notification
Set Up Your Airship MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Airship in under 10 lines of code.
MCP Clients
Agent Frameworks
JSON{
"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>"
]
}
}
}Airship 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
Airship MCP Server FAQ
Airship MCP server vs direct API integration — what's the difference?
A Airship MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Airship. A Airship 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 Airship at runtime. StackOne provides both.
How does Airship authentication work for AI agents?
Airship 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 Airship account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Airship MCP tools vulnerable to prompt injection?
Yes — Airship 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 Airship agent and how do I avoid it?
Context bloat happens when Airship tool schemas and API responses eat your Airship agent's memory, preventing it from reasoning effectively. A single Airship 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 Airship agent can access?
Yes — you can limit which actions your Airship 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 Airship MCP server?
Yes — you can create custom agent actions for your Airship MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Airship's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Airship MCP server?
Skip a Airship MCP server if your integration is purely software-to-software — direct Airship 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 Airship actions at runtime.
What AI frameworks and AI clients does the StackOne Airship MCP server support?
The StackOne Airship 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.