Connect
Optimize
Secure
Fourth MCP Server
for AI Agents
Production-ready Fourth MCP server with 29 extensible actions — plus built-in authentication, security, and optimized execution.
Fourth MCP Server
Built by 
StackOne
StackOne 
Coverage
29 Agent Actions
Create, read, update, and delete across Fourth — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Fourth MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Fourth 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 Fourth call.
Tools Discovery →What is the Fourth MCP Server?
A Fourth MCP server lets AI agents read and write Fourth data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Fourth MCP server ships with 29 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 Fourth MCP Tools and Actions
Every action from Fourth's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Employees
- Create Employee
Create a new employee in Fourth
- List Employees
Get a list of employees for the organisation
- Update Employee
Update an existing employee in Fourth
Absences
- Create Absence
Create an absence record for an employee
- List Absences
Get absences for employees
- Update Absence
Update an existing absence record
- Delete Absence
Delete an absence record for an employee
Multiple Employments
- Create Multiple Employment
Create a multiple employment record for an employee
- List Multiple Employments
Get multiple employments for a specific employee
Holidays
- Create Holiday
Create a holiday request for an employee
- Delete Holiday
Delete a holiday request for an employee
Payment Details
- Create Payment Details
Import employee payment details
- List Payment Details
Get payment details for employees
Other (16)
- List Employee Sources
Get a list of recruitment sources
- List Employments
Get employment details for employees
- List Addresses
Get addresses for employees
- List Dependents
Get dependents for employees
- List Next Of Kin
Get next of kin details for employees
- List Passports
Get passport details for employees
- List Country Specific Fields
Get country-specific fields for employees
- List Holiday Accrual
Get current holiday accrual for flexible employees
- List Divisions
Get divisions for the organisation
- List Locations
Get locations for the organisation
- List Payslips
Get payslip details for employees
- List Pay Parts
Get shift details for a pay period
- List Payroll Periods
Get payroll periods for the organisation
- Get Pay Parts Export
Get pay parts export for a specific pay period
- Get Pay Parts Export By Employee
Get pay parts export for a specific employee in a pay period
- Get Post Pay-Run Export
Get post pay-run export for a specific pay period
Set Up Your Fourth MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Fourth in under 10 lines of code.
MCP Clients
Agent Frameworks
JSON{
"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
Fourth 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
Fourth MCP Server FAQ
Fourth MCP server vs direct API integration — what's the difference?
A Fourth MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Fourth. A Fourth 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 Fourth at runtime. StackOne provides both.
How does Fourth authentication work for AI agents?
Fourth 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 Fourth account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Fourth MCP tools vulnerable to prompt injection?
Yes — Fourth 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 Fourth agent and how do I avoid it?
Context bloat happens when Fourth tool schemas and API responses eat your Fourth agent's memory, preventing it from reasoning effectively. A single Fourth 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 Fourth agent can access?
Yes — you can limit which actions your Fourth 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 Fourth MCP server?
Yes — you can create custom agent actions for your Fourth MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Fourth's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Fourth MCP server?
Skip a Fourth MCP server if your integration is purely software-to-software — direct Fourth 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 Fourth actions at runtime.
What AI frameworks and AI clients does the StackOne Fourth MCP server support?
The StackOne Fourth 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.