Connect
Optimize
Secure
Live 75 Actions
Keka MCP Server
for AI Agents
Connect your AI agent to StackOne's Keka MCP server and give it 75 MCP tools out of the box. Auth, tool execution, and security all managed.
Keka MCP Server
Built by 
StackOne
StackOne 
Coverage
75 Agent Actions
Create, read, update, and delete across Keka — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Keka MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Keka 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 Keka call.
Tools Discovery →What is the Keka MCP Server?
A Keka MCP server lets AI agents read and write Keka data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Keka MCP server ships with 75 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 Keka MCP Tools
Every action from Keka's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Employees
- Create Employee
Create a new employee record in Keka HRIS.
- List Employees
List all employees from Keka with optional filtering by IDs, numbers, employment status, probation, notice period, last modified date, and search key. Supports pagination.
- Get Employee
Get detailed information for a specific employee by their unique identifier.
- Search Employees
Search for employees by work phone or work email address.
Leave Requests
- Create Leave Request
Create a new leave request for an employee
- List Leave Requests
Retrieve a paginated list of leave requests
On Duty Requests
- Create On Duty Request
Create an on-duty request for an employee in Keka HR
- List On Duty Requests
List on-duty requests for employees in Keka HR
Work From Home Requests
- Create Work From Home Request
Create a work from home (WFH) request for an employee in Keka HR
- List Work From Home Requests
List work from home (WFH) requests for employees in Keka HR
Employee Financial Details
- List Employee Financial Details
Retrieve a paginated list of employee financial details from Keka, optionally filtered by employee IDs.
- Update Employee Financial Details
Update financial details (PF, ESI, LWF, ABRY, PT) for a specific employee in Keka.
Job Candidates
- Create Job Candidate
Create a new candidate for a job
- List Job Candidates
Retrieve a paginated list of candidates for a job
Preboarding Candidates
- Create Preboarding Candidate
Create a new preboarding candidate
- List Preboarding Candidates
Retrieve a paginated list of preboarding candidates
- Update Preboarding Candidate
Update an existing preboarding candidate
Employee Skills
- Add Employee Skills
Add one or more skills to a specific employee
- List Employee Skills
Retrieve a paginated list of skills for a specific employee
Other (56)
- Add Time Entry To Attendance Summary
Add a time entry (punch) to an employee's attendance summary
- Add Time Entry By Employee ID
Add a time entry (punch) for a specific employee by their route ID
- Add Employee Salary
Add a new salary record for an employee in Keka.
- Add Candidate Note
Add a note to a candidate
- Get Employee Update Fields
Retrieve available fields that can be updated for employees. Supports pagination.
- List Departments
List all departments from Keka with optional filtering by department IDs and last modified date. Supports pagination.
- List Locations
List all locations from Keka with optional filtering by last modified date. Supports pagination.
- List Job Titles
List all job titles from Keka with optional filtering by last modified date. Supports pagination.
- List Groups
List all groups from Keka with optional filtering by group type IDs, system group types, and last modified date. Supports pagination.
- List Group Types
List all group types from Keka. Supports pagination.
- List Currencies
List all currencies from Keka. Supports pagination.
- List Notice Periods
List all notice periods from Keka with optional filtering by notice period IDs. Supports pagination.
- List Contingent Types
List all contingent types from Keka. Supports pagination.
- List Exit Reasons
Retrieve a paginated list of exit reasons
- List Document Types
Retrieve a paginated list of document types
- List Employee Documents
Retrieve a paginated list of employee documents
- List Leave Types
Retrieve a paginated list of leave types
- List Leave Balances
Retrieve a paginated list of leave balances
- List Leave Plans
Retrieve a paginated list of leave plans
- List Attendance Records
List attendance records for employees within a date range
- List Attendance Capture Schemes
List attendance capture schemes configured in Keka HR
- List Shift Policies
List shift policies configured in Keka HR
- List Attendance Tracking Policies
List attendance tracking (penalisation) policies configured in Keka HR
- List Weekly Off Policies
List weekly off policies configured in Keka HR
- List Holidays
List holidays for a specific holiday calendar in Keka HR
- List Holiday Calendars
List holiday calendars configured in Keka HR
- List Employee Salaries
Retrieve a paginated list of employee salaries from Keka, optionally filtered by employee IDs, pay group IDs, or employment status.
- List Pay Groups
Retrieve a paginated list of pay groups from Keka.
- List Pay Cycles
Retrieve a paginated list of pay cycles from Keka, optionally filtered by pay group, month, year, or run status.
- Get Pay Register
Retrieve the pay register for a pay cycle, optionally filtered by pay group, pay cycle, or employee IDs.
- List Full And Final Settlement Details
Retrieve a paginated list of Full and Final (FnF) settlement details for employees from Keka.
- List Employee Form 16
Retrieve Form 16 tax certificates for employees from Keka, optionally filtered by employee, legal entity, or financial year.
- List Banks
Retrieve a paginated list of banks available in Keka.
- List Goals
Retrieve a paginated list of performance goals
- List Review Cycles
Retrieve a paginated list of performance review cycles
- List Employee Reviews
Retrieve a paginated list of employee performance reviews
- List Job Boards
Retrieve the list of available job boards
- List Jobs
Retrieve a paginated list of jobs
- List Candidate Interviews
Retrieve a paginated list of interviews for a candidate
- List Candidate Scorecards
Retrieve a paginated list of scorecards for a candidate
- List Skills
Retrieve a paginated list of skills
- List Assets
Retrieve a paginated list of assets
- List Asset Types
Retrieve a paginated list of asset types
- List Asset Categories
Retrieve a paginated list of asset categories
- List Asset Conditions
Retrieve a paginated list of asset conditions
- List Requisition Requests
Retrieve a paginated list of requisition requests
- Update Employee Personal Details
Update personal details for a specific employee by their employee ID.
- Update Employee Job Details
Update job details for a specific employee by their employee ID.
- Update Employee Exit
Update an existing exit request for an employee
- Update Employee Bank Details
Update the bank account details for a specific employee in Keka.
- Update Goal Progress
Update the progress of a performance goal
- Update Candidate
Update an existing candidate for a job
- Update Asset Assignment
Update the assignment of an asset to an employee
- Deactivate Employee
Submit an exit request for an employee
- Revise Employee Salary
Revise an existing salary record for an employee in Keka.
- Recover Asset
Recover an asset from an employee
Keka AI Agent Use Cases
Connect your AI agent to Keka 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 Keka MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Keka 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 HRIS / HCM MCP Servers
UKG Ready
139+ actions
Workday (Rest and Soap)
128+ actions
Factorial
127+ actions
HiBob
123+ actions
Oracle Fusion HCM
120+ actions
Humaans
117+ actions
SAP SuccessFactors
111+ 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
Keka MCP Server FAQ
Does StackOne have a Keka MCP server?
Yes. StackOne offers a hosted Keka MCP server with 75 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.
Keka MCP server vs direct API integration — what's the difference?
A Keka MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Keka. A Keka 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 Keka at runtime. StackOne provides both.
How does Keka authentication work for AI agents?
Keka 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 Keka account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Keka MCP tools vulnerable to prompt injection?
Yes — Keka 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 Keka agent and how do I avoid it?
Context bloat happens when Keka tool schemas and API responses eat your Keka agent's memory, preventing it from reasoning effectively. A single Keka 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 Keka agent can access?
Yes — you can limit which actions your Keka 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 Keka MCP server?
Yes — you can create custom agent actions for your Keka MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Keka's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Keka MCP server?
Skip a Keka MCP server if your integration is purely software-to-software — direct Keka 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 Keka actions at runtime.
What AI frameworks and AI clients does the StackOne Keka MCP server support?
The StackOne Keka 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.