Skills/npm/brightspace-mcp-server

brightspace-mcp-server@5.2.11

CAUTION· startup only

Publisher claims: "MCP server for Brightspace (D2L). Check grades, due dates, assignments, announcements, syllabus, rosters and more via Claude, ChatGPT, Cursor, Windsurf, or any MCP client." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher rohanmuppa · publishing for 271 daysInstalls 26,623Last detonated 1 h ago

Coverage

Startup only; authenticated tool behavior not tested.
Tested
install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · server startup over stdio (initialize sent) · every file read, file written and host contacted by what ran
Not tested
the tool list (the server exited before answering) · what the tools do when called with real credentials

What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
CREDENTIALS_FORM_PATHD2L_ACCESS_TOKEND2L_HTTP_TOKEND2L_PASSWORDLESSD2L_TOKEN_TTLD2L_TOTP_SECRETMIN_TOKEN_LENGTHConfiguration, not credentials: D2L_ACTIVE_ONLY, D2L_BASE_URL, D2L_CAMPUS, D2L_CURRENT_ONLY, D2L_DUO_PASSCODE, D2L_EXCLUDE_COURSES, D2L_HEADLESS, D2L_HTTP_PORT, D2L_INCLUDE_COURSES, D2L_NO_UPDATE_CHECK, D2L_REMEMBER_MFA, D2L_RUNTIME_IDLE_SECONDS, D2L_SESSION_COOKIE, D2L_SESSION_DIR, D2L_USERNAME, MCP_PATH, VITEST
Where it talks to
brightspace.com (its own)Also suny.edu, nodejs.org, windows.net, purdue.edu, tudelft.nl, universiteitleiden.nl, cuny.edu, polite.edu.sg, mcgill.ca, mun.ca, javerianacali.edu.co — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
the tool list (the server exited before answering) · what the tools do when called with real credentials

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names suny.edu, nodejs.org, windows.net, purdue.edu, tudelft.nl, universiteitleiden.nl, cuny.edu, polite.edu.sg, mcgill.ca, mun.ca, javerianacali.edu.co as well as its own vendor. The guard injects CREDENTIALS_FORM_PATH, D2L_ACCESS_TOKEN, D2L_HTTP_TOKEN, D2L_PASSWORDLESS, D2L_TOKEN_TTL, D2L_TOTP_SECRET, MIN_TOKEN_LENGTH only into requests to brightspace.com (and its subdomains) and refuses the rest.

$vet-skills run --secrets CREDENTIALS_FORM_PATH=brightspace.com,D2L_ACCESS_TOKEN=brightspace.com,D2L_HTTP_TOKEN=brightspace.com,D2L_PASSWORDLESS=brightspace.com,D2L_TOKEN_TTL=brightspace.com,D2L_TOTP_SECRET=brightspace.com,MIN_TOKEN_LENGTH=brightspace.com -- npx -y brightspace-mcp-server

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

What changed since 5.2.5

vet-skills diff brightspace-mcp-server 5.2.5 5.2.11

In the sandbox, this version reached for nothing 5.2.5 did not. Compared from the two recorded runs, not from source.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (3 scenarios; startup only; authenticated tool behavior not tested) on 2026-11-18 and scored it 70/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Access to sensitive file paths; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 35 s · 3 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessinstall script run in the sandbox
0.1sprocessexited 1: Node.js v22.23.5
15sprocessdependency install exit 0
35sclaimedstartup only: exited (0) before answering · code: 'ERR_MODULE_NOT_FOUND', url: 'file:///tmp/ks-detonate-FItWr1/task/home/work/acme-api/.claude/skills/brightspace-mcp-server/build/utils/process-guard.js' } Node.js v22.23.5
35sprocessscript backend runs setup only
35sprocesssecond launch, clock +45 days, CI unset
35sprocessexited 1: Node.js v22.23.5

Static findings

MEDIUM
Process kill commandbuild/auth/auth-runner.js:897 · Process kill command — agent can terminate processes/** watchAttention is armed once per child; a second timer could kill a live sign-in. */Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsbuild/runtime-relay.js:237 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files// runtime idled out. The settings it needs, .env included, are already inFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionbuild/setup.js:475 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(yellow(" Could not remove the saved authenticator key. Delete the brightspace-mcp-server entries from your computer's password store."));Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
npx invocation of non-well-known packagebuild/utils/self-update.js:51 · npx invocation of non-well-known package — may execute untrusted codereturn false; // npx just fetched thisFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagebuild/utils/self-update.js:6 · npx invocation of non-well-known package — may execute untrusted code* The MCP server is launched as `npx -y brightspace-mcp-server@latest`, so itFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsbuild/tools/sign-out.js:55 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files…ESS_TOKEN or D2L_SESSION_COOKIE, set in your AI app's client configuration or a .env file), and sign_out cannot remove that. To stop using it, remove that setting a…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsbuild/auth/sso-flow.js:80 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesreturn new SunySSOFlow({ ...credentials, campus: config.campus });Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commandbuild/auth/auth-runner.js:901 · Process kill command — agent can terminate processesconst kill = (signal) => {Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagebuild/utils/commands.js:24 · npx invocation of non-well-known package — may execute untrusted codeexport const SETUP_COMMAND = `npx -y ${PACKAGE_NAME}@latest setup`;Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
CRITICAL
Prompting user to enter sensitive credentialsbuild/auth/mun-sso.js:89 · Prompting user to enter sensitive credentials — social engineering// Never type the password into anything but MUN's own login server.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
HIGH
Access to sensitive file pathsbuild/utils/config.js:134 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files// and is deliberately weaker (see .env.example) so it is never the default.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packagebuild/utils/self-update.js:14 · npx invocation of non-well-known package — may execute untrusted code* `npx -y brightspace-mcp-server@latest auth` and hands back that process'sFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagebuild/utils/commands.js:22 · npx invocation of non-well-known package — may execute untrusted codeexport const LOGOUT_COMMAND = `npx -y ${PACKAGE_NAME}@latest auth --logout`;Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagebuild/utils/commands.js:20 · npx invocation of non-well-known package — may execute untrusted codeexport const AUTH_COMMAND = `npx -y ${PACKAGE_NAME}@latest auth`;Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Process kill commandbuild/sync/course-sync.js:379 · Process kill command — agent can terminate processes// What a killed earlier run (kill -9) left behind, while no other sync holds this folder.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsbuild/utils/self-update.js:85 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesenv: { ...env, [REEXEC_SENTINEL]: "1" },Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsbuild/tools/sign-in.js:13 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files…ting it, the user has to paste a fresh one into their AI app's configuration or .env file and restart the app."; const NO_RUNNER = `This server cannot start a sign-…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commandbuild/auth/auth-runner.js:23 · Process kill command — agent can terminate processes* kill the child in the middle of a sign-in the user was still completingFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagebuild/utils/commands.js:6 · npx invocation of non-well-known package — may execute untrusted code* Every npx command here is pinned to @latest deliberately. Invoking npx withFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagebuild/tools/sign-out.js:22 · npx invocation of non-well-known package — may execute untrusted code…on because of an unexpected error. Nothing more was changed; try again, or run `npx -y brightspace-mcp-server@latest auth --logout` in a terminal to see the details."…Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagebuild/utils/self-update.js:93 · npx invocation of non-well-known package — may execute untrusted code// If npx itself cannot start, run the stale copy rather than failing.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Process kill commandbuild/sync/cleanup.js:16 · Process kill command — agent can terminate processes* Remove the `.download-<uuid>.part` files a killed run (kill -9, power loss)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagebuild/setup/prepare.js:235 · npx invocation of non-well-known package — may execute untrusted codesteps.push(fail("app", "No supported AI app found — register `npx -y brightspace-mcp-server@latest` in your app by hand", false));Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
CRITICAL
Prompting user to enter sensitive credentialsbuild/utils/commands.js:65 · Prompting user to enter sensitive credentials — social engineering* The person's last setup step: enter the password, approve sign-in. AlwaysFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03

Cost to the agent

Instructions loaded
≈84 tok
1 file · 81 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

No advisories in OSV for brightspace-mcp-server@5.2.11 as of 36 min ago. This is the package itself, not its dependencies.

What would make this Verified

10 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Prompting user to enter sensitive credentials≈ +9 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  2. Unclaimed publisher≈ +8 on the totalClaim rohanmuppa: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  4. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  5. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
  6. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
Publish a new version to npm, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim rohanmuppaPropose a patch to the maintainer
brightspace-mcp-server@5.2.11 safety verdict: Caution (startup only) — KillerSkills