Blackboard MCP Server
The Blackboard® MCP Server lets an AI assistant you already use, such as Claude, ChatGPT, Gemini or GitHub Copilot, work in Blackboard LMS on your behalf. You ask in plain language. The AI model behind your assistant picks the right tool, the server carries it out in Blackboard LMS as you, and the answer comes back into your conversation.
This topic explains what MCP is, what the Blackboard MCP Server can do, and how it keeps your data within the permissions you already have.
Defining Model Text Protocol
MCP stands for Model Context Protocol. It is an open standard that gives AI assistants a common way to discover and use tools in other systems. Think of it as a standard set of fittings: once a system offers an MCP server, any assistant that supports MCP can use it, without a custom integration for each one.
Part | What it does | Example |
|---|---|---|
The AI model | Understands your request, makes a plan and chooses which tools to use. | The model inside Claude, ChatGPT or Gemini. |
The AI assistant | The app you use. It connects to MCP servers, shows the model which tools are available, runs the tools the model chooses, asking for your approval where it is set to, and passes the results back. | Claude, ChatGPT, Gemini, GitHub Copilot. |
The MCP server | Offers a set of tools and runs them when asked. It doesn't think or make decisions. | The Blackboard MCP Server, which runs actions in Blackboard LMS. |
Important
Without a standard, every AI tool needs its own connection to every system, and each one signs in, exposes data and gets audited differently. With MCP, Blackboard builds one governed connection that any compliant assistant can use, alongside MCP servers for your other systems, such as email, ticketing or your student information system.
What the Blackboard MCP Server does
The server turns your requests into calls to the Blackboard LMS REST APIs, the same public APIs other integrations use. Tools are grouped around the roles people already have.
Role | What you can do | Ask something like |
|---|---|---|
Student | See your courses and coursework, and track what is due. | "Show me everything I still need to submit this week." |
Instructor or designer | Find missing work, post announcements, open discussions, and read and build course content. | "Which students haven't submitted the Week 3 quiz in BIO-201?" |
Administrator | Search and manage courses, users, enrollments and terms. | "Find this user and list every course they're enrolled in." |
For the full list, see the Blackboard MCP Server Tool Guide.
How it works
You ask your AI assistant a question or give it a task in plain language.
The AI model chooses a tool from the Blackboard MCP Server, and the assistant sends the request with your sign-in token.
The server checks your token, runs the tool in Blackboard LMS as you, and records the request in an audit log.
Blackboard LMS answers within your permissions, and the assistant uses the result to reply or take the next step.
The first time you connect, a browser window opens. You choose your institution, sign in on your usual Blackboard LMS or single sign-on page, and approve the connection. The assistant receives a time-limited token, never your password.
Capabilities and limitations
It can | It can't |
|---|---|
Read your courses, rosters, assignments, announcements, discussions and course content. Create and update courses, users, enrollments, terms, announcements, discussions and course content, if your role allows it. | Delete anything. There are no delete tools. Reach any data you can't already reach in Blackboard LMS. Call any Blackboard LMS API it wants. It offers a fixed set of tools. Read or upload attached files, or work with grades. |
Your data and your permissions
You act as yourself. Every request uses your Blackboard LMS role and permissions. A student can't run administrator actions, and an instructor sees only their own courses.
Administrators are in control. The server is off until a Blackboard LMS administrator turns it on. To start with a pilot group, make the connector available to that group in your AI tool's admin console.
Every request is logged so your institution can review what was done.
Choose your assistant carefully. Once a result reaches your AI assistant, your institution's agreement with that AI vendor governs it. Use the institutionally managed account your institution provides, not a personal one.
Important
Decide which AI assistants are approved for use with Blackboard LMS data and turn the server on. See Turn on the Blackboard MCP Server.