Un servidor de Model Context Protocol que proporciona a un cliente MCP (Claude Desktop, Claude Code o cualquier otra cosa que hable MCP) acceso de solo lectura a tu cuenta de Canvas LMS.
Responde a dos preguntas:
"¿Qué estoy cursando y cómo me va?" — cursos activos con calificaciones actuales.
"¿Qué me queda por entregar y cuándo vence?" — tareas pendientes con fechas de entrega.
La comunicación utiliza el transporte estándar stdio, por lo que el cliente lanza el servidor como un subproceso. Nada se escribe en stdout excepto el tráfico MCP.
Node.js 18.17 o superior (el servidor usa el fetch integrado)
Un token de acceso personal de Canvas
Related MCP server: Canvas MCP Server
cd canvas-mcp-server
npm installAmbas variables son obligatorias; el servidor sale con un mensaje claro si falta alguna.
Variable | Descripción | Ejemplo |
| La raíz de tu instancia de Canvas. Una |
|
| Un token de acceso personal de Canvas. |
|
Inicia sesión en Canvas.
Ve a Cuenta → Configuración.
En Integraciones aprobadas, haz clic en + Nuevo token de acceso.
Dale un propósito y (opcionalmente) una fecha de caducidad, luego haz clic en Generar token.
Copia el token inmediatamente — Canvas solo lo muestra una vez.
El token lleva todos tus privilegios de Canvas. Mantenlo fuera del control de versiones y revócalo desde la misma página de configuración si alguna vez se filtra.
Añade el servidor a la configuración de tu cliente MCP, apuntando a la ruta absoluta de src/index.js:
{
"mcpServers": {
"canvas": {
"command": "node",
"args": ["/absolute/path/to/canvas-mcp-server/src/index.js"],
"env": {
"CANVAS_API_URL": "https://asu.instructure.com",
"CANVAS_ACCESS_TOKEN": "your-token-here"
}
}
}
}Claude Desktop — claude_desktop_config.json
(macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\).
Claude Code — claude mcp add canvas --env CANVAS_API_URL=... --env CANVAS_ACCESS_TOKEN=... -- node /absolute/path/to/canvas-mcp-server/src/index.js
Reinicia el cliente después de editar la configuración.
list_courses_and_gradesCada curso en el que estás matriculado activamente como estudiante, con su calificación actual.
Parámetro | Tipo | Predeterminado | Descripción |
| booleano |
| También incluye matriculaciones activas de términos que ya han terminado. |
Canvas informa las calificaciones dos veces cuando tu institución usa períodos de calificación: una para el período en curso y otra para todo el curso. El campo grades.scope indica cuál estás viendo:
current_grading_period — la puntuación cubre el período de calificación en curso, y course_total_score / course_total_grade llevan los números de todo el curso.
course_total — la institución no usa períodos de calificación, por lo que la puntuación es el total del curso.
unavailable — Canvas no devolvió ninguna matriculación con datos de calificación.
Dentro de cualquier ámbito, current_* ignora el trabajo que aún no ha sido calificado, mientras que final_* cuenta el trabajo no calificado como un cero.
{
"courses": [
{
"id": "101",
"name": "Full Stack Web Development",
"course_code": "GIT-411",
"term": "Fall 2026",
"term_start": "2026-08-20T00:00:00Z",
"term_end": "2026-12-18T00:00:00Z",
"enrollment_state": "active",
"grades": {
"current_score": 88.0,
"current_grade": "B+",
"final_score": 80.5,
"final_grade": "B-",
"scope": "current_grading_period",
"grading_period_title": "Fall Term",
"course_total_score": 91.4,
"course_total_grade": "A-"
},
"html_url": "https://asu.instructure.com/courses/101"
}
],
"course_count": 1,
"retrieved_at": "2026-09-01T12:00:00.000Z"
}list_upcoming_assignmentsTareas pendientes en tus cursos activos que aún no se han entregado, ordenadas por fecha de vencimiento, primero las más próximas.
Parámetro | Tipo | Predeterminado | Descripción |
| entero 1–365, o |
| Cuánto mirar hacia adelante. |
| booleano |
| Incluye trabajo vencido que nunca se entregó. |
| booleano |
| Incluye trabajo pendiente sin fecha de vencimiento. |
| cadena[] | todos los cursos activos | Restringe a IDs de curso de Canvas específicos. |
Una tarea cuenta como pendiente cuando está publicada, es calificable y no ha sido entregada, calificada o excusada. Concretamente, se filtran:
cualquier cosa con una marca de tiempo de entrega
entregas en estado submitted, pending_review o graded
tareas excusadas
tareas que ya tienen una puntuación o calificación (entrada manual o en papel)
tareas not_graded (marcas de asistencia y similares)
tareas no publicadas
{
"assignments": [
{
"id": "9004",
"name": "Missed lab writeup",
"course_id": "101",
"course_name": "Full Stack Web Development",
"due_at": "2026-08-28T06:59:00.000Z",
"days_until_due": -4.2,
"overdue": true,
"points_possible": 25,
"submission_types": ["online_upload"],
"submission_state": "unsubmitted",
"missing": true,
"locked": false,
"unlock_at": null,
"lock_at": null,
"html_url": "https://asu.instructure.com/courses/101/assignments/9004"
}
],
"assignment_count": 1,
"courses_checked": 2,
"window": {
"from": "2026-09-01T12:00:00.000Z",
"to": "2026-09-15T12:00:00.000Z",
"include_overdue": true,
"include_undated": false
},
"errors": [],
"retrieved_at": "2026-09-01T12:00:00.000Z"
}Si un curso no se puede leer — concluido, restringido o con algún error — se lista en errors y los cursos restantes aún devuelven resultados.
Paginación. Canvas pagina cada colección mediante el encabezado Link. El cliente sigue rel="next" a 100 registros por página, con un máximo de 20 páginas por endpoint para que una respuesta incorrecta no pueda causar un bucle infinito.
Concurrencia. Las tareas se obtienen de un máximo de 5 cursos a la vez para mantenerse alejado de los límites de velocidad de Canvas.
Término actual. Por defecto, solo se devuelven los cursos cuyo término no ha terminado. El término predeterminado de Canvas no tiene fecha de finalización y siempre se incluye.
Errores. Los fallos de Canvas se devuelven como errores de herramienta MCP que llevan el código de estado y el mensaje propio de Canvas, con una pista para los casos comunes (401 → token incorrecto, 404 → URL incorrecta).
Solo lectura. Ambas herramientas están anotadas con readOnlyHint. El servidor solo emite solicitudes GET y nunca modifica tus datos de Canvas.
npm test # 36 tests: API client, grade logic, filtering, and an end-to-end MCP round tripLa suite usa un sustituto de fetch con cargas útiles de Canvas grabadas, por lo que no se necesita red ni token real. Todas las fechas de los fixtures son relativas al momento en que se ejecutan las pruebas.
src/
index.js MCP server: tool definitions, schemas, stdio wiring
canvas.js Canvas REST client: auth, pagination, error mapping
courses.js Active-course and grade normalization
assignments.js Outstanding-assignment filtering and due-date windowsMIT
Fetch every course the user is actively enrolled in as a student, together with the current grade for each. When the institution uses grading periods, the score reported is for the grading period in progress and the whole-course total is included alongside it (see the 'scope' field). Defaults to the current term only.
| Name | Required | Description | Default |
|---|---|---|---|
| include_all_terms | No | Include active enrollments from terms that have already ended. |
| Name | Required | Description |
|---|---|---|
| courses | Yes | |
| course_count | Yes | |
| retrieved_at | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=true. The description adds useful behavioral nuance beyond those: grading-period behavior, inclusion of the whole-course total alongside the in-progress score, and the 'scope' field for interpretation. This is valuable context for a read-only listing tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two concise sentences. The first sentence front-loads the primary purpose, and the second adds an important grading-period nuance. There is no filler or repetition of schema details.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple read-only listing tool with one optional parameter, an output schema, and high schema coverage, the description is complete. It explains active enrollment, grading-period behavior, and term defaulting, which is sufficient for an agent to select and invoke the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, and the only parameter, include_all_terms, is well documented in the schema with a clear description and default value. The main description restates the default behavior ('Defaults to the current term only') but adds no additional parameter-level meaning, so the baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific action ('Fetch every course the user is actively enrolled in as a student') and a clear resource ('courses... together with the current grade for each'). It also adds meaningful scope distinctions like 'Defaults to the current term only' and grading-period behavior, which clearly separates it from the sibling assignment-listing tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives clear context for when to use the tool: when you need active course enrollments and current grades, defaulting to the current term. It does not explicitly mention alternatives or exclusions relative to list_upcoming_assignments, but the course/grade vs. assignment subject matter implies the boundary clearly.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Fetch assignments across the user's active courses that are still outstanding — not submitted, not graded, and not excused — with their due dates, sorted soonest first. Past-due work that was never turned in is included by default.
| Name | Required | Description | Default |
|---|---|---|---|
| course_ids | No | Restrict to these Canvas course IDs. Defaults to all active courses. | |
| days_ahead | No | How far ahead to look, in days. Pass null for no upper bound. | |
| include_overdue | No | Include past-due assignments that were never submitted. | |
| include_undated | No | Include outstanding assignments that have no due date. |
| Name | Required | Description |
|---|---|---|
| errors | Yes | Courses that could not be read; the rest of the results are still valid. |
| window | Yes | |
| assignments | Yes | |
| retrieved_at | Yes | |
| courses_checked | Yes | |
| assignment_count | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already declare readOnlyHint=true and openWorldHint=true, so the description doesn't need to repeat those. It goes beyond the annotations by specifying the filtering logic (not submitted, not graded, not excused), sorting order (soonest first), and default inclusion of overdue items. This adds useful behavioral context without contradicting the annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the core purpose, and every clause adds value. It efficiently conveys the tool's scope, filtering criteria, ordering, and default behavior without any fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the output schema exists (as noted in the context), the description doesn't need to explain return values. The tool is relatively simple with 4 optional parameters, and the description plus schema fully cover the behavior. It could be a 5, but the absence of any prerequisites or error conditions keeps it at a solid 4.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already covers 100% of the parameters with descriptions. The tool description adds a bit more by explaining the filtering and sorting behavior, which relates to how the parameters interact (e.g., include_overdue default true). Since schema coverage is high, a baseline 3 is appropriate, but the description's mention of 'sorted soonest first' and 'Past-due work ... included by default' adds context beyond the schema, justifying a 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Fetch') and identifies the resource ('assignments across the user's active courses') with clear criteria ('not submitted, not graded, not excused'). It also notes the sorting by due date and the inclusion of past-due unsubmitted work, which distinguishes it from the sibling tool (list_courses_and_grades) that focuses on grades and courses.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description makes it clear that the tool is for outstanding assignments, which implies using it when you need to see what's due or overdue. It does not explicitly state when NOT to use it or mention the sibling alternative, but the context is sufficiently clear for most use cases, and the default behavior (including overdue) is disclosed.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0list_courses_and_gradeslist_upcoming_assignmentsScored across 2 tools
The two tools serve clearly distinct purposes: one retrieves course enrollments with grades, the other retrieves upcoming assignments. There is no ambiguity in selecting between them.
Both tools follow a consistent 'list_' prefix followed by a clear noun phrase ('courses_and_grades', 'upcoming_assignments'), making the naming pattern uniform and predictable.
With only two tools, the server feels minimal but not entirely unreasonable for a focused student dashboard scope. The count is at the borderline of being thin, as agents may expect additional related operations.
The tool surface covers the two primary student needs (grades and upcoming assignments) but lacks operations like retrieving individual course details, assignment submissions, or past assignmentscars. This leaves notable gaps for broader academic workflows, though it may suffice for a narrow use case.
Manage your Canvas coursework with quick access to courses, assignments, and grades. Track upcomin…
Read-only access to Epivo's live course catalogue for AI agents.
Search university course materials, your flashcards, quizzes, streak and quota. All tools read-only.
Ask your AI about your Airbnb and VRBO listings, bookings, guest messages and reviews. Read-only.
