Connect
Optimize
Secure
Docebo MCP Server
for AI Agents
Production-ready Docebo MCP server with 56 extensible actions — plus built-in authentication, security, and optimized execution.
Docebo MCP Server
Built by 
StackOne
StackOne 
Coverage
56 Agent Actions
Create, read, update, and delete across Docebo — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Docebo MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Docebo 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 Docebo call.
Tools Discovery →What is the Docebo MCP Server?
A Docebo MCP server lets AI agents read and write Docebo data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Docebo MCP server ships with 56 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.
All Docebo MCP Tools and Actions
Every action from Docebo's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Users
- Create User
Create a new user in the Docebo platform with username, email, and password
- List Users
Retrieve a list of all users in the Docebo platform with optional filtering and pagination
- Get User
Retrieve detailed information for a specific user by their Docebo user ID
- Update User
Update an existing user's information in the Docebo platform
- Batch Import Users
Import or update multiple users in the Docebo platform in a single batch operation
- Batch Delete Users
Delete multiple users by user IDs in a single batch operation
- Delete User
Delete a user from the Docebo platform
Courses
- Create Course
Create a new course in the Docebo platform
- List Courses
Retrieve a list of all courses in the Docebo platform with optional filtering and pagination
- Get Course
Retrieve detailed information for a specific course by ID
- Update Course
Update an existing course in the Docebo platform with comprehensive settings including enrollment options, time options, player settings, and more
- Batch Import Courses
Import multiple courses in a single batch operation
- Delete Course
Delete a course from the Docebo platform
Enrollments
- Create Enrollment
Enroll a user in a course with optional level, validity dates, session assignment, and custom enrollment fields
- Get Enrollment
Retrieve enrollment details for a specific user in a specific course. Returns a single enrollment record with dates, status, completion time, and score. Both course ID and user ID are required
- Update Enrollment
Update an existing enrollment with comprehensive options including dates, status, level, session assignment, and custom fields
- Batch Import Enrollments
Import multiple enrollments in a single batch operation. Each item requires enrollment_date (YYYY-MM-DD format). Supports comprehensive options including status, scores, and assignment types
- Delete Enrollment
Un-enroll one or more users from one or more courses or learning plans, with options to reset learning tracks and delete issued certificates
Learning Plans
- Create Learning Plan
Create a new learning plan in the Docebo platform
- List Learning Plans
Retrieve a list of all learning plans in the Docebo platform
- Get Learning Plan
Retrieve detailed information for a specific learning plan by ID
- Update Learning Plan
Update an existing learning plan in the Docebo platform
- Delete Learning Plan
Delete a learning plan from the Docebo platform
Learning Objects
- Create Learning Objects
Create multiple learning objects (training materials) in a single batch operation. Different lo_type values require different fields (e.g., video requires lo_url, file requires lo_filename, scorm requires a valid SCORM zip URL)
- Get Learning Object
Retrieve detailed information for a specific learning object (training material) by ID, including title, description, type, visibility, and associated course
Categorys
- Create Category
Create a new course category in the Docebo platform
- Get Category
Retrieve detailed information for a specific category by ID
- Update Category
Update an existing category in the Docebo platform
- Delete Category
Delete a category from the Docebo platform
Sessions
- List Sessions
Retrieve a list of ILT (Instructor-Led Training) sessions for a classroom course in the Docebo platform
- Get Session
Retrieve detailed information for a specific ILT session including instructors, dates, and enrollment settings
- Delete Session
Delete an ILT session from a course in the Docebo platform
Locations
- Create Location
Create a new ILT location in the Docebo platform for scheduling training sessions
- List Locations
Retrieve a list of all ILT locations in the Docebo platform with optional sorting and pagination
- Update Location
Update an existing ILT location in the Docebo platform
- Delete Location
Delete an ILT location from the Docebo platform
Branches
- List Branches
Retrieve a list of branches of given or root level in the Docebo platform
- Batch Create Branches
Create or update multiple organizational branches in a single batch operation
- Batch Delete Branches
Delete multiple organizational branches in a single batch operation
Branchs
- Create Branch
Create a new organizational branch in the Docebo platform
- Get Branch
Get details of a selected branch
- Update Branch
Update selected branch in the Docebo platform
- Delete Branch
Delete an organizational branch from the Docebo platform
Other (13)
- Send User Message
Send a message to a user
- Get User Settings
Get setting information about a specific user
- Get Course Learning Objects
Retrieve all learning objects (training materials) for a specific course
- Get Course Enrollments
Retrieve all enrollments associated with a specific course with filtering by status, level, branch, group, and more
- List Certifications
Retrieve a list of all certifications in the Docebo platform
- List Categories
Retrieve a list of all course categories in the Docebo platform
- Get Child Categories
Retrieve child categories for a specific parent category
- Get Session Enrollments
Retrieve all enrollments for a specific ILT session with filtering and pagination options
- Get Branch Users
Retrieve information about a branch's users
- Batch Import User Certifications
Import certifications for multiple users in a single batch operation
- Enroll User In Learning Plan
Enroll a single user in a learning plan
- Unenroll User From Learning Plan
Unenroll a user from a learning plan
- Assign Users To Branch
Assign users to an organizational branch
Set Up Your Docebo MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Docebo in under 10 lines of code.
MCP Clients
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>"
]
}
}
}More Learning / LMS MCP Servers
Saba
122+ actions
Xyleme
79+ actions
360Learning
78+ actions
Adobe Learning Manager
72+ actions
Go1
69+ actions
SAP SuccessFactors
69+ actions
Discourse
67+ actions
Docebo MCP Server 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
Docebo MCP Server FAQ
Docebo MCP server vs direct API integration — what's the difference?
A Docebo MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Docebo. A Docebo 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 Docebo at runtime. StackOne provides both.
How does Docebo authentication work for AI agents?
Docebo 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 Docebo account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Docebo MCP tools vulnerable to prompt injection?
Yes — Docebo 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 Docebo agent and how do I avoid it?
Context bloat happens when Docebo tool schemas and API responses eat your Docebo agent's memory, preventing it from reasoning effectively. A single Docebo 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 Docebo agent can access?
Yes — you can limit which actions your Docebo 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 Docebo MCP server?
Yes — you can create custom agent actions for your Docebo MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Docebo's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Docebo MCP server?
Skip a Docebo MCP server if your integration is purely software-to-software — direct Docebo 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 Docebo actions at runtime.
What AI frameworks and AI clients does the StackOne Docebo MCP server support?
The StackOne Docebo 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.