io.github.RohanMuppa/brightspace

Download a specific file from a student's (or group's) dropbox submission to an existing local directory (it is not created for you), for an instructor or TA. Use get_dropbox_submissions or get_dropbox_user_submissions first to find submissionId and fileId. Requires instructor or TA access to the course. IMPORTANT: Ask the user where they want to save the file before calling this tool. After identifying the file, suggest a clean readable filename and ask if they'd like to rename it.

Download a file from course content, files linked by path inside a module description (coursePath, from get_course_content's quickLink URLs with type=coursefile), instructor assignment attachments (source: assignmentAttachment with folderId + fileId), assignment submissions, or an announcement's attachments. Use this when the user wants a file from Brightspace course content, dropbox submissions, or an announcement (newsId + fileId, from get_announcements). Two response modes: (1) INLINE (default — omit downloadPath): the file comes back directly in the tool response — extracted text for PDFs and Office documents, an image block for jpeg/png/gif/webp, or a short description for anything else — so it can be read immediately without touching any filesystem. This is the right choice in clients like Claude Desktop, whose analysis/sandbox tools cannot see a file the MCP server writes to its own host filesystem. (2) DISK (set downloadPath to an absolute path on the HOST filesystem the MCP server runs on): the file is saved there. The directory must already exist; it is not created for you. Ask the user where to save it before using disk mode — never guess a directory. After identifying the file, suggest a clean readable filename (e.g., 'Lecture 7 - Memory Management.pdf' instead of 'L07_CS251_2026SP_v2.pdf') and pass it as customFilename, or omit it to keep the original. If a content-topic download fails because the file isn't released yet, the response explains why when Brightspace's module/topic metadata supports it (not yet open, ended, locked, or hidden).

Read the files an instructor attached to an announcement: prompt questions, a rubric, an updated schedule, slides. Call it with just courseId to see which announcements have attachments, then with newsId and fileId to read one. Use this when the user asks what a file attached to an announcement says. Returns the text itself. Use download_file (newsId + fileId) instead when the user wants the file saved to disk.

Fetch announcements from one course with courseId, or all courses when omitted, newest first. count is 1-50 per page. Each body is the full announcement text as markdown (links kept); pagination.truncated only means more announcements remain, never that a body was cut. Continue with offset= pagination.nextOffset until it is null. Pagination metadata is in a separate JSON text block for array responses, or the pagination field with modifiedSince. A false coverageComplete means some courses were not fetched: retry from offset 0 after recovery. Offsets reflect the current filtered list; new posts can shift pages. Attachments are listed per announcement; fetch them with download_file (newsId + fileId) or read them with get_announcement_files.

Read the files an instructor attached to an assignment: the spec or instructions PDF, a starter workbook, a rubric document. Call it with just courseId to see which assignments have attachments, then with folderId and fileId to read one. Use this when the user asks what an assignment requires, what the instructions say, or to summarize a handout. Returns the text itself. Use download_file instead when the user wants the file saved to disk.

Fetch the full grading rubric for a dropbox assignment: every criteria group, criterion, and achievement level with its points and description, plus the student's own graded outcome per criterion once it has been released. Use this when the user asks what a rubric wants, how an assignment will be graded, or why they got a particular score on a criterion.

Fetch assignments and quizzes for a specific course or all enrolled courses. Shows dropbox submissions and quizzes with due dates, status, and rubric info. Use this when the user asks about assignments, homework, what to submit, quizzes, or assignment details and rubrics. Read submissionStatus/attemptStatus, not just submission/attemptsUsed, to decide whether something was turned in: some tenants deny students access to submission or attempt data, in which case the status is "unknown" even though submission is null or attemptsUsed is 0. Never report an "unknown" item as missing, unsubmitted, or not attempted - say it could not be verified and point the user to Brightspace. Quizzes come from the quiz list, the course content, and the gradebook; each quiz row says which in source. A quiz with id null was found only as a content topic. A quiz row with detailsStatus "unavailable" was shown in the course content but Brightspace would not return its details (it may be closed, not yet open, or limited to certain students), so its dates and attempts may be missing: point the user to its link. availability (notYetOpen, open, closed) is worked out from the quiz's own start and end dates and is left out when it has none. exempt: true means Brightspace marks the user exempt from that quiz's topic; the quiz is still listed. Each course also carries quizCoverage. "complete" means every quiz source answered, not that every quiz is guaranteed to be listed; "incomplete" means a quiz source could not be read, so the course may have quizzes not listed. Never conclude that a quiz was missed or not taken because it is absent, and never present the listed quizzes as all of them. A gradeOnly row named like a quiz is a quiz whose details could not be read.

List the groups the current user can still join themselves (self-enrollment), with spots left and when sign-up closes. Use this when a student asks which project or lab groups are open. This tool only reads; joining happens in Brightspace under Groups > Available Groups.

Fetch course calendar events — exams, midterms, labs, recitations, review sessions, schedule changes, and deadlines instructors typed straight onto the calendar — across all your courses or one course, in a time window (default: the next 7 days). Use this when the user asks when an exam is, what's on their calendar, or what's happening this week.

Fetch all email addresses for everyone in a course — instructors, TAs, and students. Use this when the user wants a list of emails for a class, needs to email the whole class, or wants contact info for everyone enrolled.

Fetch the content tree for a course showing modules, topics, files, and links. Use this when the user asks about course materials, lecture slides, uploaded files, content structure, or what's in a course module. Use moduleTitle to filter to a specific module (e.g. 'Labs', 'Staff', 'Homeworks') instead of fetching the entire tree. Use maxDepth to limit recursion depth for a table-of-contents view. A module or topic that isn't currently available carries isAvailable/availabilityStatus/availabilityMessage (and startDate/endDate when known) explaining why; absence of these fields means it's available now.

Fetch discussion board content for a course including forums, topics, and posts. Use this when the user asks about discussion boards, forum posts, class discussions, or wants to see what's been posted. Provide just courseId to list all forums and their topics. Add forumId to get topics and posts for a specific forum. Add both forumId and topicId to get all posts in a specific discussion topic.

Retrieve the feedback saved for a dropbox folder — score, graded state, feedback text, and rubric assessment detail. Students: omit entityType and entityId to read your OWN released feedback on an assignment (it is not hidden; use this when get_assignments shows feedback unavailable). Instructors and TAs: pass entityType and entityId to read what is already saved for any user or group, e.g. before drafting new feedback; reading another user's feedback requires instructor or TA access to the course.

List all assignment/dropbox folders for a course, for an instructor or TA. Returns folder ID, name, due date, start/end dates, submission type, visibility, and whether rubrics are attached. Use this to discover folderId values before calling get_dropbox_submissions, get_dropbox_user_submissions, get_dropbox_feedback, or get_rubrics_for_object. This reads the same folder listing a student's own client uses, so it is not gated to instructor/TA accounts the way get_dropbox_submissions, get_dropbox_feedback, and download_dropbox_submission_file are.

List every student's (or group's) submission to a dropbox folder, for an instructor or TA — submitter names, submission dates, late status, file lists, and feedback/grading status. Use get_dropbox_folders first to find folderId. Requires instructor or TA access; a student account gets a clear note instead of data (a student's own download_file / get_assignments already cover their own submission). Results are capped by limit (default 100, max 1000); a truncated response says so and only fetches feedback for the returned slice.

Retrieve all submissions made by one specific student (or group) in a dropbox folder, for an instructor or TA — useful for reviewing a single student's work before drafting feedback. Use get_dropbox_submissions or get_roster to find the userId first. Requires instructor or TA access to the course.

Fetch your enrolled Brightspace courses with names, codes, and IDs. Use this when the user asks about their courses, enrolled classes, what they're taking this semester, or needs a course ID for other queries.

Fetch your grade breakdown for a specific course or all enrolled courses. Shows grade items with points, percentages, and comments. Use this when the user asks about grades, scores, marks, GPA, academic performance, or how they're doing in a class.

List the current user's project/discussion groups in a course, with each group's members. Use this when a student asks who is in their project group, lab group, or discussion group.

Fetch the roster for a course including instructors, TAs, and optionally students with their names, emails, and roles. Use this when the user asks about classmates, instructor contact info, TA emails, professor names, or who's in a class. By default returns only instructors and TAs for privacy. Use includeStudents to get full class list.

Retrieve the full rubric table (criteria, levels, and point values) attached to a dropbox folder, for an instructor or TA. Use get_dropbox_folders first to find folderId. Like get_dropbox_folders, this reads the folder listing's embedded rubric data, so it is not gated to instructor/TA accounts the way get_dropbox_submissions and get_dropbox_feedback are.

Report which version of the Brightspace MCP server is running, the Node.js runtime, platform, config file path, session state directory, configured school URL, whether a credential is stored, the server's local timezone and UTC offset, (once a browser sign-in has been saved) what Microsoft remembered: stay-signed-in (which keeps the Microsoft sign-in but does not by itself skip 2FA) and the Don't ask again MFA checkbox, with a plain-language note on what that means for 2FA to relay to the user, (when signed in) the account's uniqueName/displayName as signedInAs, and this process's request counters (requests: responses by status class, network errors, cache hits/misses, coalesced joins, and token refreshes). Use this for troubleshooting, when the user asks which version they have, or what timezone/account dates are being computed against. Never contacts Brightspace and never returns secrets.

Fetch the syllabus/overview text and optional attachment for a course. Returns the course overview description as markdown. When the syllabus lives in an external LTI tool (e.g. Simple Syllabus), lists those sources in externalSyllabusSources; their contents cannot be read. If some of those lookups could not be completed (e.g. permission denied), externalSyllabusDiscovery says which, and an empty result is then not proof the course has no syllabus. If downloadPath is provided, also downloads the syllabus attachment (e.g. PDF); the directory must already exist, since it is not created for you. IMPORTANT: You MUST ask the user where they want to save the file before calling this tool with a downloadPath.

Fetch upcoming due dates across all your courses, derived from the due dates on assignments (dropbox folders), quizzes, and graded discussion topics themselves, plus course calendar events such as exams and labs (type: event). Use this when the user asks about deadlines, what's due, upcoming work, or what they need to do this week.

Read the transcript of a video embedded in course content, such as a recorded lecture or explainer clip. Call it with courseId and topicId from get_course_content (typeFilter: 'video' or 'other'), or with videoUrl directly if you already have the link. Returns transcript text with timestamps, plus title and duration when available. Currently supports Kaltura (e.g. BoilerCast, including its Brightspace LTI links) and YouTube; other platforms return a clear message naming what isn't supported yet. A failure returns its message plus a JSON block with reason (e.g. sign_in_required for a YouTube bot check) and recovery steps for the user; never present a failed call as a read transcript. Each call returns at most maxChars characters (up to 100000); to read a whole transcript, call again with offset set to the returned nextOffset until truncated is false. Read only — this never marks the video as watched.

Search a course's content (modules, topics, file names), announcements, and discussion forums/topics by keyword in a single call, instead of reading the whole content tree. Use this when the user wants to find something specific, e.g. 'find the midterm review slides' or 'did anyone post about office hours'. Results are ranked: a result matching every query term ranks above one matching only some, and within that, a match in the title ranks above one only in the body text. If one source (e.g. discussions) can't be read, it's skipped and named in `note` rather than failing the whole search. This fans out over the entire content tree, announcements, and every discussion forum, so it can be slower than calling a single tool like get_course_content directly.

Sign in to Brightspace on this computer so the other tools work. Does nothing and says so if the saved session is already valid, so it is safe to call first when you are unsure. Opens a browser window for the user to sign in by hand when no password is saved (nothing to type means a windowless sign-in can only time out); otherwise it signs in in the background and reports the 2FA number for the user to approve on their phone. A window is for the user's own hands only (no saved password, or when the user asks to see one): after a "could not be reached", stuck, or timeout answer, call sign_in again without visible. Call this when a Brightspace tool failed because of authentication, or when the user asks to sign in or log in to Brightspace. Every answer says what to do next, including whether to call again.

Sign out of Brightspace on this computer: cancel any sign-in still waiting for MFA approval here, then delete the saved Brightspace session, so every Brightspace app here must sign in again from scratch on its next question. Keeps the saved password, settings, and authenticator key. Does not sign out of Microsoft or Brightspace on other devices. Cancelling a waiting sign-in doesn't get a new prompt sooner: Microsoft sends no other prompt to the account until the one already sent expires, up to 5 minutes after it was sent. Call this ONLY when the user explicitly asks to sign out or log out of Brightspace (a shared computer, handing the machine on). Never call it on your own to fix an error, to get a new prompt, or as part of answering another question.