Skip to main content
Pre-release

This release is a pre-release and may not be stable for production use.

All About NTU MCP

An MCP server for NTU Singapore schedules, learning materials, campus navigation, research, faculty, library discovery, news, and campus services.

STARS guide · NTULearn guide · MazeMap guide · DR-NTU guide.

Library guide · Faculty guide · News guide · Campus services guide.

For local stdio usage, install uv and Python 3.10 or newer. Run the public tools from PyPI:

uvx --from all-abt-ntu-mcp==0.1.0-beta.1 all-abt-ntu

The client examples below include the personal extra for authenticated tools.

Chromium

For authenticated STARS, NTULearn and LibFacilities tools, install Chromium once:

uvx --from 'playwright>=1.50,<2' playwright install chromium

Credentials

Public tools need no credentials. For personal tools, opt into native OS keyring storage by running this yourself in a local terminal:

uvx --from all-abt-ntu-mcp==0.1.0-beta.1 all-abt-ntu auth save

Your password is hidden while typing and stored encrypted in your OS keyring, rather than in plaintext files. The server never includes it in MCP responses sent to the LLM.

The prompts save one account for STARS, NTULearn and LibFacilities and enable automatic login/session recovery. Run auth save again to update it, auth status to check storage without revealing credentials, or auth delete to remove it. Replace auth save at the end of the command above with the action you want.

The keyring must be available and unlocked: Secret Service or KWallet on Linux, Keychain on macOS, Credential Manager on Windows. There is no plaintext fallback. Passwords are not accepted through MCP, command arguments, environment variables, .env, or client configuration. Remove any credentials left in your old configuration; the server no longer reads them. More details: shared credential storage.

Some Linux installations do not include a keyring service. Install a provider such as GNOME Keyring or KWallet using your distribution's package manager, then follow your desktop's setup instructions to start and unlock it before running auth save.

Codex

Add to ~/.codex/config.toml:

[mcp_servers.all-abt-ntu-mcp]
command = "uvx"
args = ["--from", "all-abt-ntu-mcp[personal]==0.1.0-beta.1", "all-abt-ntu"]
env_vars = ["DBUS_SESSION_BUS_ADDRESS", "XDG_RUNTIME_DIR"] # for Linux
startup_timeout_sec = 120
tool_timeout_sec = 240

Restart Codex and check codex mcp list. Personal tools use your locally saved keyring account. The env_vars line forwards the Linux desktop session needed for keyring access; start Codex from a terminal where auth status succeeds. These variables contain no NTU credentials.

Claude Code

Register for your user:

claude mcp add --scope user all-abt-ntu-mcp \
  -- uvx --from 'all-abt-ntu-mcp[personal]==0.1.0-beta.1' all-abt-ntu
claude mcp list

Personal tools use your locally saved keyring account. Check claude mcp list or /mcp inside Claude Code. See Claude Code's MCP guide for details.

OpenCode

Add to ~/.config/opencode/opencode.json:

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "all-abt-ntu-mcp": {
      "type": "local",
      "command": ["uvx", "--from", "all-abt-ntu-mcp[personal]==0.1.0-beta.1", "all-abt-ntu"],
      "enabled": true,
      "timeout": 240000
    }
  }
}

Personal tools use your locally saved keyring account. Check opencode mcp list. See OpenCode's MCP guide for details.

Manual install

Clone the repository and run the server from a local checkout:

git clone --branch main https://github.com/pitchaya-s/ntu-stars-mcp.git all-abt-ntu-mcp
cd all-abt-ntu-mcp
uv sync
uv run all-abt-ntu

For personal tools, run uv sync --extra personal, then uv run all-abt-ntu auth save in your own terminal. Use uv run all-abt-ntu auth status or auth delete to inspect storage status or remove the account. These commands manage credentials; starting the server still uses uv run all-abt-ntu.

The process uses MCP stdio, so it stays open while its MCP client is connected. Course responses are cached in memory for one hour by default; vacancy snapshots are cached for at most 60 seconds. Set NTU_CACHE_TTL_SECONDS to change the cache time or use 0 to disable caching.

Source layout

src/
├── shared/                 Local/public runtimes, HTTP app, keyring, and parsing
├── stars/
│   ├── mcp_server.py        STARS tool registration and input schemas
│   ├── personal_tools.py    Local authenticated STARS tools
│   ├── room_tools.py        Teaching-based room tool registration
│   ├── room_schemas.py      Typed room constraints and results
│   ├── domain/             Course models, timetable matching and room searches
│   ├── client/             Public NTU requests and caching
│   ├── parser/             Schedule and personal-page parsing
│   └── wish/               WISH login and saved-plan editing
├── ntulearn/
│   ├── mcp_server.py        NTULearn tool registration and input schemas
│   ├── models/             Typed responses grouped by domain
│   ├── client/             Login, sessions, and REST requests
│   ├── parser/             Response and document parsing
│   └── services/           Content, files, mailbox, people, and activity
├── mazemap/
│   ├── mcp_server.py        Public map tool registration and input schemas
│   ├── models.py           Typed place and direction responses
│   ├── client.py           HTTP requests, pacing, and caching
│   └── parser.py           Place and route normalization
├── drntu/
│   ├── mcp_server.py        Public repository tool registration and schemas
│   ├── models.py           Typed publication, facet, and dataset responses
│   ├── client.py           HTTP requests, pacing, and caching
│   ├── parser.py           DSpace metadata and pagination validation
│   ├── repository.py       Publication search, browsing, and file discovery
│   └── datasets.py         Published Dataverse versions and file inventories
├── library/
│   ├── mcp_server.py        Library tool registration and schemas
│   ├── personal_tools.py    Local authenticated facility tool
│   ├── models.py           Catalogue, access and facility responses
│   ├── client.py           OneSearch requests and pagination
│   ├── facilities.py       Public facility directory and map availability
│   ├── session.py          Optional facility login and daily time grids
│   ├── schedule.py         Time-grid validation and normalization
│   └── parser.py           Primo record normalization
├── faculty/
│   ├── mcp_server.py        Public faculty tools and input schemas
│   ├── models.py           Typed profile and research-interest responses
│   ├── client.py           Directory requests, filters, and pagination
│   └── parser.py           Profile cards and interest form parsing
├── news/
│   ├── mcp_server.py        Public news tools and input schemas
│   ├── models.py           Typed story, category, and article responses
│   ├── client.py           News search and bounded article retrieval
│   └── parser.py           Story cards and article body extraction
└── service/
    ├── mcp_server.py        Public campus service tools and input schemas
    ├── models.py           Typed location and filter responses
    ├── client.py           Complete directory collection and local search
    └── parser.py           Contact, hours, and map normalization
tests/
├── stars/                  STARS tests and fictionalized fixtures
├── ntulearn/               NTULearn tests and synthetic fixtures
├── mazemap/                MazeMap tests and synthetic fixtures
├── repository/             DR-NTU tests and synthetic fixtures
├── library/                OneSearch and LibFacilities tests and fixtures
├── faculty/                Faculty directory tests and synthetic fixtures
├── news/                   News search and article tests with synthetic fixtures
├── service/                Campus directory tests and synthetic fixtures
├── hosted/                 Public HTTP protocol, isolation, and deployment checks
├── test_*.py               Keyring, local CLI, and shared lifecycle tests
└── typescript_smoke.mjs     Shared MCP interoperability check

Tools

STARS

Public lookups work without credentials. Planner and Degree Audit use the shared NTU credentials.

Tool Purpose Credentials
stars_search_courses Find undergraduate courses by partial code or title keywords in a published term No
stars_get_course_metadata Course name, AUs, prerequisites, description, and term metadata No
stars_get_course_indexes All indexes with complete schedules, vacancies, and waitlist lengths No
stars_get_index One index's complete schedule, vacancies, and waitlist length No
stars_compare_indexes Shared sessions, index-specific sessions, and optional clash checks No
stars_find_matching_indexes Filter by days, times, lesson types, teaching weeks, and supplied schedule clashes No
stars_find_available_rooms Teaching-observed rooms with no scheduled classes in a time/week window No
stars_get_room_schedule Courses, indexes and lessons using a room No
stars_get_graduate_course_schedule Graduate course class groups and scheduled sessions No
stars_get_undergraduate_exam_schedule Undergraduate exam date, time, duration, and published-term notice No
stars_auth_status Whether optional WISH credentials are configured and a session has been verified No
stars_get_stars_planner Your registered courses and saved Plans 1–3 with timetables Yes
stars_save_stars_plan Replace a saved plan's course/index list and verify the saved result Yes
stars_get_degree_audit Your AU requirements, results, and registered courses Yes

Vacancies are available 09:00–22:00 Singapore time; unknown counts are null. Saving a plan replaces its entire course/index list. See the STARS guide for parameters, examples, and sources.

NTULearn

Tool Purpose Credentials
ntulearn_auth_status Credential configuration and last verified session No
ntulearn_list_courses Your enrolled courses and organizations, with availability and IDs Yes
ntulearn_get_course_contents One level of course content, with parent_id to open a folder Yes
ntulearn_get_announcements Published announcements for one course Yes
ntulearn_get_calendar Calendar entries and published deadlines Yes
ntulearn_get_upcoming All calendar pages across enrolled or selected courses Yes
ntulearn_get_gradebook Gradebook columns and your own visible scores and status Yes
ntulearn_get_content_attachments Attached files for a leaf content item Yes
ntulearn_read_file_content Read PDF, Office, and text attachments inline Yes
ntulearn_download_file Save an attachment to a new, explicit local file path Yes
ntulearn_list_messages List inbox or sent messages from course conversations Yes
ntulearn_read_message Full message body and published conversation recipients Yes
ntulearn_list_course_users Visible course users and their roles Yes
ntulearn_list_course_groups Course groups and group sets Yes
ntulearn_get_group_members Visible members of a course group Yes
ntulearn_search_course_content Recursive substring search within one course Yes
ntulearn_search_all_courses Search course content with course IDs and breadcrumbs Yes
ntulearn_get_content_tree Nested course content tree bounded by depth and size Yes
ntulearn_download_course Download course attachments into local folders Yes
ntulearn_whats_new Recent announcements, upcoming events, and grade snapshots Yes

Start with ntulearn_list_courses, then use the returned IDs. See the NTULearn guide for parameters, examples, and sources.

MazeMap

Tool Purpose Credentials
mazemap_list_campuses NTU campuses and their map IDs No
mazemap_list_buildings Buildings and floor IDs, names, and levels No
mazemap_search_places Find rooms, venues, and amenities by code or name No
mazemap_get_place One place's location, aliases, building, and floor No
mazemap_get_directions Walking instructions, distance, time, and accessibility No

Search for a place first, then use its POI ID for details or directions. See the MazeMap guide for parameters, examples, and sources.

DR-NTU

Tool Purpose Credentials
drntu_search Find publications by keywords, repository scope, and facet filters No
drntu_get_item Published metadata, abstracts, citations, and rights No
drntu_browse Explore communities, subcommunities, and collections No
drntu_get_facets Available search filters, values, and result counts No
drntu_list_bundles An item's file groups, including original documents No
drntu_list_files File names, sizes, checksums, rights, and content links No
drntu_get_dataset Published dataset metadata, versions, and file inventories No

Public metadata can describe restricted files. See the DR-NTU guide for parameters, examples, and sources.

Library

Tool Purpose Credentials
library_search Search OneSearch by keywords, title, author, ISBN, or resource type No
library_get_record Bibliographic metadata, identifiers, descriptions, and access links No
library_get_availability Physical holdings and institutional full-text service links No
library_list_facilities Library facilities, floor maps, and closure notices No
library_get_map_availability Seat and room statuses at a Singapore date and time No
library_get_facility_schedule Daily room and seat time grids and facility descriptions Yes

Use the returned record ID and context for details. See the Library guide for parameters and access limitations.

Faculty

Tool Purpose Credentials
faculty_search Find faculty by name or research interest, with public profile details No
faculty_list_interests Research-interest labels and IDs for faculty search No

See the Faculty guide for parameters, pagination, and sources.

News

Tool Purpose Credentials
news_search Search news by keyword, category, and latest or oldest order No
news_list_categories Published news category labels and filter IDs No
news_get_article Read an article's text in bounded chunks No

See the News guide for parameters and sources.

Campus services

Tool Purpose Credentials
service_search Find food outlets, shops, clinics, and services with hours and contacts No
service_list_filters Official directory type and category filter IDs No

See the Campus services guide for parameters and directory coverage.

Tests

Personal-data, map, repository, library, faculty, news, and service fixtures are synthetic. Timetable fixtures use fictional course labels and indexes while retaining the HTML structures needed for parser tests. Opt-in live tests print counts and statuses; they do not save academic records or learning materials in the repository.

The offline tests cover keyring storage and failure handling, local credential prompts, session recovery, parsing, scheduling, lossless compaction, output-schema validation, tool calls/errors, and resource discovery. Protocol tests use Python SDK clients and an independent JSON-RPC client over stdio, including protocol versions 2025-06-18 and 2025-11-25:

uv run python -m unittest discover -s tests -t . -v

An optional check uses the official TypeScript SDK. Node dependencies stay in a temporary directory:

NTU_MCP_TEST_SDK="$(mktemp -d)"
npm install --prefix "$NTU_MCP_TEST_SDK" --ignore-scripts --no-audit --no-fund @modelcontextprotocol/sdk@1.32.1
uv run node tests/typescript_smoke.mjs "$NTU_MCP_TEST_SDK"

These interoperability checks use offline fixtures and never edit saved plans.

Hosted HTTP checks cover public-only registration, rejected personal calls, output schemas, both modern and legacy Python SDK clients, Host/Origin validation, request-size limits, and independent serverless event loops. See the HTTP test instructions for the TypeScript client and opt-in live smoke.

Live checks and service-specific testing instructions: STARS · NTULearn · MazeMap · DR-NTU.

Library tests · Faculty tests · News tests · Campus services tests.

Limitation

Access depends on service availability and NTU permissions. Timetables are published schedules; vacancies are snapshots. NTULearn may restrict content, and large collections can return partial results. Inline document reading extracts text without OCR. MazeMap directions are estimates; map data does not establish room availability or current physical access. DR-NTU file metadata does not establish download permission, and the dataset service may interrupt requests with CAPTCHA.

Room searches cover published undergraduate teaching only, not occupancy, graduate classes, exams, other bookings or access permissions. Unplaced lesson venues remain outside room-specific coverage. Library records and access labels do not establish subscription entitlement, anonymous full-text access, or a loanable copy. Facility booking statuses do not establish occupancy. MFA stops library login; no borrowing or facility bookings are submitted.

Disclaimer

This is an independent project and is not affiliated with, sponsored by, or endorsed by Nanyang Technological University (NTU), Singapore.

Your NTU credentials are retrieved locally from your OS keyring and submitted over HTTPS to NTU or its Microsoft sign-in service. They are never returned through MCP. Academic data returned by tools is visible to the AI client. Keyring storage protects credentials at rest; it does not isolate them from other programs or agents allowed to access your unlocked keyring or the server process.

Metadata

Release files for all-abt-ntu-mcp 0.1.0b1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for all-abt-ntu-mcp 0.1.0b1
File Size Uploaded Provenance
all_abt_ntu_mcp-0.1.0b1.tar.gz 135.6 kB With provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for all-abt-ntu-mcp 0.1.0b1
File Interpreter ABI Platform
all_abt_ntu_mcp-0.1.0b1-py3-none-any.whl Python 3 none any Details

Total release size: 322.6 kB

Release files / all_abt_ntu_mcp-0.1.0b1.tar.gz

Download URL all_abt_ntu_mcp-0.1.0b1.tar.gz
Size 135.6 kB
Tags Source
SHA-256 checksum
How to use checksums
42c31b3ef6f4acf04aa9c73b35634cbbc62fac14a79c948ddc10440d7365ff3e
BLAKE2b-256 checksum
How to use checksums
adf9b7bd4a37f1e0378226a94de31a4d85451e6dab222ad0639ab0e412e73524
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 23, 2026.

Transparency log

Release files / all_abt_ntu_mcp-0.1.0b1-py3-none-any.whl

Download URL all_abt_ntu_mcp-0.1.0b1-py3-none-any.whl
Size 187.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
7c6582b900196a2ab62c08ca6cfb83637b33725fbca868300628ff761829f489
BLAKE2b-256 checksum
How to use checksums
f8cc66f64a857f241b180af1cb3a1d8b60d9bb119693f6c56c7402bfea5ae2a2
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 23, 2026.

Transparency log

Security for all-abt-ntu-mcp 0.1.0b1

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Full provenance

All 2 files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for all_abt_ntu_mcp-0.1.0b1.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 23, 2026.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release
Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page