ntulearn-mcp

MCP server + agent-first CLI for NTULearn — NTU Singapore's Blackboard Learn instance. Point any MCP host (Claude Desktop, Claude Code, Cursor, Cline, Prime Agent) at it to ask about your courses, announcements, calendar, and grades — and to organise course files into a folder hierarchy on disk.

The shipped server is a single Rust binary built on ultrafast-mcp, with 21 tools, 2 prompt templates, and a course-resource URI. No Python, no pip, no virtualenv.

Website: https://ntulearn-mcp.krtk.app

Quick start

git clone https://github.com/gangula-karthik/ntulearn-mcp.git
cd ntulearn-mcp/rust
cargo build --release          # binary: rust/target/release/ntulearn-mcp

Log in once — setup opens NTULearn in a throwaway-profile browser and captures your session cookie for you. No copy-paste, no devtools, no keychain prompts.

rust/target/release/ntulearn-mcp setup
rust/target/release/ntulearn-mcp check   # expect: Live validity : OK (200)

Register the binary with your MCP host:

{
  "mcpServers": {
    "ntulearn": {
      "command": "/Users/you/ntulearn-mcp/rust/target/release/ntulearn-mcp",
      "args": []
    }
  }
}

That's it. The same binary serves MCP with no arguments and acts as a CLI with a command.

Related MCP server: sjtu-canvas-mcp

Why the CLI: about 64x fewer tokens

MCP hosts inject every tool's JSON schema into context every turn — about 6.6k tokens for this server's 21 tools. The same binary doubles as a plain CLI, whose terse tabular output an agent reads in a few hundred tokens:

ntulearn-mcp courses                 # 6 courses ≈ 100 tokens (MCP tool result: ≈ 450)
ntulearn-mcp tree _2706844_1         # a course's content tree
ntulearn-mcp whats-new --days 7      # announcements + due dates + grades digest
ntulearn-mcp multi "courses" "grades" "upcoming --type GradebookColumn"   # concurrent

Measured with the built-in benchmark (ntulearn-mcp selfbench):

The CLI shares the same handlers, cache, and cookie lifecycle as the MCP server. Point your agent at the binary and have it run ntulearn-mcp help (≈590 tokens, once) instead of registering 21 tools.

What people ask for

1. "What announcements happened across my courses this week?" — fans out across all enrolled courses, newest first.

2. "What assignments are due next week?" — reads the calendar, including gradable items.

3. "Organise this semester's content into ~/NTU/y3s1/sc2002/week 8/…." — walks the course tree and downloads into any folder layout you describe.

4. "Pull the due dates and grade weightages out of this course briefing PDF." — reads small text-heavy documents inline.

For multi-page, diagram-heavy lecture decks, use download_file and open the PDF in your client — MCP tool results are capped at 1 MB, so this server does not compete with drag-and-drop for full decks.

CLI reference

ntulearn-mcp help prints this list; ntulearn-mcp help <cmd> shows one command's flags.

courses                                  my enrolled courses (run this first for course ids)
contents     course-id                   one level of a course's content tree
tree         course-id                   entire content tree of a course in one call
search       course-id query             search one course's content tree
find         query                       search content across ALL courses
dl           course-id content-id        download a content item's files to disk
read         course-id content-id        read a content item's files inline (pdf/office/text)
upcoming                                 calendar items + due dates across courses
announcements                            announcements across courses, newest first
grades                                   gradebook columns + your grades across courses
attempts     course-id column-id         attempts on one gradebook column
messages                                 course messages (inbox/sent)
message      message-id                  read one course message
users        course-id                   users enrolled in a course
groups       course-id                   groups in a course
members      course-id group-id          members of one group
summary      course-id                   one-shot course digest (staff, contents, dates)
whats-new                                curated digest of everything new since a cutoff
dl-course    course-id                   bulk-download a course's files
ics                                      export calendar items to an .ics file
grades-csv                               export gradebook to .csv

Output is compact TSV by default. Flags: --json, --md, --toon, --fields a,b, --max-chars N, --full, --limit N, --offset N. Every MCP tool argument is also accepted as a kebab-case flag (--include-disabled, --course-ids a,b, --mode vision).

multi runs several commands concurrently in one process, deduplicating identical in-flight HTTP fetches and sharing one cache:

ntulearn-mcp multi "courses" "announcements --since 2026-01-01" "grades"
# results arrive concatenated, each prefixed with: ===== <command> =====

Output formats

TOON (Token-Oriented Object Notation, spec v4.1) declares array shapes once and drops repeated keys, so the savings scale with how tabular the payload is. Every MCP tool accepts response_format: "toon" too.

Tools

21 tools, most doing cross-course aggregation by default — you rarely pass course IDs by hand.

Read-only tools default to response_format='json'; pass 'markdown' for a readable summary. List-returning tools accept limit/offset. A resource URI, ntulearn://courses/{course_id}, returns a JSON course briefing, and two prompts (ntulearn-weekly-brief, ntulearn-assignment-triage) chain the tools for you.

Known environment limits

• list_messages / read_message — the public /users/me/messages REST API returns 404 on this instance, so the client walks the internal v1 conversation API instead (one cached mailbox flatten → per-course conversations) and derives recipients from the conversation.

• get_group_members — the public groups endpoint returns 403 for student accounts, so the client uses the internal v1 memberships endpoint instead.

• Calendar windows wider than ~16 weeks are rejected by NTULearn with a 400 courseErrors entry — keep since/until within a semester.

• read_file_content extracts text from simple documents; for large or graphical PDFs, use download_file and open the file in your client.

Authentication

The BbRouter cookie is resolved strictly in this order:

1. NTULEARN_COOKIE environment variable

2. Config file at <config>/ntulearn-mcp/cookie

3. Firefox cookies.sqlite (read-only, plaintext)

No keychain access, ever — no password dialogs, no security commands. When NTULearn rejects a call with 401, the server re-resolves the cookie, persists a working value, and retries once. Refresh is never proactive; it happens on a live 401 or when you run ntulearn-mcp refresh.

setup is the normal first-run path: it validates any existing cookie live, and if there is none, opens Chrome/Arc/Brave/Edge/Chromium with a throwaway profile and polls the DevTools protocol for your cookie (15-minute login timeout). The captured value is validated against the API before it is saved, then the browser and profile are cleaned up. On a headless server with no supported browser, it falls back to a one-time paste.

The cookie expires with your NTULearn session (days to weeks). Re-run setup when it does.

1. Log in at https://ntulearn.ntu.edu.sg.

2. DevTools (F12) → Application → Cookies → ntulearn.ntu.edu.sg.

3. Copy the Value of the BbRouter cookie (starts with expires:).

4. Run ntulearn-mcp setup and choose paste, or set it in your MCP host's env block:

   { "env": { "NTULEARN_COOKIE": "expires:1234567890,id:..." } }

5. Restart your MCP host.

Configuration

All optional — the defaults work for most users.

Updates

The binary checks GitHub for a newer release at most once every 24 hours, and never blocks or breaks the server. When one is available you get a one-line notice in the MCP host's log and at the start of the session.

ntulearn-mcp update            # check + prompt before installing
ntulearn-mcp update --check    # exit 0 = current, 10 = update available
ntulearn-mcp update --yes      # install without prompting
ntulearn-mcp update --auto on  # background-install new releases
ntulearn-mcp update --channel beta   # try prereleases first

With --auto on the server downloads the release in the background, verifies its sha256 against the release's checksums.txt, and atomically swaps the binary — the new version activates when your MCP host next restarts the server. Every checksums.txt is minisign-signed by CI, and the public key is committed as minisign.pub and baked into the binary, so a tampered release is refused. Set require_signature: true in settings.json to refuse unsigned releases outright. Installs the binary did not make itself (cargo, Homebrew, dev builds) are detected and answered with the right update command instead of a self-replace. A Homebrew formula template lives in packaging/homebrew/.

Cutting a release (maintainers): bump rust/Cargo.toml, tag v<version>, push. The workflow builds Linux, macOS (arm64 + x64), and Windows binaries, and publishes checksums.txt with its minisign signature. Tags with a hyphen (e.g. v0.8.0-rc.1) publish as prereleases automatically.

Troubleshooting

• "No NTULearn cookie found", or tools fail with 401 — run ntulearn-mcp check to see the cookie source and live validity, then ntulearn-mcp setup to re-capture one.

• MCP host lists the server but tool calls return nothing — run rust/target/release/ntulearn-mcp directly. The usual cause is an unresolvable cookie; the error message will say so.

• Prime Agent lists the server but tools aren't available — run /reload (or restart it) so settings are re-read.

• read_file_content returns "No download URL found" — that content node is not a file (a text page or tool link, say). Use download_file for real attached files.

Development

cd rust
cargo test                              # 53 unit tests
cargo build --release
target/release/ntulearn-mcp selfbench   # token + latency + concurrency benchmark

Layout (rust/crates/ntulearn-mcp/src/):

main.rs      no args → MCP stdio server; command → CLI; setup/check/refresh
cli.rs       the 21 commands, compact TSV renderer, `multi` concurrency
handlers.rs  the 21 tool handlers (shared by MCP server and CLI)
bench.rs     selfbench + mock Blackboard API
client.rs    reqwest (HTTP/2, retries, parallel fan-out, singleflight dedup)
cache.rs     SQLite (WAL, persistent conn) + in-memory TTL cache
cookie.rs    layered cookie resolution (never keychain)
setup.rs     setup / check / refresh subcommands
capture.rs   throwaway-browser CDP cookie capture
parsers.rs   HTML body → download URL extraction
render.rs    markdown / csv / ics renderers
resources.rs course resource template + reader
prompts.rs   prompt templates
schemas.rs   tool schemas
tools.rs     tool definition registry

Before pushing, check that no credential is staged or in history:

git status --short
git log --all -p | grep -nE '(BbRouter=|expires:[0-9]{10,},id:|Set-Cookie|ghp_[A-Za-z0-9]{20,})' | grep -viE 'test|example|README' || echo "clean"

If anything real shows up, do not push. Rotate the credential first.

Disclaimer

Use at your own risk. This is an unofficial, personal-use tool. It is not affiliated with, endorsed by, or sponsored by NTU Singapore, Anthology Inc., or Blackboard Learn.

• Your account, your responsibility. Driving the LMS with your session cookie may be inconsistent with NTU's acceptable use policy. Check NTU policy if you are unsure.

• Your cookie stays local. It is read locally and sent only to ntulearn.ntu.edu.sg.

• Don't share cookie values. Anyone with your BbRouter can act as you until it expires.

• Don't run this for someone else. Each user should run their own instance against their own account.

MIT licensed — see LICENSE. All warranties are disclaimed.