Connect
Optimize
Secure
Live 50 Actions
ClayHR MCP Server
for AI Agents
Connect your AI agent to StackOne's ClayHR MCP server and give it 50 MCP tools out of the box. Auth, tool execution, and security all managed.
ClayHR MCP Server
Built by 
StackOne
StackOne 
Coverage
50 Agent Actions
Create, read, update, and delete across ClayHR — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your ClayHR MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every ClayHR 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 ClayHR call.
Tools Discovery →What is the ClayHR MCP Server?
A ClayHR MCP server lets AI agents read and write ClayHR data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's ClayHR MCP server ships with 50 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, observability, and agent execution runtime. Connect it from MCP clients like Claude Desktop, Claude Code, Cursor, Goose, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.
All ClayHR MCP Tools
Every action from ClayHR's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Announcements
- Create Announcement
Create a new announcement in ClayHR.
- Retrieve Announcement
Retrieve a single announcement by its ID from ClayHR.
Expense Reports
- Create Expense Report
Create a new expense report for a user.
- List Expense Reports
Retrieve expense reports for a user, filterable by user ID, GUID, or email.
- Delete Expense Report
Delete an expense report by its ID.
Expense Items
- Create Expense Item
Create a new expense item and attach it to an expense report.
- Delete Expense Item
Delete an expense item by its ID.
Performance Reviews
- Create Performance Review
Create a new performance review for a specified user in ClayHR.
- List Performance Reviews
Retrieve all performance reviews (including in-progress) for the authenticated user.
Other (41)
- Create Goal
Create a new goal in ClayHR.
- Create A New Leave Request
Create a new leave request in ClayHR.
- Create Bulk Performance Reviews
Launch performance reviews in bulk for multiple users in ClayHR.
- Create A Project
Create a new project in ClayHR.
- Create Skill
Create a new skill in ClayHR.
- Create Survey Response
Create a survey-type form response for a specific survey assignment in ClayHR.
- Create Survey Item Response
Save an answer for a single question within a survey assignment in ClayHR.
- List Users
Retrieve the list of all users from ClayHR.
- List Document Library
Retrieve attachments within the document library from ClayHR.
- Download Document
Retrieve a document as a byte array by file ID from ClayHR.
- List Currencies
Retrieve the list of available currencies supported by the system.
- Get Expense Report Details
Retrieve detailed information for a single expense report by ID or GUID.
- List Expense Types
Retrieve the list of expense types available in the system.
- Retrieve Form Details
Retrieve the structure and metadata of a dynamic form (non-survey, non-test) by its form ID.
- Retrieve Form Responses
Retrieve the list of responses submitted for a specific form.
- Retrieve Forms
Retrieve all dynamic form templates configured organization-wide in ClayHR.
- Retrieve Completed Forms Assigned To The Authenticated User
Retrieve forms that the authenticated user has already completed and submitted.
- Get PTO Policies By User ID
Retrieve only the PTO policies specifically assigned to the currently authenticated user, not the full organization list.
- Get Remaining Hours Credit For A Leave Policy
Retrieve the remaining hours credit for a specific leave policy and user.
- Retrieve Performance Review Assignments For A User
Retrieve pending performance review assignments (reviews you need to complete as a reviewer) for the authenticated user.
- List Completed Performance Reviews
Retrieve only completed/finalized performance reviews for a specific user by their user ID.
- List Performance Review Templates
Retrieve all available performance review templates from ClayHR.
- List Projects
Retrieve the list of all projects from ClayHR.
- Get Project Details By Project ID
Retrieve detailed information for a specific project by its ID from ClayHR.
- Get Survey Details
Retrieve the structure and configuration of a survey-type form by its form ID.
- List Assigned Tests
Retrieve the list of tests assigned to a user in ClayHR.
- Get Test Details
Retrieve the configuration and questions of a test/quiz by its dynamic form ID.
- List Timesheet Approvals
Retrieve a list of timesheet approvals from ClayHR.
- Get Training Content
Retrieve training content by training ID from ClayHR.
- List PTO Policies
Retrieve all PTO policies configured organization-wide in ClayHR.
- Update Timesheet Status
Update the status of a timesheet in ClayHR.
- Delete User Address
Deletes a specific address record for a user in ClayHR.
- Delete User Education
Deletes a specific education record for a user in ClayHR.
- Delete User Employment
Deletes a specific employment record for a user in ClayHR.
- Save Custom Field Values
Save custom field values for a user in ClayHR.
- Save A Form Response
Save a completed dynamic form response (non-survey) for a specific form assignment.
- Save A Form Item Response
Save an answer for a single field within a dynamic form (non-survey) assignment.
- Process A User's Leave By Leave ID And Status
Process a leave request by updating its status (e.g. approved, rejected, pending).
- Save Project Allocation By Project ID
Create a project allocation to assign a user to a project in ClayHR.
- Clock In
Clock in an employee on the timesheet in ClayHR.
- Clock Out
Clock out an employee on the timesheet in ClayHR.
ClayHR AI Agent Use Cases
Connect your AI agent to ClayHR and help your team scale the HR operations they run by hand today.
Employee Onboarding
Use StackOne to connect your AI agent to your HRIS, identity management, and LMS to automate employee onboarding.
View HR Policy Q&A Chatbot
Use StackOne to connect your AI agent to your HRIS, knowledge base, and messaging tools to automate HR policy Q&A.
View Employee Offboarding
Use StackOne to connect your AI agent to your HRIS, identity management, and ITSM to automate employee offboarding and deprovisioning.
ViewSet Up Your ClayHR MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to ClayHR in under 10 lines of code.
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>"
]
}
}
}Check More hr-workforce MCP Servers
Phenom
87+ actions
Loket
61+ actions
Employment Hero
51+ actions
ADP Workforce Now
50+ actions
KiwiHR
44+ actions
CatalystOne
36+ actions
PrismHR
30+ actions
Platform 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
MCP vs A2A: Architecture, Security, and When to Use Each
MCP vs A2A: what each protocol standardizes, how they differ, their shared security risks including indirect prompt injection, and when to use one, both, or a hybrid architecture.
12 min
MCP vs API: What 200+ Connector Builds Taught Us
MCP wraps APIs, it doesn't replace them. After building 200+ connectors that serve both, here's when each approach wins.
14 min read
ClayHR MCP Server FAQ
Does StackOne have a ClayHR MCP server?
Yes. StackOne offers a hosted ClayHR MCP server with 50 pre-built actions, and every action is tested and QA'd by StackOne. Connect it to Claude, Cursor, and any other MCP client, or to any agent framework through the AI Action SDK. It ships with managed agent authentication, prompt injection defense, and tool discovery with server-side execution that preserve your agent's context window and keep reasoning performance.
ClayHR MCP server vs direct API integration — what's the difference?
A ClayHR MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling ClayHR. A ClayHR 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 ClayHR at runtime. StackOne provides both.
How does ClayHR authentication work for AI agents?
ClayHR 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 ClayHR account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are ClayHR MCP tools vulnerable to prompt injection?
Yes — ClayHR 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 ClayHR agent and how do I avoid it?
Context bloat happens when ClayHR tool schemas and API responses eat your ClayHR agent's memory, preventing it from reasoning effectively. A single ClayHR 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 ClayHR agent can access?
Yes — you can limit which actions your ClayHR 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 ClayHR MCP server?
Yes — you can create custom agent actions for your ClayHR MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research ClayHR's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a ClayHR MCP server?
Skip a ClayHR MCP server if your integration is purely software-to-software — direct ClayHR 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 ClayHR actions at runtime.
What AI frameworks and AI clients does the StackOne ClayHR MCP server support?
The StackOne ClayHR 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.