Skip to main content

The #1 agentic semantic tool search: 91.6% first-try accuracy on S1 Search Bench • Explore Tool Discovery →

Live 47 Actions

Lucca MCP Server
for AI Agents

Connect your AI agent to StackOne's Lucca MCP server and give it 47 MCP tools out of the box. Auth, tool execution, and security all managed.

Start Free Book Demo Read Docs →
Lucca logo
Lucca MCP Server
Built by StackOne StackOne
DrataGPLocalyzeFlipMindtoolsScreenloop

Coverage

47 Agent Actions

Create, read, update, and delete across Lucca — and extend your agent's capabilities with custom actions.

MCP Actions → Build Actions →

Authentication

Agent Tool Authentication

Per-user OAuth in one call. Your Lucca MCP server gets session-scoped tokens with zero credentials stored on your infra.

Agent Auth →

Security

Agent Protection

Every Lucca 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 Lucca call.

Tools Discovery →

What is the Lucca MCP Server?

A Lucca MCP server lets AI agents read and write Lucca data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Lucca MCP server ships with 47 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 Lucca MCP Tools

Every action from Lucca's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.

A Departments

  • Create A Department

    Create a new department.

  • Retrieve A Department

    Retrieve a single department by ID.

  • Update A Department

    Update a department.

A Files

  • Upload A File

    Upload a file in order to reference it as the attachment of another resource (e.g. a portrait).

  • Retrieve A File

    Retrieve a file, either its JSON representation or its content.

A Webhook-endpoints

  • Create A Webhook-endpoint

    Create a new webhook-endpoint.

  • Retrieve A Webhook-endpoint

    Retrieves a single webhook-endpoint resource.

  • Update A Webhook-endpoint

    Update an existing webhook-endpoint.

  • Delete A Webhook-endpoint

    Delete an existing webhook-endpoint.

Other (38)

  • List Employees

    Returns a paginated list of employees.

  • Retrieve An Employee

    Retrieve a single employee.

  • List Employee-personal-records

    Retrieve a paginated list of employee-personal-records.

  • Retrieve An Employee-personal-record

    Retrieve an employee-personal-record.

  • List Departments

    Returns a paginated list of departments.

  • List Legal-entities

    Returns a paginated list of legal-entities.

  • Retrieve A Legal-entity

    Retrieve a legal-entity.

  • List Business-establishments

    List business-establishments.

  • Retrieve A Business-establishment

    Retrieve a business-establishment.

  • List Employments

    Returns a paginated list of employments.

  • Retrieve An Employment

    Retrieve an employment by its ID.

  • List Employment-templates

    Retrieve a paginated list of employment-templates.

  • Retrieve An Employment-template

    Retrieve an employment-template by its ID.

  • List Job-positions

    Retrieve a paginated list of job-positions.

  • Retrieve A Job-position

    Retrieve a job-position by its ID.

  • List Probationary-periods

    List probationary-periods.

  • Retrieve A Probationary-period

    Retrieve a probationary-period by its ID.

  • List Employee-attribute-definitions

    Returns a paginated list of employee-attribute-definitions.

  • Retrieve An Employee-attribute-definition

    Retrieve a single employee-attribute-definition by ID.

  • List Employee-attributes

    Returns a paginated list of employee-attributes.

  • Retrieve An Employee-attribute

    Retrieve a single employee-attribute by ID.

  • List Professions

    List professions.

  • Retrieve A Profession

    Retrieve a profession by its ID.

  • List Job-qualifications

    Returns a paginated list of job-qualifications.

  • Retrieve A Job-qualification

    Retrieve a job-qualification by its ID.

  • List Occupation-categories

    Returns a paginated list of occupation-categories.

  • Retrieve An Occupation-category

    Retrieve an occupation-category.

  • List Taxonomies

    Returns a paginated list of taxonomies.

  • Retrieve A Taxonomy

    Retrieve a taxonomy by its ID.

  • List Taxonomy-labels

    Returns a paginated list of taxonomy-labels.

  • Retrieve A Taxonomy-label

    Retrieve a taxonomy-label by its ID.

  • List Webhook-endpoints

    Returns a paginated list of webhook-endpoints.

  • List Webhook-deliveries

    Returns a paginated list of webhook-deliveries.

  • Retrieve A Webhook-delivery

    Retrieve a webhook-delivery.

  • List Webhook-delivery-attempts

    Retrieve a paginated list of webhook-delivery-attempts.

  • Retrieve A Webhook-delivery-attempt

    Retrieve a webhook-delivery-attempt.

  • Retrieve/Download A Portrait

    Retrieve a single employee portrait, either as a JSON representation, or the actual image file.

  • Trigger A Test Delivery

    Triggers a test delivery to a webhook endpoint to verify it is configured correctly.

Lucca AI Agent Use Cases

Connect your AI agent to Lucca 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
WorkdayBambooHRPersonioHiBobGustoRipplingOkta360Learning
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
WorkdayBambooHRPersonioHiBobGustoRipplingSharePointConfluence
Employee Offboarding

Use StackOne to connect your AI agent to your HRIS, identity management, and ITSM to automate employee offboarding and deprovisioning.

View
WorkdayBambooHRPersonioOktaServiceNowRipplingGustoJira
More HRIS & HCM use cases

Set Up Your Lucca MCP Server in Minutes

One endpoint. Any framework. Your agent is talking to Lucca in under 10 lines of code.

MCP Clients

Claude Desktop setup guide
Claude Code setup guide
Cursor setup guide
Goose setup guide

Agent Frameworks

Claude Desktop
{
  "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

All HRIS / HCM MCP Servers →

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

Lucca MCP Server FAQ

Does StackOne have a Lucca MCP server?
Yes. StackOne offers a hosted Lucca MCP server with 47 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.
Lucca MCP server vs direct API integration — what's the difference?
A Lucca MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Lucca. A Lucca 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 Lucca at runtime. StackOne provides both.
How does Lucca authentication work for AI agents?
Lucca 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 Lucca account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via origin_owner_id.
Are Lucca MCP tools vulnerable to prompt injection?
Yes — Lucca 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 Lucca agent and how do I avoid it?
Context bloat happens when Lucca tool schemas and API responses eat your Lucca agent's memory, preventing it from reasoning effectively. A single Lucca 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 Lucca agent can access?
Yes — you can limit which actions your Lucca 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 Lucca MCP server?
Yes — you can create custom agent actions for your Lucca MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Lucca's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Lucca MCP server?
Skip a Lucca MCP server if your integration is purely software-to-software — direct Lucca 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 Lucca actions at runtime.
What AI frameworks and AI clients does the StackOne Lucca MCP server support?
The StackOne Lucca 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.

Start Free Book Demo