Connect
Optimize
Secure
The #1 agentic semantic tool search: 91.6% first-try accuracy on S1 Search Bench • Explore Tool Discovery →
Connect your AI agent to StackOne's Loket MCP server and give it 61 MCP tools out of the box. Auth, tool execution, and security all managed.
Coverage
Create, read, update, and delete across Loket — and extend your agent's capabilities with custom actions.
Authentication
Per-user OAuth in one call. Your Loket MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →Security
Every Loket 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 Loket call.
Tools Discovery →A Loket MCP server lets AI agents read and write Loket data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Loket MCP server ships with 61 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.
Every action from Loket's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Retrieve a list of employers accessible to the authenticated user.
Update the details of an existing employer.
Create a new employment record for an existing employee.
Update the type and fields of an existing employment.
Create a new concept employee for a specific employer.
Update the details of an existing concept employee.
Delete a concept employee record.
Create a new payroll period data record for a specific employment.
Insert or update payroll period data records for a specific employment.
Create a new leave record for a specific employment.
Update the details of an existing leave record.
Delete a specific leave record by its unique identifier.
Create a new leave request for a specific employment.
Update the details of an existing leave request.
Create a new absence record for a specific employee.
Update the details of an existing absence record.
Delete a specific absence record by its unique identifier.
Create a new wage record for a specific employment.
Update the details of an existing wage record.
Delete a specific wage record by its unique identifier.
Create a new working hours record for a specific employment.
Update the details of an existing working hours record.
Delete a specific working hours record by its unique identifier.
Create a new department for a specific employer.
Update the details of an existing department.
Retrieve details of a specific employer by their unique identifier.
Retrieve a list of employees belonging to a specific employer.
Retrieve the full details of a specific employee by their unique identifier.
Retrieve a list of all employments for a specific employer.
Retrieve a list of all employments for a specific employee.
Retrieve the full details of a specific employment by its unique identifier.
Retrieve a list of concept employees for a specific employer.
Retrieve the full details of a specific concept employee by their unique identifier.
Retrieve a list of payroll administrations for a specific employer.
Retrieve a list of payroll runs for a specific payroll administration.
Retrieve the details of a specific payroll run by its ID.
Retrieve a list of payroll period data records for a specific employment.
Retrieve a list of payslips for a specific employment.
Download the payslip for a specific employment and payroll run.
Retrieve all leave records for a specific employment.
Retrieve a specific leave record by its unique identifier.
Retrieve all leave requests for a specific employment.
Retrieve all leave requests for the employees of a specific employer.
Retrieve details of a specific leave request by its unique identifier.
Retrieve all leave policies configured for a specific employer.
Retrieve a single leave policy by its ID.
Retrieve all absence records for a specific employee.
Retrieve details of a specific absence record by its unique identifier.
Retrieve all wage records for a specific employment.
Retrieve details of a specific wage record by its unique identifier.
Retrieve all working hours records for a specific employment.
Retrieve details of a specific working hours record by its unique identifier.
Retrieve all organizational entity records for a specific employment.
Retrieve details of a specific organizational entity record by its unique identifier.
Retrieve all departments for a specific employer.
Retrieve details of a specific department by its unique identifier.
Retrieve the profile of the currently authenticated user.
Update the details of an existing employee.
Terminate an active employment record.
Undo the termination of a previously terminated employment.
Convert a concept employee to a full active employee.
Connect your AI agent to Loket and help your team scale the HR operations they run by hand today.
Use StackOne to connect your AI agent to your HRIS, identity management, and LMS to automate employee onboarding.
ViewUse StackOne to connect your AI agent to your HRIS, knowledge base, and messaging tools to automate HR policy Q&A.
ViewUse StackOne to connect your AI agent to your HRIS, identity management, and ITSM to automate employee offboarding and deprovisioning.
ViewOne endpoint. Any framework. Your agent is talking to Loket in under 10 lines of code.
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>"
]
}
}
}87+ actions
51+ actions
50+ actions
50+ actions
44+ actions
36+ actions
30+ 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
MCP vs A2A: what each protocol standardizes, how they differ, their shared security risks including indirect prompt injection, and when to use one, both, or a hybrid architecture.
12 min
MCP wraps APIs, it doesn't replace them. After building 200+ connectors that serve both, here's when each approach wins.
14 min read
origin_owner_id.All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.