Connect
Optimize
Secure
CharlieHR MCP Server
for AI Agents
Production-ready CharlieHR MCP server with 22 extensible actions — plus built-in authentication, security, and optimized execution.
CharlieHR MCP Server
Built by 
StackOne
StackOne 
Coverage
22 Agent Actions
Create, read, update, and delete across CharlieHR — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your CharlieHR MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every CharlieHR 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 CharlieHR call.
Tools Discovery →What is the CharlieHR MCP Server?
A CharlieHR MCP server lets AI agents read and write CharlieHR data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's CharlieHR MCP server ships with 22 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 CharlieHR MCP Tools and Actions
Every action from CharlieHR's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Bank Accounts
- List Bank Accounts
Retrieve bank account information for all team members
- Get Bank Account
Retrieve bank account information for a specific team member
Companys
- Get Company
Retrieve company information for the authenticated account
Leave Allowances
- List Leave Allowances
Retrieve leave allowances for all team members
Leave Requests
- List Leave Requests
Retrieve all leave requests for the company
- Get Leave Request
Retrieve a specific leave request by ID
Offices
- List Offices
Retrieve all offices for the company
- Get Office
Retrieve a specific office by ID
Salaries
- List Salaries
Retrieve salary information for all team members
Salarys
- Get Salary
Retrieve a specific salary record by ID
Team Member Note Types
- Create Team Member Note Type
Create a new team member note type
- List Team Member Note Types
Retrieve all team member note types for the company
- Get Team Member Note Type
Retrieve a specific team member note type by ID
Team Members
- List Team Members
Retrieve all team members for the company
- Get Team Member
Retrieve a specific team member by ID
Team Member Leave Allowances
- Get Team Member Leave Allowance
Retrieve leave allowance for a specific team member
Team Member Leave Requests
- Get Team Member Leave Requests
Retrieve leave requests for a specific team member
Team Member Salaries
- Get Team Member Salaries
Retrieve salary history for a specific team member
Team Member Notes
- Create Team Member Note
Create a new note for a specific team member
- List Team Member Notes
Retrieve all notes for a specific team member
Teams
- List Teams
Retrieve all teams for the company
- Get Team
Retrieve a specific team by ID
Set Up Your CharlieHR MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to CharlieHR 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
CharlieHR 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
CharlieHR MCP Server FAQ
CharlieHR MCP server vs direct API integration — what's the difference?
A CharlieHR MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling CharlieHR. A CharlieHR 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 CharlieHR at runtime. StackOne provides both.
How does CharlieHR authentication work for AI agents?
CharlieHR 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 CharlieHR account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are CharlieHR MCP tools vulnerable to prompt injection?
Yes — CharlieHR 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 CharlieHR agent and how do I avoid it?
Context bloat happens when CharlieHR tool schemas and API responses eat your CharlieHR agent's memory, preventing it from reasoning effectively. A single CharlieHR 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 CharlieHR agent can access?
Yes — you can limit which actions your CharlieHR 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 CharlieHR MCP server?
Yes — you can create custom agent actions for your CharlieHR MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research CharlieHR's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a CharlieHR MCP server?
Skip a CharlieHR MCP server if your integration is purely software-to-software — direct CharlieHR 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 CharlieHR actions at runtime.
What AI frameworks and AI clients does the StackOne CharlieHR MCP server support?
The StackOne CharlieHR 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.