Connect
Optimize
Secure
The #1 agentic semantic tool search: 91.6% first-try accuracy on S1 Search Bench • Explore Tool Discovery →
Connect your AI agent to StackOne's Leapsome MCP server and give it 29 MCP tools out of the box. Auth, tool execution, and security all managed.
Coverage
Create, read, update, and delete across Leapsome — and extend your agent's capabilities with custom actions.
Authentication
Per-user OAuth in one call. Your Leapsome MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →Security
Every Leapsome 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 Leapsome call.
Tools Discovery →A Leapsome MCP server lets AI agents read and write Leapsome data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Leapsome MCP server ships with 29 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.
Every action from Leapsome's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
List review cycles
List review cycles
Create User
Get Users
Get User
Update User
Create Group
Get Group
Update Group
Create praise
Create instant feedback
Create private note
List employees
List access roles
List goals
List goal tags
List goal comments
Get goal details
List review cycle participants
List feedback
List document categories
List timesheets
List payroll cycles
List payroll cycle participants
List work locations
List absences
Update employee access roles
Update key result
Update initiative
Connect your AI agent to Leapsome and help your team scale the HR operations they run by hand today.
Use StackOne to connect your AI agent to your HRIS, identity management, and LMS to automate employee onboarding.
ViewUse StackOne to connect your AI agent to your HRIS, knowledge base, and messaging tools to automate HR policy Q&A.
ViewUse StackOne to connect your AI agent to your HRIS, identity management, and ITSM to automate employee offboarding and deprovisioning.
ViewOne endpoint. Any framework. Your agent is talking to Leapsome in under 10 lines of code.
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>"
]
}
}
}139+ actions
128+ actions
127+ actions
123+ actions
120+ actions
117+ actions
111+ 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
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 wraps APIs, it doesn't replace them. After building 200+ connectors that serve both, here's when each approach wins.
14 min read
origin_owner_id.All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.