Connect
Optimize
Secure
Announcing StackOne Defender: leading open-source prompt injection guard for your agent • Read More →
Production-ready Simployer One MCP server with 54 extensible actions — plus built-in authentication, security, and optimized execution.
Coverage
Create, read, update, and delete across Simployer One — and extend your agent's capabilities with custom actions.
Authentication
Per-user OAuth in one call. Your Simployer One MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →Security
Every Simployer One 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 Simployer One call.
Tools Discovery →A Simployer One MCP server lets AI agents read and write Simployer One data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Simployer One MCP server ships with 54 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 Simployer One's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Retrieve a list of all companies in the Simployer account
Retrieve a specific company by its ID
Create a new compensation record
Retrieve a list of all compensations
Retrieve a specific compensation by its ID
Update an existing compensation record
Delete a compensation record by its ID
Create a new cost center
Retrieve a list of all cost centers
Retrieve a specific cost center by its ID
Update an existing cost center
Delete a cost center by its ID
Create a new department
Retrieve a list of all departments
Retrieve a specific department by its ID
Update an existing department
Delete a department by its ID
Create a new employee
Retrieve a list of all employees
Retrieve a specific employee by their ID
Update an existing employee
Delete an employee by their ID
Create a new employment type
Retrieve a list of all employment types
Retrieve a specific employment type by its ID
Update an existing employment type
Delete an employment type by its ID
Create a new employment record
Retrieve a list of all employments
Retrieve a specific employment by its ID
Update an existing employment record
Delete an employment record by its ID
Create a new leave type
Retrieve a list of all leave types
Retrieve a specific leave type by its ID
Update an existing leave type
Delete a leave type by its ID
Create a new leave request
Retrieve a list of all leaves
Retrieve a specific leave by its ID
Update an existing leave request
Delete a leave request by its ID
Retrieve a list of all offices
Retrieve a specific office by its ID
Create a new project
Retrieve a list of all projects
Retrieve a specific project by its ID
Update an existing project
Delete a project by its ID
Create a new team
Retrieve a list of all teams
Retrieve a specific team by its ID
Update an existing team
Delete a team by its ID
One endpoint. Any framework. Your agent is talking to Simployer One 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.