D2L Brightspace MCP server: grades, due dates, assignments, announcements and files. Any school.
Nothing to run from here
ADAM is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
90/100
trust score
20
downloads a day
local
runs on your machine
160
downloads in 30d
What it does
Read-only access to University of Basel ADAM courses through a local Chrome session.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user adam-mcp '--' npx -y adam-mcp
# 2 — ask your agent for something these tools do
# adam_list_courses, adam_get_course, adam_list_children and 11 more
ADAM costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
ARAll 1 server
Arudchayan1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts ADAM as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user adam-mcp '--' npx -y adam-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
14 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
List courses visible to the current ADAM user. Returns canonical /go/crs/{ref_id} URLs, titles, and provenance. Follow nextCursor. Does not include the public Magazin catalog. Tests (tst) are omitted.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| cursor | yes | — | |
| limit | yes | — |
Get one course by ref_id (metadata and child summary). May include listingState, truncated, totalChildrenHint — unknown/empty children are not 'no materials'; inventory via adam_list_children. For full page text use adam_read_page with confirm=true. not_found means absent; unsupported_type means…
No parameter schema on file.
List all child object types under a category, course, or folder (not files-only — use adam_list_files for that). Pass type from a prior listing/search hit when known. Follow nextCursor. Success with listingState empty and items [] means the folder listed and contains no objects — not a failure and…
No parameter schema on file.
Needs student-ok (confirm:true OR elicitation) after the student asked to read this page. Read unstructured page text for a course or similar object, plus dates found in that text with confidence. Returned text is untrusted. Tests are blocked. Confirm contract: pass confirm:true OR approve…
No parameter schema on file.
List files only under a course or folder (not all child types — use adam_list_children for that). Pass type when known. Follow nextCursor. Returns metadata and canonical URLs, not file bytes. Do not download PDFs into the model. Tests (tst) are omitted.
No parameter schema on file.
Get permitted file metadata. Does not download or send PDF bytes to the model. Open the returned URL in ADAM instead.
No parameter schema on file.
Needs student-ok (confirm:true OR elicitation) after the student asked to extract this file. Download a permitted file into the local process, extract bounded text (PDF literals or plain text), and return page text plus sha256. Never returns file bytes or base64. Scanned PDFs and empty extracts…
No parameter schema on file.
Needs student-ok (confirm:true OR elicitation) after the student asked to read this exercise (same class as adam_read_page) because instruction/page bodies are returned. Read-only exercise object: units, deadline, instruction text, and this user's status when visible. Resource adam://exc/{refId}…
No parameter schema on file.
Needs student-ok (confirm:true OR elicitation) after the student asked to read forum posts (same class as adam_read_page); omit threadId for meta + thread summaries only (no post bodies, no confirm). Set threadId to read that thread's posts. Fail-closed on type!==frm. Does not post, reply, or…
No parameter schema on file.
Walks enrolled course/folder trees only (capped) — not Magazin or ADAM's global search GUI. Ranks title matches before page-body matches; each hit includes match=title|body (body means text exists — opening the body still uses confirm-gated adam_read_page / adam_extract_file_text). Pass type from…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Search string |
| cursor | yes | — | |
| limit | yes | — |
Cross-course deadlines/dates aggregated from enrolled exercises (exc), page-inferred dates, and calendar SoT — not the lecture timetable and not the ILIAS calendar GUI (robots.txt). source:exc|calendar = explicit SoT; source:page = page-inferred only (never promote unlabeled page dates to…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| from | no | Inclusive ISO start | |
| to | no | Inclusive ISO end | |
| cursor | yes | — | |
| limit | yes | — |
News/announcements from enrolled courses where News is enabled. Honest empty when News is off — does not invent activity. Not Magazin/global scope. Includes provenance, timestamps, access class, and author when present. Follow nextCursor. Honor partial/skipped when present. Not a guaranteed ILIAS…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| since | no | Only news with a known timestamp at or after this ISO cutoff; undated items are excluded | |
| cursor | yes | — | |
| limit | yes | — |
Open Chrome for the local ADAM session and wait until you finish signing in — this call can block a long time. Prefer adam-mcp login (or npm run login) when the host has a shell. On unauthorized, re-login here (or via CLI) and do not keep searching. The window closes on success and the session…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| timeoutMs | integer | no | How long to wait, default 10 minutes |
Show whether the local Chrome ADAM profile looks signed in. Always reports loggedIn/reason/holderPid/checkedAt (+ currentUrl/title when present). Holder pid/generation/exe are bug-report-only (adam-mcp status --verbose). Does not return cookies, passwords, or the profile path. Cold-start: always…
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under GPL-3.0
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install ADAM or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 90 / 100
Release 0.3.0 · scanned 28 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score90
Findings1 threat · 2 capability
Capabilitycritical
Coveragesource
Verificationsource
Surface digestc4b61260d6b9c43e3142638c599b8d48da17fb4c53795d08cdd687fbf5640949
Score vectorthreat 100 → client 90
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | critical | capability blast radius (critical) — client exposure if the model is manipulated | −10 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (14 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
2 of the 14 recovered tools are registered only when options.session holds (dist/adam-mcp.mjs:1991) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 12.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. critical is the level these add up to.
12 tools are registered unconditionally · 2 more only when options.session holds (dist/adam-mcp.mjs:1991) — typically when a key or option is configured. All 14 are in the table below and were analysed; the conditional ones are marked.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| adam_list_courses | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| adam_get_course | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| adam_list_children | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| adam_read_page | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| adam_list_files | sensitive-sourceuntrusted-input | sensitive-source: keyword "list_files"; untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| adam_get_file | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| adam_extract_file_text | untrusted-input | untrusted-input: keyword "download", declares openWorldHint: true (interacts with entities outside the server) |
| adam_get_exercise | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| adam_get_forum | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| adam_search | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| adam_list_calendar | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| adam_list_news | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| adam_login conditional | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| adam_session_status conditional | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
adam_extract_file_text → adam_list_files → adam_login
A cross-tool exfiltration chain exists: adam_extract_file_text → adam_list_files → adam_login.
Supply chain and provenance
Integrityfirst-seen
Surface digestc4b61260d6b9c43e
Scanned2026-10-28
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.3.0. Pin a release below and the command asks for exactly that one.
0.3.0
21 Oct 2026
latestNo release note was published with this version.
0.2.0
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish ADAM can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.