Connect
Optimize
Secure
CezanneHR MCP Server
for AI Agents
Production-ready CezanneHR MCP server with 47 extensible actions — plus built-in authentication, security, and optimized execution.
CezanneHR MCP Server
Built by 
StackOne
StackOne 
Coverage
47 Agent Actions
Create, read, update, and delete across CezanneHR — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your CezanneHR MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every CezanneHR 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 CezanneHR call.
Tools Discovery →What is the CezanneHR MCP Server?
A CezanneHR MCP server lets AI agents read and write CezanneHR data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's CezanneHR MCP server ships with 47 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 CezanneHR MCP Tools and Actions
Every action from CezanneHR's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Absence Events
- Create Absence Event
Create a new absence event for an employee
- List Absence Events
Retrieve a list of all absence events
- Update Absence Event
Update an existing absence event
- Delete Absence Event
Delete an absence event
Benefits Records
- Create Benefits Record
Add a benefits record for an employee
- Update Benefits Record
Update an employee's benefits record
- Delete Benefits Record
Delete an employee's benefits record
Companys
- Create Company
Create a new company record
- Update Company
Update a company record
- Delete Company
Delete a company record
Compensation Records
- Create Compensation Record
Add compensation details for an employee
- List Compensation Records
Retrieve employee compensation records
- Update Compensation Record
Update an employee's compensation details
- Delete Compensation Record
Delete an employee's compensation details
Employees
- Create Employee
Create a new employee record in the People table
- List Employees
Retrieve a list of all employees from the People table
- Update Employee
Update an existing employee record
- Delete Employee
Delete an employee record from the People table
Employments
- Create Employment
Create a new employment record for an employee
- List Employments
Retrieve a list of all employment records
- Update Employment
Update an existing employment record
- Delete Employment
Delete an employment record
Jobs
- Create Job
Create a new job definition
- List Jobs
Retrieve a list of all job definitions
- Update Job
Update an existing job definition
- Delete Job
Delete a job definition
Organizational Units
- Create Organizational Unit
Create a new organizational unit
- List Organizational Units
Retrieve a list of all organizational units (departments)
- Update Organizational Unit
Update an existing organizational unit
- Delete Organizational Unit
Delete an organizational unit
Other (17)
- List Absence Event Details
Retrieve detailed breakdown of absence events by day
- List Absence Plans
Retrieve absence plan assignments for employees
- List Benefits
Retrieve employee benefit records
- List Companies
Retrieve company records from the system
- List Company Locations
Retrieve company location records
- List Cost Centres
Retrieve cost centre records
- Search Compensation History
Search employee compensation history
- List Reports To Records
Retrieve employee supervisor/reporting relationships
- List Employment Contracts
Retrieve employee contract records
- List Bank Details
Retrieve employee bank account records
- List Employee Photos
Retrieve employee profile photos
- List Employee Timesheets
Retrieve employee timesheet records
- List Employee Timesheet Details
Retrieve detailed employee timesheet entries
- List Addresses
Retrieve employee address records
- List Timesheet Activities
Retrieve timesheet activity records
- List Timesheet Plans
Retrieve employee timesheet plan assignments
- List Timesheet Projects
Retrieve timesheet project definitions
Set Up Your CezanneHR MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to CezanneHR 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
CezanneHR 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
CezanneHR MCP Server FAQ
CezanneHR MCP server vs direct API integration — what's the difference?
A CezanneHR MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling CezanneHR. A CezanneHR 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 CezanneHR at runtime. StackOne provides both.
How does CezanneHR authentication work for AI agents?
CezanneHR 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 CezanneHR account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are CezanneHR MCP tools vulnerable to prompt injection?
Yes — CezanneHR 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 CezanneHR agent and how do I avoid it?
Context bloat happens when CezanneHR tool schemas and API responses eat your CezanneHR agent's memory, preventing it from reasoning effectively. A single CezanneHR 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 CezanneHR agent can access?
Yes — you can limit which actions your CezanneHR 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 CezanneHR MCP server?
Yes — you can create custom agent actions for your CezanneHR MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research CezanneHR's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a CezanneHR MCP server?
Skip a CezanneHR MCP server if your integration is purely software-to-software — direct CezanneHR 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 CezanneHR actions at runtime.
What AI frameworks and AI clients does the StackOne CezanneHR MCP server support?
The StackOne CezanneHR 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.