Connect
Optimize
Secure
Announcing StackOne Defender: leading open-source prompt injection guard for your agent • Read More →
Production-ready Rippling MCP server with 37 extensible actions — plus built-in authentication, security, and optimized execution.
Coverage
Create, read, update, and delete across Rippling — and extend your agent's capabilities with custom actions.
Authentication
Per-user OAuth in one call. Your Rippling MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →Security
Every Rippling tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →Performance
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Rippling call.
Tools Discovery →A Rippling MCP server lets AI agents read and write Rippling data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Rippling MCP server ships with 37 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.
Every action from Rippling's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Retrieves compensation information for workers
Retrieves detailed compensation data for a specific compensation record
Returns a paginated list of employment types
Retrieves details for a specific employment type by ID
Retrieves teams with parent-child relationships and hierarchies
Retrieves detailed information about a specific team
Updates an existing time entry by ID using partial update semantics
Permanently deletes a time entry by ID
Retrieves a paginated list of all users in the system
Fetches detailed user information including name, emails, and addresses
Retrieves a list of workers with filtering, expansion, and sorting capabilities
Retrieves detailed information about a single worker by ID
Creates a new department within the organization
Creates a new leave request and returns its ID and details
Creates a new time entry and returns its ID and details
Retrieves a paginated list of companies representing the tenant organization on Rippling
Returns a paginated list of all departments within the organization
Retrieves details for a specific department by ID
Retrieves app access entitlements for identity and access management
Returns a paginated list of all leave balances within the organization
Retrieves details for a specific leave balance by ID
Returns a paginated list of all leave requests within the organization
Retrieves details for a specific leave request by ID
Returns a paginated list of all leave types within the organization
Retrieves details for a specific leave type by ID
Returns a paginated list of all levels within the organization
Retrieves details for a specific level by ID
Returns a paginated list of all timecards for the organization
Retrieves details for a specific timecard by ID
Returns a paginated list of all time entries for the organization
Retrieves details for a specific time entry by ID
Returns a paginated list of all career tracks within the organization
Retrieves details for a specific career track by ID
Returns a paginated list of all work locations configured for the organization
Retrieves details for a specific work location by ID
Updates a department within the organization by ID
Updates an existing leave request by ID
One endpoint. Any framework. Your agent is talking to Rippling in under 10 lines of code.
MCP Clients
Agent Frameworks
{
"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>"
]
}
}
}140+ actions
128+ actions
127+ actions
123+ actions
120+ actions
117+ actions
100+ actions
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
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
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
origin_owner_id.All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.