Connect
Optimize
Secure
Announcing StackOne Defender: leading open-source prompt injection guard for your agent • Read More →
Production-ready Deputy MCP server with 48 extensible actions — plus built-in authentication, security, and optimized execution.
Coverage
Create, read, update, and delete across Deputy — and extend your agent's capabilities with custom actions.
Authentication
Per-user OAuth in one call. Your Deputy MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →Security
Every Deputy 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 Deputy call.
Tools Discovery →A Deputy MCP server lets AI agents read and write Deputy data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Deputy 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 Deputy's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Create a new location in Deputy
Get all locations (companies) in the Deputy installation
Update an existing location in Deputy
Delete a location in Deputy
Add an employee
Get details for all employees
Get details for an employee by ID
Update an existing employee
Add unavailability details for an employee
Get unavailability details for an employee
Copy rosters from one date range to another
Publish rosters to make them visible to employees
Create a new operational unit (department/area)
Get all operational units (areas/departments)
Update an existing operational unit
Delete an operational unit
Add a new workplace/location to Deputy
Add a location against an employee
Create multiple operational units (departments/areas) at once
Create a memo in Deputy
Find out an employee's current status
Get all employee agreements
Search for employment contracts using query filters
Search for employment contract leave rules
Get all employee roles
Get all employee workplace assignments
Search for employee history records
Get all employee availability records
Get all employee appraisal records
Get all employee agreement history records
Get all employment condition records
Get rosters from last 12 hours and forward 36 hours
Get awards library list
Get agreed hours for a specific employee
Get sales metrics data
Get all categories
Get all custom field definitions
Get all events
Remove a location from an employee
Terminate an employee
Re-activate a terminated employee
Invite employee to Deputy
Post a journal entry for an employee
Start an employee's timesheet (Clock On)
Stop an employee's timesheet (Clock Off)
Pause or unpause an employee's timesheet (take a break/finish break)
View a timesheet by ID
Discard unpublished rosters
One endpoint. Any framework. Your agent is talking to Deputy 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>"
]
}
}
}140+ actions
128+ actions
127+ actions
123+ actions
120+ actions
117+ actions
100+ 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.