Skip to main content

Announcing StackOne Defender: leading open-source prompt injection guard for your agent • Read More →

Connect

Connectors Agent Auth MCP Connector Builder

Optimize

Tool Discovery Falcon Engine

Secure

Defender
Connectors

HRIS / HCM

Employee Onboarding Employee Offboarding

Recruiting

Application Screening Interview Scheduling

Customer Support

Ticket Triage Voice Call Summarization

Sales & CRM

Deal Risk Scoring Lead Qualification

Accounting & Finance

Invoice Processing Month-End Accruals

Marketing

Campaign Reports Lead Nurture Sequences
View all use cases

Developers

Docs Changelog Status

Learn

Blog Case Studies Events Partners
Pricing
Login Book Demo Start Free

BreatheHR MCP Server
for AI Agents

Production-ready BreatheHR MCP server with 42 extensible actions — plus built-in authentication, security, and optimized execution.

Start Free Book Demo Read Docs →
BreatheHR logo
BreatheHR MCP Server
Built by StackOne StackOne

Coverage

42 Agent Actions

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

MCP Actions → Create Actions →

Authentication

Agent Tool Authentication

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

Agent Auth →

Security

Agent Protection

Every BreatheHR 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 BreatheHR call.

Tools Discovery →

What is the BreatheHR MCP Server?

A BreatheHR MCP server lets AI agents read and write BreatheHR data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's BreatheHR MCP server ships with 42 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.

All BreatheHR MCP Tools and Actions

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

Employees

  • Create Employee

    Create a new employee

  • List Employees

    Get a list of employees

  • Get Employee

    Get a specific employee by ID

Employee Leave Requests

  • Create Employee Leave Request

    Create a leave request for a specific employee

  • List Employee Leave Requests

    Get leave requests for a specific employee by ID

Leave Requests

  • List Leave Requests

    Get a list of leave requests

  • Get Leave Request

    Get a specific leave request by ID

Sickness

  • Update Sickness

    Update a specific sickness record by ID

  • Delete Sickness

    Delete a specific sickness record by ID

Company Projects

  • List Company Projects

    Get a list of company projects

  • Get Company Project

    Get a specific company project by ID

Other (31)

  • Create Employee Sickness

    Create a sickness record for a specific employee

  • List Employee Absences

    Get absences for a specific employee by ID

  • List Employee Benefits

    Get benefits for a specific employee by ID

  • List Employee Bonuses

    Get bonuses for a specific employee by ID

  • List Employee Holiday Years

    Get holiday years for a specific employee by ID

  • List Employee Salaries

    Get salaries for a specific employee by ID

  • List Employee Sicknesses

    Get sicknesses for a specific employee by ID

  • List Holiday Allowances

    Get a list of holiday allowances

  • List Statutory Holiday Countries

    Get a list of statutory holiday countries

  • Get Leave Request Cancelling

    Find the request this leave request is cancelling

  • List Other Leave Reasons

    Get a list of other leave reasons

  • List Locations

    Get a list of locations

  • List Salaries

    Get a list of salaries

  • List Sicknesses

    Get a list of sicknesses

  • List Working Patterns

    Get a list of working patterns

  • List Absences

    Get a list of absences

  • Get Account Details

    Get account details

  • List Benefits

    Get a list of benefits

  • List Bonuses

    Get a list of bonuses

  • List Company Documents

    Get a list of company documents

  • List Departments

    Get a list of departments

  • List Department Absences

    Get absences for a specific department by ID

  • List Department Benefits

    Get benefits for a specific department by ID

  • List Department Bonuses

    Get bonuses for a specific department by ID

  • List Department Leave Requests

    Get leave requests for a specific department by ID

  • List Department Salaries

    Get salaries for a specific department by ID

  • List Divisions

    Get a list of divisions

  • List Employee Jobs

    Get a list of employee jobs

  • Approve Leave Request

    Approve a specific leave request by ID

  • Reject Leave Request

    Reject a specific leave request by ID

  • Cancel Absence

    Cancel a specific absence by ID

Set Up Your BreatheHR MCP Server in Minutes

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

MCP Clients

Agent Frameworks

Claude Desktop
{
  "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>"
      ]
    }
  }
}

More HRIS / HCM MCP Servers

UKG Ready

140+ actions

Workday (Rest and Soap)

128+ actions

Factorial

127+ actions

HiBob

123+ actions

Oracle Fusion HCM

120+ actions

Humaans

117+ actions

BambooHR

100+ actions

All HRIS / HCM MCP Servers →

BreatheHR MCP Server 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

BreatheHR MCP Server FAQ

BreatheHR MCP server vs direct API integration — what's the difference?
A BreatheHR MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling BreatheHR. A BreatheHR 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 BreatheHR at runtime. StackOne provides both.
How does BreatheHR authentication work for AI agents?
BreatheHR 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 BreatheHR account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via origin_owner_id.
Are BreatheHR MCP tools vulnerable to prompt injection?
Yes — BreatheHR 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 BreatheHR agent and how do I avoid it?
Context bloat happens when BreatheHR tool schemas and API responses eat your BreatheHR agent's memory, preventing it from reasoning effectively. A single BreatheHR 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 BreatheHR agent can access?
Yes — you can limit which actions your BreatheHR 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 BreatheHR MCP server?
Yes — you can create custom agent actions for your BreatheHR MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research BreatheHR's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a BreatheHR MCP server?
Skip a BreatheHR MCP server if your integration is purely software-to-software — direct BreatheHR 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 BreatheHR actions at runtime.
What AI frameworks and AI clients does the StackOne BreatheHR MCP server support?
The StackOne BreatheHR 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