Connect
Optimize
Secure
Zelt MCP Server
for AI Agents
Production-ready Zelt MCP server with 34 extensible actions — plus built-in authentication, security, and optimized execution.
Zelt MCP Server
Built by 
StackOne
StackOne 
Coverage
34 Agent Actions
Create, read, update, and delete across Zelt — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Zelt MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Zelt 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 Zelt call.
Tools Discovery →What is the Zelt MCP Server?
A Zelt MCP server lets AI agents read and write Zelt data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Zelt MCP server ships with 34 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 Zelt MCP Tools and Actions
Every action from Zelt's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
User Compensations
- Create User Compensation
Create a new user compensation record
- Update User Compensation
Update user compensation record
- Delete User Compensation
Delete user compensation record
User Contract Records
- Update User Contract Record
Update an existing user contract record
- Delete User Contract Record
Delete a specific user contract record
User Events
- Get User Events
Get user events by user id
- Update User Event
Update a user event by id
User Role Records
- Update User Role Record
Update an existing user role record
- Delete User Role Record
Delete a specific user role record
User Basic Details
- Get User Basic Details
Get basic details for a specific user
- Update User Basic Details
Update basic details for a specific user
User Personal Infos
- Get User Personal Info
Get personal information for a specific user
- Update User Personal Info
Update personal information for a specific user
Other (21)
- Create New User Contract
Create a new contract record for a user
- Create Documents For Company
Create one or multiple documents for the company
- Create New User Role Record
Create a new role record for a user
- Create User
Create a new user in the system
- List Absences
List absences
- List All Sites For Company
List all sites for company
- List All Departments For Company
List all departments for company
- List All Job Positions
List all job positions
- List All Job Levels
List all job levels
- List All Permission Groups With Members
List all permission groups with members for the company
- Get User Compensation Details
Get user compensation details
- Get Currently Effective Compensation Details
Get currently effective compensation details
- Get User Contracts By User ID
Get all contracts for a specific user
- Get Current User Contract By User ID
Get the current active contract for a specific user
- List Document Types For Company
Get all available document types for the company
- Get Currently Effective User Event
Get currently effective user event
- Get User Role Details
Get all role details for a specific user
- Get Currently Effective User Role
Get the current active role for a specific user
- List All Users
Retrieve a list of all users for the company
- Bulk Import Attendance Entries
Bulk import attendance entries (max 100 per request)
- Rehire User
Rehire a user
Set Up Your Zelt MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Zelt 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
Zelt 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
Zelt MCP Server FAQ
Zelt MCP server vs direct API integration — what's the difference?
A Zelt MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Zelt. A Zelt 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 Zelt at runtime. StackOne provides both.
How does Zelt authentication work for AI agents?
Zelt 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 Zelt account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Zelt MCP tools vulnerable to prompt injection?
Yes — Zelt 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 Zelt agent and how do I avoid it?
Context bloat happens when Zelt tool schemas and API responses eat your Zelt agent's memory, preventing it from reasoning effectively. A single Zelt 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 Zelt agent can access?
Yes — you can limit which actions your Zelt 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 Zelt MCP server?
Yes — you can create custom agent actions for your Zelt MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Zelt's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Zelt MCP server?
Skip a Zelt MCP server if your integration is purely software-to-software — direct Zelt 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 Zelt actions at runtime.
What AI frameworks and AI clients does the StackOne Zelt MCP server support?
The StackOne Zelt 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.