Connect
Optimize
Secure
Announcing StackOne Defender: leading open-source prompt injection guard for your agent • Read More →
Production-ready Sage HR MCP server with 35 extensible actions — plus built-in authentication, security, and optimized execution.
Coverage
Create, read, update, and delete across Sage HR — and extend your agent's capabilities with custom actions.
Authentication
Per-user OAuth in one call. Your Sage HR MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →Security
Every Sage HR 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 Sage HR call.
Tools Discovery →A Sage HR MCP server lets AI agents read and write Sage HR data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Sage HR MCP server ships with 35 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 Sage HR's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Create a new employee in the company.
Retrieve a list of all active employees in the company.
Retrieve details of a specific active employee.
Update an existing employee's details.
Retrieve custom fields for a specific employee.
Update a custom field value for a specific employee.
Retrieve a list of all terminated employees.
Retrieve details of a specific terminated employee.
Create a new time-off request for an employee.
Retrieve a list of all time-off requests.
Upload a new document.
Retrieve a list of all documents.
Retrieve details of a specific document.
Update an existing document.
Delete a document.
Create a new onboarding task template.
Create a new offboarding task template.
Retrieve salary history for a specific employee.
Retrieve time-off balances for a specific employee.
Retrieve a list of all time-off policies.
Retrieve details of a specific time-off policy.
Retrieve a list of employees who are out of the office.
Retrieve individual leave allowances report.
Retrieve a list of all document categories.
Retrieve a list of all company positions.
Retrieve a list of all company teams.
Retrieve a list of all termination reasons.
Retrieve overall quarterly goals progress.
Retrieve company-level quarterly goals progress.
Retrieve team-level quarterly goals progress.
Retrieve individual-level quarterly goals progress.
Retrieve a list of all onboarding task categories.
Retrieve a list of all offboarding task categories.
Terminate an employee.
Rehire a previously terminated employee.
One endpoint. Any framework. Your agent is talking to Sage HR 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.