Canvas MCP Server
by Koo42195
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LOG_LEVEL | No | Logging level, e.g. 'debug'. | |
| CANVAS_DOMAIN | Yes | Your Canvas school domain, e.g. your_school.instructure.com. | |
| MCP_HTTP_HOST | No | Host to bind the streamable HTTP transport to. | 127.0.0.1 |
| MCP_HTTP_PATH | No | Path for the streamable HTTP transport. | /mcp |
| MCP_HTTP_PORT | No | Port for the streamable HTTP transport. | 3000 |
| MCP_TRANSPORT | No | Transport mode for the server. Use 'stdio' for local MCP clients or 'streamable-http' for HTTP transport. | stdio |
| CANVAS_TIMEOUT | No | Canvas API request timeout. Increase if experiencing timeouts. | |
| CANVAS_API_TOKEN | Yes | Canvas API token for authentication. | |
| MCP_HTTP_STATEFUL | No | Enable stateful streamable HTTP mode. | true |
| MCP_HTTP_JSON_RESPONSE | No | Use JSON responses for streamable HTTP. | true |
| MCP_HTTP_ALLOWED_ORIGINS | No | Allowed origins for streamable HTTP CORS. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityActive
ResponsivenessNo issues