Nebula MCP
Provides read-only tools for the Nebula Labs UT Dallas API, covering course and section search/lookup, professor search/lookup, grade distribution histograms, academic calendars, and student organization (club) search, plus optional opt-in access to campus events from the Comet Calendar by date, building, room, or keyword.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Nebula MCP search CS 3345 sections in Fall 2026 and show grade distributions"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Nebula MCP
A small, read-only Model Context Protocol server for the Nebula Labs UT Dallas API: courses, sections, professors, grade distributions, academic calendars, student organizations, and (opt-in) campus events.
Ten tools are enabled by default. Campus events are opt-in, so a default installation cannot read the Comet Calendar unless you ask for it.
This project is independent of Nebula Labs and UT Dallas. Data availability, freshness, and completeness depend entirely on the upstream API. Nothing here is an official university system of record.
Requirements
Node.js 22 or newer (the server is ESM and uses the built-in
fetch,AbortSignal.any, andnode --test).A Nebula Labs API key for tool calls. Discovery (
initialize,tools/list) works without one.
Related MCP server: lms-cli
Install and run
npm ci
npm run build
NEBULA_API_KEY=your-key node dist/src/index.jsThe server speaks MCP over stdio; it prints diagnostics to stderr only, so stdout stays a clean JSON-RPC channel.
Register it with an MCP client (Claude Desktop, VS Code, Cursor, Zed, …) using a stdio entry point:
{
"mcpServers": {
"utd-nebula": {
"command": "node",
"args": ["/absolute/path/to/nebula-MCP/dist/src/index.js"],
"env": { "NEBULA_API_KEY": "your-key" }
}
}
}Configuration
Variable | Required | Meaning |
| for tool calls | Sent as |
| no | Comma-separated subset of |
There is no base-URL override. The server always talks to https://api.utdnebula.com, uses GET only, refuses redirects, and never accepts a caller-supplied path, URL, or key.
Tools
Tool | Toolset | Arguments (all bounded) |
| academics |
|
| academics |
|
| academics | paired |
| academics |
|
| academics |
|
| academics |
|
| academics | one of |
| academics |
|
| clubs |
|
| clubs |
|
| events |
|
Semantics worth knowing before you rely on them:
Exact academic matching. Subject prefixes are uppercased; text filters are trimmed and whitespace is normalized. Academic filters are case-sensitive with no fuzzy matching or capitalization retries. Club keyword search is fuzzy.
No catalog guessing.
course_getandprofessor_gettake ids only. The server never picks a "newest catalog" row for you, and never resolves a name to an id behind your back.Bounded requests. Course/professor searches fetch one upstream page at the cursor offset. Trends sections, clubs, events and per-term grades fetch one complete response (within the byte limit) and page locally. No hidden multi-page fallbacks or widened filters.
section_getexplicitly fetches instructors in a second request.Honest pagination. Course/professor searches use
has_more: nullwhen exhaustion is unknown, andfalseonly after an empty upstream page; a terminal empty call may be needed. Locally paged datasets know when their last page is reached. Every partial nonempty page has a continuation cursor.Grade buckets are raw counts. Exactly 14 buckets, in Trends order:
A+, A, A-, B+, B, B-, C+, C, C-, D+, D, D-, F, W. An all-zero distribution means no recorded observations, not a missing entity. No GPA, no ranking.Calendars are not inferred. Omitting
termreturns whatever the upstream API marks as current; the server never derives the current term from the clock.
Detailed arguments and examples live in docs/tools.md. See the design contract and review/validation record.
Result shape
Every successful call returns one minified JSON text block:
{
"ok": true,
"data": { "items": [], "returned": 0, "has_more": false },
"meta": {
"source": "api.utdnebula.com",
"fetched_at": "2026-11-17T00:00:00.000Z",
"requests": 1,
"notes": ["..."],
"truncated": false
}
}Errors set MCP isError: true and return a bounded block with no echoed key material:
{
"ok": false,
"error": {
"code": "INVALID_ARGUMENT",
"message": "subject_prefix must be a short alphanumeric subject code such as CS",
"hint": "Remove punctuation or wildcards.",
"retryable": false
}
}Codes: INVALID_ARGUMENT, NOT_FOUND, AUTH_MISSING, AUTH_REJECTED, RATE_LIMITED, UPSTREAM_TIMEOUT, UPSTREAM_ERROR, UPSTREAM_SCHEMA, RESPONSE_TOO_LARGE, CANCELLED, UNSUPPORTED.
Lists page with opaque next_cursor values. Cursors are versioned base64url JSON that bind the tool and a hash of the normalized filters; changing a filter or switching tools invalidates the cursor. They carry pagination state only, never credentials or URLs.
The complete MCP result, including metadata and serialization overhead, is capped at 12,000 UTF-8 bytes; list data targets 6,000 bytes. Truncation is disclosed in data/metadata. Cursors advance by rows actually emitted, never by discarded rows. Upstream updates can still cause paging drift. A row/detail that cannot fit returns RESPONSE_TOO_LARGE, not an unusable empty success.
Tool descriptions are at most 160 characters, and the server exposes only selected toolsets. Client-side deferred discovery is supported naturally; this repository does not install or configure clients.
Limits and safety
Fixed API origin,
GETonly, redirects rejected, no caller-provided paths.Streaming response bodies with a hard byte ceiling; oversized bodies fail with
RESPONSE_TOO_LARGE.10-second per-attempt timeout plus a bounded total budget, one retry for
429/502/503/504honoring a shortRetry-After, and MCP cancellation propagated to the fetch signal.Strict schemas: unknown properties and invalid argument combinations are rejected before any network call.
Read-only tool annotations (
readOnlyHint: true,destructiveHint: false,idempotentHint: true,openWorldHint: true).No credentials in logs, cursors, errors, or results. Nothing is written to disk.
Development
npm ci
npm run typecheck # tsc --noEmit
npm run build # emit dist/
npm test # build, then node --test dist/test/*.test.js
npm run check # typecheck + testTests are fully offline: synthetic fixtures model upstream envelopes; a real stdio subprocess and the official SDK client exercise discovery, strict schemas, argument validation, missing-key handling, toolset selection, reflected-secret redaction, and output budgets. No API key, network access, or captured production data is involved. There is no live smoke test in the required path; see AGENTS.md for contribution rules and commit conventions.
Data notes and limitations
Name-filtered grade aggregates merge homonymous instructors; ID-based aggregates scope to the supplied entity. Course filters resolve through the upstream internal course number, so cross-listed or renumbered courses can combine.
Section and professor results reflect the upstream index at fetch time; there is no live registration, seat-count, or waitlist data.
Campus events come from the Comet Calendar index. An empty day means no indexed events, not proof that nothing happens on campus. Listed rooms are event locations, not verified bookings.
Club results are a fuzzy index; absence from it does not mean an organization does not exist. Contact links are returned as data and never opened automatically.
License
MIT.
Available Tools
10 toolsacademic_calendar_getGet a UT Dallas academic calendarARead-onlyIdempotent
Get UTD academic term dates, registration/drop deadlines and exams. Term accepts 26F or Fall 2026; omitted uses the upstream current marker.
Inputs: term.
club_getGet a UT Dallas clubARead-onlyIdempotent
Get a UTD club by its club ID (not slug): description, tags, contacts, officers and update time. Links are data only.
Inputs: club_id (required).
club_searchSearch UT Dallas clubsARead-onlyIdempotent
Search UTD student clubs/organizations by keyword, name, alias or tag. Returns compact ranked matches and IDs for club_get.
Inputs: query (required), limit, cursor.
course_getGet a UT Dallas courseARead-onlyIdempotent
Get a UTD course by ID: catalog metadata, description, prerequisite/corequisite tree and section count. Use course_search to find IDs.
Inputs: course_id (required).
course_searchSearch UT Dallas coursesBRead-onlyIdempotent
Find UTD courses by exact subject prefix, number, catalog year, school or class level. Prefix required; one upstream page per call.
Inputs: subject_prefix (required), limit, cursor, school, +3 more.
grades_getGet UT Dallas grade distributionsCRead-onlyIdempotent
UTD grade counts by ID (overall only) or exact course/instructor filters; overall, term, or term+section-type. Historical counts, not GPA.
Inputs: by, limit, terms, cursor, +8 more.
professor_getGet a UT Dallas professorARead-onlyIdempotent
Get a UTD professor by ID: directory contacts, office, office hours, profile and bounded section references. Does not expand courses.
Inputs: professor_id (required).
professor_searchSearch UT Dallas professorsARead-onlyIdempotent
Find UTD professors by exact, case-sensitive first and/or last name. At least one name required; no fuzzy matching or capitalization retries.
Inputs: limit, cursor, last_name, first_name.
section_getGet a UT Dallas sectionARead-onlyIdempotent
Get a UTD section by ID: term dates, meetings, instruction mode, core flags, syllabus, TAs and instructors. Use grades_get for grade counts.
Inputs: section_id (required).
section_searchSearch UT Dallas sectionsARead-onlyIdempotent
List UTD Trends sections by exact course (prefix+number) and/or professor (first+last name), optionally term (26S/26U/26F). Coverage may lag.
Inputs: term, limit, cursor, last_name, +3 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 10 tools
Each tool targets a distinct resource and action: search/get pairs for courses, sections, professors, and clubs, plus standalone grades and academic calendar tools. Overlap between section_get and grades_get is explicitly clarified, leaving no real ambiguity.
All ten tools follow the same resource_action snake_case pattern (course_search, section_get, professor_search, club_get, etc.). The convention is uniform and predictable throughout.
Ten tools are well-scoped for a read-only university data server. Each search/get pair and the grades/calendar tools earn their place without unnecessary proliferation.
The surface covers search and retrieval for courses, sections, professors, and clubs, plus grades and calendar data, which supports core workflows. Minor gaps exist, such as no subject/term enumeration or fuzzy search, but these are workable constraints documented in descriptions.
Maintenance
Related MCP Connectors
Search university course materials, your flashcards, quizzes, streak and quota. All tools read-only.
Read-only search and retrieval of published books, articles and authors, with public catalog links.
Read-only access to Epivo's live course catalogue for AI agents.
Search Australian CRICOS courses, education providers and ANZSCO skilled occupations using One U Education (万友教育)'s public catalogue, including tuition, intakes, English requirements, campuses and study pathways. Provides six read-only tools with source links; no API key is required, and tuition fees are indicative and shown in AUD.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables read-only queries of i桂航 campus data, including schedules, classes, terms, and campus information through MCP tools.-
- AlicenseNot gradedqualityBmaintenanceEnables natural-language queries across multiple schools' Canvas and Blackboard accounts for courses, notifications, assignments, grades, feedback, and schedules, with read-only access and local todo/calendar export.9MIT
- AlicenseNot gradedqualityCmaintenanceEnables natural-language, read-only queries against the campus systems a user is authorized to access, covering schedules, exams, grades, notices, library resources, and personal workflows while returning source, scope, and gap information.MIT
- AlicenseNot gradedqualityCmaintenanceProvides read-only access to Ed Discussion, letting users list enrolled courses and their threads, read full thread content including answers and comments, fetch digests of recent threads, and keyword-search the latest threads. It issues only GET requests, so it cannot post, vote, or modify anything.ISC