Connect
Optimize
Secure
Coursera MCP Server
for AI Agents
Production-ready Coursera MCP server with extensible actions — plus built-in authentication, security, and optimized execution.
Coursera MCP Server
Built by 
StackOne
StackOne 
Coverage
16 Agent Actions
Create, read, update, and delete across Coursera — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Coursera MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Coursera 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 Coursera call.
Tools Discovery →What is the Coursera MCP Server?
A Coursera MCP server lets AI agents read and write Coursera data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Coursera MCP server ships with 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 Coursera MCP Tools and Actions
Every action from Coursera's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Organizations
- Get Organization
Retrieve details about your Coursera organization.
Users
- List Users
Retrieve a paginated list of users within your Coursera organization.
- Delete User
Delete a user from all programs. This also revokes access to the corresponding courses/specializations in the programs.
User Assignments
- List User Assignments
Retrieve course progress summaries for all users in your organization.
Contents
- List Content
Retrieve a paginated list of content (courses, specializations, videos) from your Coursera catalog.
- Get Content
Retrieve detailed information about a specific content item (course, specialization, or professional certificate).
Programs
- List Programs
Retrieve a paginated list of active learning programs in your organization.
Program Memberships
- List Program Memberships
Returns a paginated list of accepted members in your program.
Program Invitations
- Create Program Invitation
This adds a user as an invitee to a program. The external user id in the request can be an LMS / App specific identifier that can be later used for downstream calls. You can also trigger the invitation email to be sent automatically by specifying true for sendEmail in the request.
- List Program Invitations
Returns a paginated list of pending invitations in your program.
- Delete Program Invitation
Delete a pending program invitation.
Program Invitations (Batch)s
- Create Program Invitations (Batch)
This adds multiple users as invitees to a program. The external user id in the request can be an LMS / App specific identifier that can be later used for downstream calls. You can also trigger the invitation email to be sent automatically by specifying true for sendEmail in the request.
Program Enrollments
- Create Program Enrollment
Enrolls a selected user into a specific course. Note that this will only work if the user already has a Coursera account and a current program membership.
- Get Program Enrollment
For a specific user, return whether they are currently enrolled in a specific course.
Curriculum Collections
- List Curriculum Collections
Retrieve a paginated list of curriculum collections in a program.
Program Course Materials
- List Program Course Materials
Returns a paginated list of individual course materials for a given course.
Set Up Your Coursera MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Coursera 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
Coursera 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
Coursera MCP Server FAQ
Coursera MCP server vs direct API integration — what's the difference?
A Coursera MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Coursera. A Coursera 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 Coursera at runtime. StackOne provides both.
How does Coursera authentication work for AI agents?
Coursera 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 Coursera account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Coursera MCP tools vulnerable to prompt injection?
Yes — Coursera 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 Coursera agent and how do I avoid it?
Context bloat happens when Coursera tool schemas and API responses eat your Coursera agent's memory, preventing it from reasoning effectively. A single Coursera 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 Coursera agent can access?
Yes — you can limit which actions your Coursera 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 Coursera MCP server?
Yes — you can create custom agent actions for your Coursera MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Coursera's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Coursera MCP server?
Skip a Coursera MCP server if your integration is purely software-to-software — direct Coursera 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 Coursera actions at runtime.
What AI frameworks and AI clients does the StackOne Coursera MCP server support?
The StackOne Coursera 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.