Learning Commons MCP Server
for AI Agents
Connect your AI agent to StackOne's Learning Commons MCP server and give it 31 MCP tools out of the box. Auth, tool execution, and security all managed.
StackOne 
Coverage
31 Agent Actions
Extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Learning Commons MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Learning Commons 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 Learning Commons call.
Tools Discovery →What is the Learning Commons MCP Server?
A Learning Commons MCP server lets AI agents work with Learning Commons data through the Model Context Protocol, Anthropic's open standard for connecting LLMs to external tools. StackOne's Learning Commons MCP server ships with 31 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 Learning Commons MCP Tools
Every StackOne action for Learning Commons, ready for your agent. Scoped to exactly what you need.
Durable Skills
- Search Durable Skills
Search durable skills
- Get Durable Skill
Durable skill by ID
Learning Components
- Get Learning Component
Learning component by ID
- Search Learning Components
Search learning components
Standards
- Get Standard
Standard by ID
- Search Standards
Search standards
Other (25)
- List Crosswalks For A Standard
Crosswalks for a standard
- List Courses
Courses in a curriculum
- Get Course Scope And Sequence
Scope and sequence for a course
- Get Lesson Grouping
Lesson grouping by ID
- Get Lesson
Lesson by ID
- Get Activities In A Lesson
Activities in a lesson
- Get Standards For A Lesson
Standards for a lesson
- Get Standards For An Activity
Standards for an activity
- Get Standards For An Assessment
Standards for an assessment
- List Assessments In A Course
Assessments in a course
- Get Curriculum Dependency Map
Dependency map for a curriculum
- List Durable Skills Frameworks
Durable skills frameworks
- List Durable Skills In Framework
Durable skills in a framework
- List Durable Skill Children
Children of a durable skill
- List Learning Components For A Standard
Learning components for a standard
- List Learning Components By Subject
Learning components by subject
- List Standards Frameworks
Standards frameworks
- List Standards In Framework
Standards in a framework
- List Standard Children
Children of a standard
- List Standard Prerequisites
Prerequisites for a standard
- List Standards A Standard Builds Towards
Standards a standard builds towards
- List Related Standards
Related standards for a standard
- Get Lessons For A Standard
Lessons for a standard
- Get Activities For A Standard
Activities for a standard
- Get Assessments For A Standard
Assessments for a standard
Set Up Your Learning Commons MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Learning Commons 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 learning-development MCP Servers
Platform Resources
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 Hundreds of Connector Builds Taught Us
MCP wraps APIs, it doesn't replace them. After building hundreds of connectors that serve both, here's when each approach wins.
14 min read
Learning Commons MCP Server FAQ
Does StackOne have a Learning Commons MCP server?
Learning Commons MCP server vs direct API integration — what's the difference?
How does Learning Commons authentication work for AI agents?
origin_owner_id.Are Learning Commons MCP tools vulnerable to prompt injection?
What is the context bloat of a Learning Commons agent and how do I avoid it?
Can I limit which actions my Learning Commons agent can access?
Can I create custom agent actions for my Learning Commons MCP server?
When should I NOT use a Learning Commons MCP server?
What AI frameworks and AI clients does the StackOne Learning Commons MCP server support?
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.