Live 8 Actions

Sage People MCP Server
for AI Agents

Q: What AI frameworks and AI clients does the StackOne Sage People MCP server support?

The StackOne Sage People MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.

Connect your AI agent to StackOne's Sage People MCP server and give it ready-to-use MCP tools out of the box. Auth, tool execution, and security all managed.

Start Free Book Demo Read Docs →

Sage People MCP Server

Built by

StackOne

Coverage

8 Agent Actions

Create, read, update, and delete across Sage People — and extend your agent's capabilities with custom actions.

MCP Actions → Build Actions →

Authentication

Agent Tool Authentication

Per-user OAuth in one call. Your Sage People MCP server gets session-scoped tokens with zero credentials stored on your infra.

Agent Auth →

Security

Agent Protection

Every Sage People tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.

Prompt Injection Defense →

Performance

Max Agent Context. Min Cost.

Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Sage People call.

Tools Discovery →

What is the Sage People MCP Server?

A Sage People MCP server lets AI agents read and write Sage People data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Sage People MCP server ships with 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.

All Sage People MCP Tools

Every action from Sage People's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.

Employees

List Employees
Get a paginated list of Sage People employees (workers). Backed by the Salesforce Team Member object (fHCM2__Team_Member__c). Supports cursor pagination via the `marker` parameter and server-side filtering via Microsoft `$filter` syntax. Requires the API user to have the "Sage People Employees API" Permission Set assigned.
Get Employee
Get a single Sage People employee by id. Returns the full employee record (profile, current employment, work address, additional fields). Requires the API user to have the "Sage People Employees API" Permission Set.

Salaries

List Salaries
Get a paginated list of Sage People salary records (compensation). Backed by the Salesforce fHCM2__Salary__c object. Each record has an employeeId FK back to Employee, amount, multiplier (e.g. 12 for monthly × 12 = annual), currency, start date, and pay code. Requires "Sage People Salaries API" Permission Set.

Bonuses

List Bonuses
Get a paginated list of Sage People bonus records (one-off compensation events). Backed by the Salesforce fHCM2__Bonus__c object. Each record has an employeeId, amount, currency, paid date, pay code, and a reason (free-text — often "Performance", "Spot", "Retention"). Requires "Sage People Bonuses API" Permission Set.

Absences

List Absences
Get a paginated list of Sage People absence (leave) records. Backed by the Salesforce fHCM2__Absence__c object. Each record has employeeId, reason (e.g. "Planned Vacation", "Sickness"), startDate, endDate, duration + durationUnits (Day/Hour), and an approved boolean. Requires "Sage People Absences API" Permission Set.

Absence Balances

List Absence Balances
Get a paginated list of Sage People absence balance records (PTO / accrual balances). Backed by the Salesforce fHCM2__Accrual_Balance__c object. Each record has employeeId, reason (the leave-type name), units ("days" or "hours"), the calculated-date timestamp, period name (e.g. "2026"), and a nested periodEndBalance with accrued/timeOffInLieu/carryOver floats. Requires "Sage People Absence Balances API" Permission Set.

Timesheets

List Timesheets
Get a paginated list of Sage People timesheet records. Backed by the Salesforce fHCM2__Timesheet__c object. Each record has employeeId, hoursWorked (float), hoursEarned (float — may differ from worked due to multipliers), startDate, endDate, and status (e.g. "approved", "submitted", "draft"). Requires "Sage People Timesheets API" Permission Set.

Employee Pay Details

Create Employee Pay Details
Push payroll output into Sage People for a single employee. This is the only WRITE endpoint in the Sage People API — pay details are append-only (no update/delete). Requires the API user to have the "Sage People Pay Details API" Permission Set assigned. Supports an optional file attachment (e.g. payslip PDF/text, base64-encoded) and a list of additionalFields keyed by Salesforce SOQL field name.

Sage People AI Agent Use Cases

Connect your AI agent to Sage People and help your team scale the HR operations they run by hand today.

Employee Onboarding

Use StackOne to connect your AI agent to your HRIS, identity management, and LMS to automate employee onboarding.

View

HR Policy Q&A Chatbot

Use StackOne to connect your AI agent to your HRIS, knowledge base, and messaging tools to automate HR policy Q&A.

View

Employee Offboarding

Use StackOne to connect your AI agent to your HRIS, identity management, and ITSM to automate employee offboarding and deprovisioning.

View

More HRIS & HCM use cases

Set Up Your Sage People MCP Server in Minutes

One endpoint. Any framework. Your agent is talking to Sage People in under 10 lines of code.

MCP Clients

Agent Frameworks

Claude Desktop-

JSON

Claude Desktop Docs

{
  "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>"
      ]
    }
  }
}

Check More hr-workforce MCP Servers

Phenom

87+ actions

Loket

61+ actions

59+ actions

51+ actions

50+ actions

50+ actions

44+ actions

All hr-workforce MCP Servers →

Platform Resources

MCP Code Mode: Keeping Tool Responses Out of Agent Context

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

Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery

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

Indirect Prompt Injection Defense for MCP Tools: A Technical Guide

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: Architecture, Security, and When to Use Each

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 vs API: What 200+ Connector Builds Taught Us

MCP wraps APIs, it doesn't replace them. After building 200+ connectors that serve both, here's when each approach wins.

14 min read

Sage People MCP Server FAQ

Does StackOne have a Sage People MCP server?

Yes. StackOne offers a hosted Sage People MCP server, and every action is tested and QA'd by StackOne. Connect it to Claude, Cursor, and any other MCP client, or to any agent framework through the AI Action SDK. It ships with managed agent authentication, prompt injection defense, and tool discovery with server-side execution that preserve your agent's context window and keep reasoning performance.

Sage People MCP server vs direct API integration — what's the difference?

A Sage People MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Sage People. A Sage People MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling Sage People at runtime. StackOne provides both.

How does Sage People authentication work for AI agents?

Sage People authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Sage People account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via origin_owner_id.

Are Sage People MCP tools vulnerable to prompt injection?

Yes — Sage People MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.

What is the context bloat of a Sage People agent and how do I avoid it?

Context bloat happens when Sage People tool schemas and API responses eat your Sage People agent's memory, preventing it from reasoning effectively. A single Sage People query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.

Can I limit which actions my Sage People agent can access?

Yes — you can limit which actions your Sage People agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.

Can I create custom agent actions for my Sage People MCP server?

Yes — you can create custom agent actions for your Sage People MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Sage People's API, generate production-ready connector YAML, test against the live API, and validate before you ship.

When should I NOT use a Sage People MCP server?

Skip a Sage People MCP server if your integration is purely software-to-software — direct Sage People API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call Sage People actions at runtime.

What AI frameworks and AI clients does the StackOne Sage People MCP server support?

The StackOne Sage People MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.

Put your AI agents to work

All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.

Start Free Book Demo

Sage People MCP Serverfor AI Agents

8 Agent Actions

Agent Tool Authentication

Agent Protection

Max Agent Context. Min Cost.

What is the Sage People MCP Server?

All Sage People MCP Tools

Employees

Salaries

Bonuses

Absences

Absence Balances

Timesheets

Employee Pay Details

Sage People AI Agent Use Cases

Set Up Your Sage People MCP Server in Minutes

Check More hr-workforce MCP Servers

Platform Resources

MCP Code Mode: Keeping Tool Responses Out of Agent Context

Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery

Indirect Prompt Injection Defense for MCP Tools: A Technical Guide

MCP vs A2A: Architecture, Security, and When to Use Each

MCP vs API: What 200+ Connector Builds Taught Us

Sage People MCP Server FAQ

Put your AI agents to work

Sage People MCP Server
for AI Agents