Anteater MCP
The server is a read-only UCI course-planning assistant exposing MCP tools for course discovery, section lookup, eligibility checks, and degree planning.
List terms, academic calendars, and department codes.
Search the course catalogue or fetch full details for a course.
Find live class sections by term, department, GE, instructor, days, time, building, section type, and availability.
Review historical grade distributions and instructor information.
Check enrollment history to estimate how fast a class fills.
Evaluate prerequisites against completed courses and AP/exam scores.
Check a set of section codes for meeting-time conflicts, final-exam conflicts, and total units.
Recommend courses matching constraints, ranked by historical GPA or open seats.
List degree programs and retrieve major/minor/specialization or general-education requirements.
Find past syllabi and sample quarter-by-quarter program plans.
Look up AP exam credit and course-clearing equivalencies.
All tools are read-only; nothing mutates data.
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., "@Anteater MCP Find me a GE-2 for Fall that ends before 5pm and still has seats, ranked by how well people do."
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.
Anteater MCP
Release 1.0.0-beta.3 returns structured error codes from every tool and from the REST facade, so clients can tell a rejected API key from a rate limit or an upstream outage. See Changes for the REST response change.
An MCP server that lets Claude and ChatGPT help you pick classes at UC Irvine.
It wraps Anteater API — UCI's course catalogue, the live schedule of classes (WebSoc), historical grade distributions, enrollment history, prerequisite trees, AP credit, degree requirements and supplementary RMP ratings — and exposes them as 20 tools, 6 guided prompts and 4 reference resources, shaped around the questions students actually ask.
Zero runtime dependencies. Run the source with Node 24 LTS, or download a standalone Linux, macOS or Windows executable that already contains the same Node runtime.
"Find me a GE-2 for Fall that ends before 5pm and still has seats, ranked by how well people do."
Course Title Units GPA A% n SeatsOpen Example meeting
------------ ------------------- ----- ---- --- ---- --------- ---------------------------
BIO SCI 17 EVO PSYCHOLOGY 4 3.80 88% 2410 2 TuTh 15:30-16:50 @ SH 134
UNI STU H30A ANALYSIS HEALTH LIT 4 3.77 84% 864 15 TuTh 12:30-13:50 @ ALP 1600
LPS 31 INTRO INDUCT LOGIC 4 3.61 80% 2108 11 TuTh 14:00-15:20 @ EH 1200Quickstart
git clone https://github.com/KKazuhaK/Anteater-MCP.git
cd anteater-mcp
node --version # Node 24 LTS
node anteater-mcp.mjs --list-tools # confirm it runsThen add it to your client — Claude Desktop, Claude Code, ChatGPT, or any other MCP client.
Nothing else is required. An API key is optional but recommended.
Related MCP server: chimeralang-mcp
Installing
Standalone binary
Each GitHub Release contains native
archives for Linux, macOS and Windows on amd64 and arm64, plus SHA256SUMS.txt. These do
not require Node.js:
# After downloading and extracting the archive for your platform:
./anteater-mcp --version
./anteater-mcp --list-toolsIn an MCP client configuration, use the absolute path to anteater-mcp (or
anteater-mcp.exe) as command and omit the args array. macOS archives are ad-hoc
signed; public Developer ID signing and notarization are not yet configured.
Docker
The published image supports Linux amd64 and arm64. Docker Desktop on macOS and Windows runs the same Linux image:
cp .env.example .env
# Set ANTEATER_MCP_TOKEN in .env, then:
docker compose up -d
curl -fsS http://127.0.0.1:8787/healthThe Compose service is non-root, read-only, capability-free and bound to loopback by default. See DEPLOY.md before placing it behind public HTTPS.
Claude Desktop
Open the config file:
OS | Path |
macOS |
|
Windows |
|
Linux |
|
Add an anteater entry. The path must be absolute — Claude Desktop does not run the
server from your project directory:
{
"mcpServers": {
"anteater": {
"command": "node",
"args": ["/absolute/path/to/anteater-mcp/anteater-mcp.mjs"]
}
}
}With an API key:
{
"mcpServers": {
"anteater": {
"command": "node",
"args": ["/absolute/path/to/anteater-mcp/anteater-mcp.mjs"],
"env": { "ANTEATER_API_KEY": "your-secret-key" }
}
}
}Restart Claude Desktop completely (quit, don't just close the window). You should see 20 anteater tools, and the 6 prompts appear as slash commands.
claude_desktop_config.example.json in this repo is the same thing, ready to copy.
Claude Code
claude mcp add anteater -- node /absolute/path/to/anteater-mcp/anteater-mcp.mjsWith a key:
claude mcp add anteater -e ANTEATER_API_KEY=your-secret-key -- node /absolute/path/to/anteater-mcp/anteater-mcp.mjsVerify with claude mcp list.
ChatGPT
Two routes. The first needs no server.
ChatGPT → Explore GPTs → Create → Configure → Create new action
Paste the contents of
gpt-actions-openapi.jsoninto the Schema boxAuthentication — two workable choices:
None. Anteater API is readable anonymously. Simplest, but you share a global hourly quota with every other anonymous caller and will hit 429s.
API Key → Auth Type: Bearer, with your Anteater API key. ChatGPT then sends
Authorization: Bearer <key>on every call and you get your own quota. ⚠️ The key is stored with the GPT, so anyone you share the GPT with uses your key. Fine for a private GPT; do not publish one with your key in it.
Paste
gpt-instructions.mdinto the Instructions box
The GPT calls anteaterapi.com directly. Twelve operations cover courses, WebSoc,
grades, enrollment history and degree requirements.
The trade-off: the GPT receives raw JSON. WebSoc responses nest four levels deep
(schools > departments > courses > sections), so broad queries get truncated by
Actions — the supplied instructions tell it to always narrow. Prerequisite evaluation
and conflict detection are not available; the model has to reason them out itself.
ChatGPT's Developer Mode connector needs a public HTTPS MCP endpoint:
node anteater-mcp.mjs --http --port 8787 # binds 127.0.0.1 only — do not add --host
# in another terminal
ngrok http 8787 # or: cloudflared tunnel --url http://localhost:8787Add the URL under Settings → Connectors → Advanced → Developer mode. All 20 tools work, including batch course lookup, deterministic degree-progress checks, prerequisite checking and conflict detection.
ChatGPT's developer mode supports OAuth, no authentication, or mixed — there is no field for a custom header, so put the token in the URL query string:
https://<your-domain>/mcp?token=<ANTEATER_MCP_TOKEN>This URL form is a compatibility option, not a security improvement: URLs may be saved in connector settings and reverse-proxy logs. Use a Bearer header whenever the client supports one.
Both transports ChatGPT accepts, SSE and streaming HTTP, are implemented. For a permanent deployment rather than a tunnel, follow DEPLOY.md — the setup is identical to the Claude one, only the connector UI differs.
⚠️ Without
ANTEATER_MCP_TOKENthe endpoint is unauthenticated. Set it before exposing anything. See HTTP mode security.
⚠️ ChatGPT's MCP plugins are web-only. OpenAI's own documentation says developer mode is "available to Pro, Plus, Business, Enterprise, and Education accounts on the web" — the phone apps cannot reach an MCP server. For ChatGPT on a phone, use a Custom GPT whose Action points at this server's REST facade, described below.
Which ChatGPT route gets you what
Custom GPT + Actions | Developer mode + MCP | |
Server needed | No | Yes, public HTTPS |
Auth options | None · API Key (Basic/Bearer/custom header) · OAuth | Access token / API key with a Bearer, Basic or custom header scheme · OAuth · none. Claude's connector dialog takes request headers too, so |
Can carry your Anteater key | Yes, API Key → Bearer | Yes, server-side via |
What the model gets | 12 raw API operations, JSON | All 20 tools, formatted, plus 6 prompts and 4 resources |
Prerequisite / conflict checking | No — the model must reason it out | Yes |
Works on mobile | Yes | No — MCP plugins are web-only |
On your phone
Claude's iOS and Android apps support remote MCP servers. Deploy this behind HTTPS, add it once on claude.ai in a browser, and it syncs to the apps — you cannot add a new server from the phone itself. DEPLOY.md has a complete recipe: token auth, a systemd unit, Caddy or nginx, and the connector setup.
The ChatGPT Custom GPT route also works on mobile and needs no server at all.
Codex
Codex speaks streamable HTTP and reads the token from an environment variable, so it never lands in a config file:
export ANTEATER_MCP_TOKEN=... # in your shell profile
codex mcp add anteater --url https://your.domain/mcp --bearer-token-env-var ANTEATER_MCP_TOKENOr write it to ~/.codex/config.toml directly — a project-local .codex/config.toml
takes precedence over the global one:
[mcp_servers.anteater]
url = "https://your.domain/mcp"
bearer_token_env_var = "ANTEATER_MCP_TOKEN"Codex reads the variable at connect time and sends Authorization: Bearer <token>.
Any other MCP client
The server speaks standard MCP over stdio. Point your client at:
command: node
args: ["/absolute/path/to/anteater-mcp/anteater-mcp.mjs"]Or run it as a streamable-HTTP server at http://127.0.0.1:8787/mcp with
node anteater-mcp.mjs --http.
Protocol versions 2025-06-18, 2025-03-26 and 2024-11-05 are all accepted;
the server negotiates down rather than echoing whatever it is sent.
What you get
Tools (20)
Finding classes
Tool | What it answers |
| The workhorse. Live sections for a term: times, instructor, room, seats, waitlist, final exam. Supports an exclusive day filter ( |
| The one you want. Filter by GE, days, time window and open seats; rank by historical GPA |
| What courses exist at all |
| One course in full: description, prerequisites, restrictions, what it unlocks |
| Up to 50 known courses in one compact comparison, with optional details |
| Which quarters have data, plus the academic calendar |
| Department codes ( |
Judging a class before you take it
Tool | What it answers |
| Grade distribution by instructor or by term — "which professor should I take?" |
| A professor's courses and the grades they actually give |
| Rate My Professors average, review count and profile link for instructors teaching in a term |
| Day-by-day fill curves — "will I get in?" |
| Links to syllabi from past offerings — real workload and grading breakdown |
| Required and recommended textbooks, with ISBNs and UCI Library links |
Checking you can actually enrol
Tool | What it answers |
| Walks the prerequisite tree against what you've completed |
| Meeting conflicts, final-exam conflicts, total units, and whether the set is actually enrollable — missing discussions/labs, cancelled or full sections, TBA meetings |
| What an AP score is worth: units, GE, courses cleared |
Planning a degree
Tool | What it answers |
| Degree requirement trees, including university-wide GE |
| Deterministic progress check from completed courses and AP scores; keeps uncertain rules visibly unverified |
| Majors, minors, specializations |
| The catalogue's recommended quarter-by-quarter sequence |
Five of these compute things the upstream API does not provide: prerequisite-tree evaluation, schedule conflict detection, the join between the live schedule and historical grade data, AP-grant rendering, and deterministic degree-progress evaluation.
All 20 are annotated readOnlyHint: true — nothing here mutates anything.
Prompts (6)
In Claude Desktop these appear as slash commands. Each one drives a full multi-tool workflow rather than a single lookup.
Prompt | Arguments | What it does |
|
| Builds a complete conflict-free schedule from scratch |
|
| Compares instructors by grades, then by who's actually teaching |
|
| Finds a GE that fits your schedule and grades well |
|
| Validates section codes for conflicts, units and enrollment risk |
|
| Checks eligibility, including AP substitutions |
|
| Runs the deterministic progress check, then plans what remains |
* = required. Arguments named term, ge, department, major and course offer
autocomplete through the MCP completions API.
Resources (4)
Reference tables your client can read directly, without spending a tool call:
anteater://reference/departments— every department code and nameanteater://reference/terms— every term with schedule dataanteater://reference/ge-categories— GE codes and what they meananteater://reference/restriction-codes— enrollment restriction codes, per the Registrar
Configuration
API key
Optional, but recommended: anonymous calls draw on a shared hourly quota that is easy to exhaust, and a key gives you your own.
It will not unlock fuzzy search. /v2/rest/search rejects ordinary keys with
not permitted to access this resource — it needs elevated permission ICSSC grants
separately. Without it search_courses falls back to substring matching on title, then
description, and says so in its output. The structured filters (department,
geCategory, courseLevel, units) are unaffected and are usually the better tool
anyway.
Choose type
secret—publishablekeys are verified against theOriginheader, which Node does not send, so they will not work hereEither set it in your client config (see above), or for local development:
cp .env.example .env # then edit .env
set -a; . ./.env; set +a # load it without echoing the value.env is gitignored. Never paste a key into an issue, PR or screenshot.
Shared and personal upstream keys (MCPHub)
For direct execution inside MCPHub, import the stdio configuration in the MCPHub guide. Each user can bind a personal key, and a separate shared entry uses the public/default key. No independent Anteater container is required. The following header mechanism is for HTTP deployments.
HTTP calls can use either the deployment's shared ANTEATER_API_KEY or a personal
key sent as X-Anteater-Api-Key. The personal header takes precedence for that
request, including all of its concurrent upstream calls. If the header is absent,
the shared key is used (or anonymous upstream access if no shared key is configured).
A blank or ambiguous personal header is rejected; an invalid personal key never
retries with the shared key. Anteater API caches are separated by credential.
Authorization: Bearer <ANTEATER_MCP_TOKEN> still authenticates access to this
server. It is independent of the upstream API key and is required for both modes
when configured. Personal keys belong in headers, never URL query parameters.
See MCPHub setup for separate Shared and Personal server entries. Personal entries require a binding; Shared remains available without one.
Environment variables
Variable | Purpose |
| Your secret key. See above. |
|
|
| Defaults to |
| Independent fallback for live WebSoc schedule queries. Defaults to |
| HTTP mode only, and required before you expose the server. Clients send |
| HTTP mode only. Comma-separated extra origins to allow. |
| HTTP mode only. Which direct peers may set |
| HTTP mode only; equivalent to |
Command line
node anteater-mcp.mjs # stdio (what MCP clients use)
node anteater-mcp.mjs --http # HTTP on 127.0.0.1:8787, endpoint /mcp
node anteater-mcp.mjs --http --port 9000 # different port
node anteater-mcp.mjs --http --host 0.0.0.0 # bind all interfaces (warns; see below)
node anteater-mcp.mjs --list-tools # list every toolHTTP mode security
Binds
127.0.0.1by default.server.listen(port)with no host binds every interface, which would expose an unauthenticated server to the whole LAN.--hostis required to change that, and it warns when you do.Validates
Origin. The MCP specification requires this of local HTTP servers: without it, any page you visit can POST to your port and drive every tool (DNS rebinding / CSRF). Requests with noOrigin— native MCP clients — are allowed; requests with one must be localhost or listed inANTEATER_ALLOWED_ORIGINS.Access-Control-Allow-Originechoes the single validated origin, never*.Unauthenticated unless
ANTEATER_MCP_TOKENis set. That is fine on loopback and not fine anywhere else; the server warns at startup if it is bound off-loopback without one. See DEPLOY.md.HTTP activity is logged to stderr as one JSON request line and one response line. Logs include a request ID, method, sanitized target, remote address, status, duration, RPC/tool name, and outcome when available. Authorization values and RPC arguments are never logged; URL token values are shown as
[REDACTED]./healthreports status and the source URL;/sourceredirects to this repository, which helps anyone deploying a modified copy comply with AGPL section 13.
Errors
A failed tool call returns isError: true and a single text content item holding a JSON
object, so a client can tell a bad credential from a service outage without parsing prose:
{"error": "RATE_LIMITED", "message": "Anteater API rate limit hit. Wait a moment, or set ANTEATER_API_KEY ...", "retry_after_seconds": 30}
| Meaning |
| The requesting user's own key was rejected: Anteater API answered a JSON 401 (or a JSON 403 whose body says the key is invalid) to a key sent in the |
| Anteater API answered a JSON 403: the key is valid but not allowed to use that endpoint. |
| Anteater API answered 429. |
| The tool input was wrong: a missing or malformed argument, an unknown department or term, a course that does not exist (upstream 404), or an upstream 400/422. |
| Network failure, timeout, 5xx, a non-JSON reply (for example a WAF or CDN challenge page, including a non-JSON 401/403), any other unexpected fault, or the server's own configured key being rejected ( |
message stays human-readable and is safe to show to a user; it never contains the API
key. Codes are stable; wording is not.
The REST facade (/tools/<name>) keeps HTTP 200 with {"result": ..., "isError": true} for
a tool failure. result is the same JSON string as the MCP text, and a top-level
"error": "<CODE>" repeats the code. Transport problems keep their HTTP status but now
share one body shape, {"error": "<CODE>", "message": "<text>"}, with error one of
INVALID_ARGUMENT (400), UNAUTHORIZED (401), NOT_FOUND (unknown tool, 404),
METHOD_NOT_ALLOWED (405) or PAYLOAD_TOO_LARGE (413). A failing resources/read
keeps JSON-RPC error -32603 and adds data: {"error": "<CODE>"}. All of this is
described in /openapi.json. The static gpt-actions-openapi.json talks to Anteater API
directly and is unaffected.
Changes
1.0.0-beta.3
Tool failures are now structured. The text content of an
isErrorresult is a JSON object{"error": CODE, "message": text}instead ofError: ...prose. Codes:CREDENTIAL_INVALID,PERMISSION_DENIED,RATE_LIMITED,INVALID_ARGUMENT,SOURCE_UNAVAILABLE.REST facade
resultformat change. On failure,/tools/<name>still returns HTTP 200 withisError: true, butresultis now that JSON string rather thanError: ...prose, and a top-levelerrorcode is added. Transport errors (400, 401, 404, 405, 413) now return{"error": CODE, "message": text}where some returned plain text or{"error": text}. Match onerror, not on the oldError:prefix.New
ANTEATER_API_KEY_SCOPE(operatordefault, oruser).get_course,check_prerequisitesno longer report an upstream outage or rate limit as "No course ...": only a real 404 does.
Troubleshooting
Symptom | Cause and fix |
Tools don't appear in Claude Desktop | The path must be absolute, and you must fully quit and reopen the app. Check the config parses: |
| The anonymous quota is shared and replenishes hourly. Set |
| Your own API key was rejected. Replace the |
| Operator: replace |
| Fuzzy search needs a privileged key that ordinary keys are not granted; it falls back to substring matching and says so. Use the structured filters instead. |
| A whole term is tens of thousands of sections. Add |
| UCI has three summer terms. Use |
| Use |
A course has no grade data | Recent quarters lag, and P/NP-only courses have none. |
Seats look stale | Live figures are cached for 5 minutes; the catalogue for 24 hours. |
Schedule fallback appears | Anteater API was unavailable, so the schedule came from Zotcourse's WebSoc-backed endpoint. Verify seats and section pairing in WebReg. Set |
Development
npm test # 20 conformance tests; makes no API calls
npm run test:live # live calls; needs a key in practice
npm ci # build tooling only; the shipped server has no runtime packages
npm run build:sea # standalone binary; requires the exact Node in .node-versionUPSTREAM.md records the exact Anteater API version and the upstream commits this server was validated against, endpoint by endpoint — start there when the API changes and something begins returning wrong or empty results.
VERIFICATION.md is a full release checklist — per-regression pass criteria, security checks and integration checks — written so someone who has never read the code can run it.
CI uses the same pinned Node 24 LTS release as Docker and native packaging. It runs the offline suite, syntax and OpenAPI checks, a standalone-executable smoke test, and a locked-down container protocol test. It deliberately makes no live Anteater API calls, so it never draws on the public rate limit.
Pushing a tag that exactly matches v plus the package.json version builds six native
executables, generates checksums and provenance attestations, pushes an amd64/arm64 image
to GHCR, and publishes the GitHub Release. Stable tags update :latest; every release
updates :beta; exact :vX.Y.Z tags are immutable.
After the first image publish, set the GHCR package visibility to Public once. The
workflow uses the scoped GITHUB_TOKEN; if repository policy blocks bot-created Releases,
add a fine-grained RELEASE_PAT secret with Contents write access, matching the upstream
project's fallback.
Scope
Anteater API also serves dining halls, library traffic and study-room bookings. Those are deliberately not wrapped — this server stays focused on choosing and registering for classes.
LARC tutoring sections are in scope but effectively dead upstream: /v2/rest/larc returns
22 courses for 2024 Fall and nothing for any term since, so a tool would always answer
"none" for the term a student is actually planning.
Known limitations
These are properties of the upstream data, not bugs. The server states them rather than papering over them, because the alternative is confident wrong advice.
WebSoc does not publish which discussion belongs to which lecture. Some courses encode it in the section number (
Lec A→Dis A1), others number companions independently (I&C SCI 31: lectures A/B, labs 1–9).check_scheduletherefore tells you when a required component is missing entirely, and when a pairing cannot be verified — but it cannot confirm that a given lab goes with a given lecture. Confirm that on WebReg. Neither of ICSSC's own clients infers this either: AntAlmanac and PeterPortal both render sections as a flat list and leave the pairing to the student, which is good evidence the data simply is not there.Enrollment restrictions are not evaluated against you.
search_sectionsandrecommend_coursessurface the codes and their meanings; whether you satisfy "Major only" or "Graduate only" is enforced by the registrar.Transfer and community-college coursework is absent.
check_prerequisitesreports any completed course it does not recognise instead of silently ignoring it, but only an advisor can clear transfer credit.No registration-window dates. The academic calendar covers instruction and finals; it does not say when your enrollment window opens. Check StudentAccess.
Grade data lags. Recent quarters may be missing, and a recent term's grades are often filed under
STAFF. A small sample size makes an average GPA unreliable — the tools always printnso you can judge.Historical GPA is course-wide.
recommend_coursesranks by the average across all past instructors, which may not be whoever is teaching this term. Useget_course_gradesto check the specific instructor before deciding.
Bugs found and fixed before release
A six-dimension parallel review (logic, MCP conformance, live-API contract, security, robustness, repo readiness) produced 41 raw findings, 38 after deduplication. The ones that would actually have misled someone:
Bug | Consequence |
A bare | Both transports. Over HTTP that was an unauthenticated 4-byte denial of service. |
Every final exam date was one month early | WebSoc's |
7 of 19 restriction codes were wrong |
|
| The bare |
Standalone lab courses counted as 0 units |
|
| Every seminar-only GE was invisible; GE-1A returned nothing at all. |
| The endpoint has a required |
HTTP mode bound | While logging "listening on localhost". |
Fall sorted as the earliest term of its year | Reversed the chronology in |
A second round, driving the server through six realistic student scenarios end to end, found 54 more — 10 of them blockers. The worst:
Bug | Consequence |
| It checked only times. A lecture with no required lab, or a full or cancelled section, passed silently — the student would be rejected at WebReg. |
| A student who could only attend Tu/Th was shown three- and four-day courses, and courses whose mandatory labs were all MWF. |
A bare instructor surname matched nothing |
|
Degree requirements defaulted to the 2023–2024 catalogue | Three years stale, with no indication, for a student on 2026–2027. |
| Then printed a confident "NOT satisfied" for work the student had actually done. |
| Its highest-ranked GE picks were courses the student could not enrol in. |
| When given the comma-separated string that |
Also fixed: inverted check marks in NOT prerequisite subtrees, course numbers lost for
the 48 department codes containing a space, multi-byte UTF-8 corrupted across HTTP chunk
boundaries, a quadratic-backtracking regex on unvalidated input, and socAvailable
mislabelled as "enrollment opens" when it is the schedule publication date.
API quirks worth knowing
Undocumented upstream; all handled here, and listed in case they save you the debugging.
daysmust be comma-separated.Tu,Thworks,TuThis rejected. It matches at least one of the listed days, not all of them.enrollmentHistoryreturns parallel arrays (dates[],totalEnrolledHistory[],requestedHistory[], …), not scalars.-1means "not tracked".finalExam.monthis 0-indexed.Course comments are raw HTML fragments, complete with
<p>and".startTime/endTimemean "starts at or after" and "ends at or before", not interval overlap./v2/rest/searchneeds a privileged API key. An ordinary key is refused withnot permitted to access this resource, which is a different error from thekey is requiredyou get with no key at all — worth distinguishing, since telling someone who already has a key to get a key is a dead end./v2/rest/websoc/syllabitakescourseId, notdepartment+courseNumber./v2/rest/courseMaterialsneedsdepartmentANDcourseNumbertogether. Either alone is refused, and it collapses the three summer sessions into a singleSummer.Restriction strings contain prose.
"A and N"must be split on whitespace and have the literaland/ordiscarded, or the conjunction renders as a code.Section status is an enum, not free text:
OPEN,Waitl,FULL,NewOnly, or empty. OnlyOPENmeans a continuing student can enrol now —NewOnlymarks seats held for incoming students.numNewOnlyReservedcounts seats inside the capacity that are reserved the same way, so the apparent opening overstates the real one.
Distribution
Published to the MCP Registry as
io.github.KKazuhaK/anteater-mcp, listing the container image only. The registry entry
describes how to run your own instance; it does not point at anyone's deployment, since a
hosted instance is gated behind its own token and its upstream quota belongs to whoever
runs it.
Each release also publishes the GHCR image and standalone binaries for six platforms.
Licence and attribution
Data from Anteater API, maintained by ICSSC Projects.
This is not an official UCI tool. Verify on WebReg or the General Catalogue before registering. Use is subject to Anteater API's attribution policy.
Licensed AGPL-3.0-or-later, matching the upstream Anteater API server so code can move freely in either direction if this is ever contributed upstream. This is an independent HTTP client and contains no upstream source code. If you modify it and run it as a network service, AGPL section 13 requires you to offer users your Corresponding Source — see NOTICE.
For academic use:
@misc{anteater-api,
author = {ICS Student Council},
title = {Anteater API},
year = {2024},
howpublished = {\url{https://github.com/icssc/anteater-api}},
}Available Tools
16 toolsap_creditWhat an AP exam is worth at UCIARead-onlyIdempotent
Look up what AP exam scores earn at UCI: units, elective units, GE categories and specific courses cleared. Use for incoming students planning a first quarter, or to work out whether an exam score already satisfies a prerequisite. The catalogueName in the output is the exact string check_prerequisites expects in apScores.
Inputs: exam.
check_prerequisitesCheck whether you can take a courseARead-onlyIdempotent
Evaluate a course's prerequisite tree against the courses a student has already completed, showing exactly which requirements are met and which are missing. Also reports enrollment restrictions (major-only, etc.), which the API cannot verify automatically.
Inputs: courseId (required), apScores, completed.
check_scheduleCheck a set of sections for conflictsARead-onlyIdempotent
Given a term and a list of 5-digit section codes, build the weekly timetable, total the units, and report any meeting-time or final-exam conflicts. Use this to validate a proposed schedule before registration.
Inputs: term (required), sectionCodes (required).
course_gradesGrade distribution for a courseARead-onlyIdempotent
Historical grade distributions and average GPA for a course, broken down by instructor (default) or by term. Use this to answer 'which professor should I take?' or 'how hard is this class?'. Data is from UCI's public records; recent quarters may be missing.
Inputs: year, groupBy, quarter, courseId, +4 more.
enrollment_historyHow fast a class fills upARead-onlyIdempotent
Historical enrollment for a course: final enrollment vs capacity, waitlist size, and (for recent terms) the day-by-day fill curve. Use this to judge registration risk — 'will I get in?', 'do I need to enroll at 7am?', 'does the waitlist clear?'.
Inputs: year, quarter, courseId, showCurve, +4 more.
find_sectionsFind class sections in a term (WebSoc)ARead-onlyIdempotent
The main course-finding tool. Queries UCI's live schedule of classes for one term and returns matching sections with meeting times, instructor, location, seats taken, waitlist and final exam. Filter by department, course number, GE category, instructor, days of week, time window, and seat availability. At least one narrowing filter besides the term is required.
Inputs: term (required), ge, days, limit, +17 more.
get_courseGet full course detailsARead-onlyIdempotent
Full catalogue detail for one course: description, units, prerequisites (text and structure), courses that unlock from it, enrollment restrictions, GE credit, repeatability, and which terms it has been offered. Use this before advising someone to take a course.
Inputs: courseId (required).
get_program_requirementsGet degree requirementsARead-onlyIdempotent
The full requirement tree for a major, minor or specialization, or the university's general undergraduate requirements (GE categories, unit minimums). Use for degree planning — 'what do I still need?'.
Inputs: kind, block, programId, catalogYear, +1 more.
get_syllabiFind past syllabi for a courseARead-onlyIdempotent
Links to syllabi from previous offerings of a course, by term and instructor. Use to show a student what the workload, grading breakdown and topics actually look like before they enroll. Links point at UCI Canvas and may require a UCInetID login.
Inputs: courseId (required), year, quarter, instructor.
instructor_infoLook up an instructorARead-onlyIdempotent
Find a UCI instructor and see their title, department, the courses they have taught, and their average GPA given across all courses. Use to evaluate a professor before enrolling.
Inputs: name, ucinetid, includeGrades.
list_departmentsList department codesARead-onlyIdempotent
List UCI department codes used by the schedule of classes (e.g. COMPSCI, I&C SCI, BIO SCI). Use when you are unsure of the exact code for a subject. Optionally filter by a substring.
Inputs: filter.
list_programsList majors, minors and specializationsARead-onlyIdempotent
List UCI degree programs. Use to find the program id needed by get_program_requirements.
Inputs: kind, filter.
list_termsList terms and academic calendarARead-onlyIdempotent
List the UCI terms (quarters) that have schedule-of-classes data, plus the current week of instruction. Optionally pass a term to get that term's academic calendar (instruction begins/ends, finals week, holidays). Call this first when the user says 'next quarter' or doesn't name a term.
Inputs: term.
recommend_coursesRecommend courses matching constraintsARead-onlyIdempotent
The 'find me a class' tool. Combines the live schedule with historical grade data to rank candidate courses for a term. Filter by GE category, department, level, days of week, time window and seat availability; results are ranked by historical average GPA (or by open seats). Ideal for 'find me an easy GE-2 with open seats that doesn't meet before 10am'.
Inputs: term (required), ge, days, limit, +7 more.
sample_programSample four-year plan for a majorARead-onlyIdempotent
The catalogue's recommended quarter-by-quarter course sequence for a major. Use to answer 'what should I take first year?' or to sanity-check whether a student is on track. Call with no argument to list the majors that have a published plan.
Inputs: program.
search_coursesSearch the course catalogueARead-onlyIdempotent
Search the UCI course catalogue (all courses that exist, not term-specific offerings). Use a free-text query for fuzzy search ('machine learning', 'CS 161'), or the structured filters to browse (e.g. all GE-2 lower-division courses worth 4 units). To see which sections actually run in a given quarter and whether seats are open, use find_sections instead.
Inputs: limit, query, maxUnits, minUnits, +6 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 16 tools
Most tools target distinct resources and workflows; course lookup is split between catalogue search, live section search, and ranked recommendation, but descriptions explicitly steer usage. A few adjacent tools (course_grades vs instructor_info, sample_program vs get_program_requirements) could be confused in edge cases.
The dominant verb_noun pattern (list_, search_, get_, find_, check_, recommend_) is clear and predictable. Four noun_noun names (ap_credit, course_grades, instructor_info, enrollment_history) are minor deviations rather than a break in readability.
16 tools is at the high end, but each maps to a distinct aspect of UCI course planning: catalogue, sections, grades, instructors, prerequisites, schedules, syllabi, and degree requirements. It feels broad rather than padded, though a slightly leaner set might combine some grade/enrollment lookups.
For a read-only academic-advising server, the surface covers the main workflows: discovering programs/requirements, searching and validating courses, checking prerequisites and schedules, and evaluating instructors via grades and history. There are no obvious dead ends; list_programs and list_terms feed the tools that need IDs and terms.
Maintenance
Related MCP Connectors
Teamfight Tactics data & AI coaching for Claude and ChatGPT — 19 tools, built-in Riot key.
Search award flights and cash fares, optimize points, and predict fares inside ChatGPT and Claude.
Track calories and macros right in Claude or ChatGPT and build a personal nutrition diary
111SEO research, Search Console, GA4 and PPC tools for Claude and ChatGPT.
Related MCP Servers
- AlicenseBqualityDmaintenanceEnables Claude to interact with core AWS services like S3, EC2, RDS, and CloudWatch, along with a generic SDK wrapper for any AWS operation. It also supports cost monitoring and optional vector store capabilities for document ingestion and search.103-
- AlicenseCqualityBmaintenanceProvides Claude with 44 tools for confidence gating, typed outputs, hallucination detection, and constraint enforcement during conversations.5136 PyPI1MIT
- AlicenseCqualityBmaintenanceProvides 40 tools to Claude for Wikipedia citation analysis, edit history, and DOI/ISBN annotation, enabling citation quality scoring and metadata enrichment without leaving the chat.3829 PyPI1MIT
- AlicenseBqualityCmaintenanceEnables a local-first MBA recruiting coach inside Claude that remembers your campaign, tracking target firms, live job boards, deadlines, applications, connections, and warm intros, while drafting human-approved outreach and never submitting applications or scraping LinkedIn.23MIT