Connect
Optimize
Secure
Announcing StackOne Defender: leading open-source prompt injection guard for your agent • Read More →
Production-ready Easyship MCP server with 48 extensible actions — plus built-in authentication, security, and optimized execution.
Coverage
Create, read, update, and delete across Easyship — and extend your agent's capabilities with custom actions.
Authentication
Per-user OAuth in one call. Your Easyship MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →Security
Every Easyship tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →Performance
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Easyship call.
Tools Discovery →A Easyship MCP server lets AI agents read and write Easyship data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Easyship MCP server ships with 48 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.
Every action from Easyship's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Create a new address
Update an address in your account
Upload a new asset
Retrieve a list of assets
Update an existing asset
Delete an asset
Create a box
Update a box in your account
Delete a box from your account
Create a new courier account
Retrieve details of a courier
Delete a LYOC courier
Create a new shipment
Retrieve a list of shipments with optional filters
Retrieve details of a specific shipment
Update shipment details
Delete a shipment that has not yet been shipped
Retrieve tracking status and checkpoint history for shipments
Retrieve a list of trackings available with your account
Create a single tracking in your account
Show a single tracking in your account
Delete a single tracking from your account
Create a new label for an existing shipment
Create a new tag
Retrieve information about current account
Retrieve account settings
Retrieve a list of countries
Retrieve a list of states
Retrieve a list of all addresses ordered by date of creation
Retrieve a list of available courier boxes and your custom boxes
Retrieve a list of active couriers
Retrieve a list of courier services for selected courier
Retrieve a list of available LYOC
List transaction records for a specific shipment
List unavailable couriers and reasons for a specific shipment
Retrieve a list of item categories
Retrieve a list of HS codes
Retrieve a list of stores
Retrieve a list of tags
List supported couriers for tracking
List courier services that do not support label generation but are trackable
Create an address validation for international addresses
Activate specific address
Deactivate specific address
Create a domestic address validation for US addresses
Deactivate a specific asset
Activate a specific asset
Cancel a shipment that has been shipped
One endpoint. Any framework. Your agent is talking to Easyship in under 10 lines of code.
MCP Clients
Agent Frameworks
{
"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>"
]
}
}
}162+ actions
133+ actions
125+ actions
125+ actions
120+ actions
73+ actions
69+ actions
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
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
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
origin_owner_id.All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.