<p align="center"> <img src="assets/logo.png" alt="openemis-mcp logo — AI bridge for OpenEMIS school management" width="320"> </p>

openemis-mcp — AI bridge for OpenEMIS school management

Free, read-only MCP bridge between AI agents and any OpenEMIS school.

OpenEMIS is a free, open-source school management information system developed by UNESCO and KORDIT. It runs the day-to-day administration of every kind of educational institution — kindergartens, primary schools, secondary schools, secondary vocational institutions, technical colleges, and universities — managing students, staff, attendance, assessment, infrastructure, meals, scholarships, examinations, training, and ministry-level reporting. This MCP gives AI agents read-only access to the data in any OpenEMIS school so you can ask questions in plain English and get answers in seconds.

Built on the published OpenEMIS Core API (reference: api.openemis.org/core) and verified against the public demo at demo.openemis.org/core.

What this is: openemis-mcp is a free MCP server that connects AI assistants (Claude, Cursor, Codex) to the OpenEMIS school management system. It exposes 678 resources — students, student attendance, student risks, staff, exams, infrastructure — across 26 curated read-only playbooks, plus 14 redirect stubs for write operations.

Ask in plain English:

"How many current students are at Avory Primary?"

The agent plans the calls, this MCP delivers the data:

"Avory Primary School has 97 currently enrolled students across 6 classes."

No code. No JSON. Just ask.

What's included (free, MIT)

26 read-only playbooks covering attendance, assessment, student profiles, staff profiles, infrastructure, meals, risk dashboards, class reports, timetables, audit logs, school accreditation / registration, admission and enrolment queue state, and a primer on how the OpenEMIS workflow plugin powers every multi-step approval — each verified against the v5 manifest at 100% resource coverage. 14 additional playbook stubs are discoverable here but redirect to [openemis-mcp-pro](https://github.com/tixuz/openemis-mcp-pro) for the actual write/auth steps.

Translations: Русский · Español · हिन्दी · العربية — the original 17 view playbooks also translated in all four languages; 9 newer playbooks (added in v1.1.0 for Core 5.10.0, plus the two workflow playbooks) are English-only for now.

✏️ Write operations (creating/updating records in OpenEMIS) require [openemis-mcp-pro](https://github.com/tixuz/openemis-mcp-pro). This free server is intentionally read-only — post, put, and delete are not available.

What's in Pro

openemis-mcp-pro adds write tools, remote hosting, and ChatGPT compatibility on top of this free read-only server.

HTTP server mode lets you install Pro once on an Oracle Always Free ARM instance and connect from any device — no per-machine setup. The built-in OpenAPI adapter means teachers can use ChatGPT (or any AI assistant) to mark attendance and look up student records by importing a single schema URL. See the ChatGPT Teacher Guide for step-by-step setup.

→ Pricing: [email protected]

Install

Requires Node 22+.

git clone https://github.com/tixuz/openemis-mcp.git
cd openemis-mcp
npm install
npm run build
cp .env.example .env
$EDITOR .env

Configure

OPENEMIS_BASE_URL=https://demo.openemis.org/core
OPENEMIS_USERNAME=admin
OPENEMIS_PASSWORD=your_password
OPENEMIS_API_KEY=your_api_key

Smoke test

set -a && source .env && set +a
node scripts/smoke-login.mjs

Register with Claude Code

claude mcp add openemis \
  --env OPENEMIS_BASE_URL="https://your-instance/core" \
  --env OPENEMIS_USERNAME="…" \
  --env OPENEMIS_PASSWORD="…" \
  --env OPENEMIS_API_KEY="…" \
  -- node "$(pwd)/dist/server.js"

Works with any MCP-compatible client: Claude Code, Cursor, Cline, Codex (via gemmy-and-qwenny), or any stdio MCP client.

Verbose logging (optional)

Capture every tool call and its response as JSONL — useful for debugging, tuning playbooks, or sharing a bug report.

# stderr (visible in your MCP client's log panel)
OPENEMIS_LOG_VERBOSE=1 node dist/server.js

# write to a file
OPENEMIS_LOG_VERBOSE=1 OPENEMIS_LOG_FILE=/tmp/openemis.jsonl node dist/server.js

Each line is a JSON object: {ts, type:"tool_call"|"tool_result"|"tool_error", tool, args?, result?, latency_ms, ...}. Credential-shaped keys (password, authorization, api_key, token, secret) are redacted automatically.

⚠️ Privacy: tool_result entries contain the actual OpenEMIS data returned to the agent — student names, staff IDs, enrollment details. Enable only on instances you own, or with explicit consent. Default is OFF.

🌐 Remote / server install: openemis-mcp-pro adds an HTTP server mode — install once on Oracle Always Free and every AI assistant (Claude Code, Cursor, ChatGPT) connects by URL with no per-machine setup. See the ChatGPT Teacher Guide for how to let teachers mark attendance via ChatGPT.

Playbooks

24 read-only workflow guides — see docs/playbooks/. Write-side playbooks (mark attendance, enrol a student, set school accreditation, etc.) are discoverable here as stubs that point at [openemis-mcp-pro](https://github.com/tixuz/openemis-mcp-pro).

Read playbooks (school data lookups)

New in v1.2.0 (OpenEMIS Core 5.13.0)

• List-filtering via the native `IN` operator (POCOR-9660). _conditions=<field>:IN(1,2,3) filters any field by a value list — including non-PK and composite-PK resources — so a class roster is one call: query institution-class-students by institution_class_id, then security-users with _conditions=id:IN(101,102,103). params.ids="1,2,3" now collapses to a single ?id=1,2,3 round-trip by default (set OPENEMIS_CORE_IN_OPERATOR=off only for pre-5.10 cores).
• Stricter filter validation (POCOR-9697). Filtering on a field that does not exist on a resource now returns HTTP 400 instead of being silently ignored — use exact field names from the Resource Reference.
• 3 new read-only Runtime resources (POCOR-9694): tasks, task-jobs, task-failures — the OpenEMIS Runtime queue / job / failure projection. 678 resources · 3,361 endpoints total.

New in v1.1.0 (OpenEMIS Core 5.10.0)

Loaded via openemis_get_playbook — full English content in data/playbooks.json. Translations and per-playbook markdown docs land in a follow-up release.

Write / auth playbooks (stubs — install mcp-pro)

mark-student-attendance, mark-staff-attendance, enroll-new-student, record-behavior-incident, submit-exam-marks, generate-student-report-card-pdf, generate-institution-statistics-pdf, add-institution-asset, record-infrastructure-repair, add-meal-programme, resolve-my-identity, set-school-accreditation, set-school-registration, mark-student-meal-participation — all redirect agents to [openemis-mcp-pro](https://github.com/tixuz/openemis-mcp-pro), which ships openemis_create / openemis_update / openemis_delete and per-user authentication.

Core compatibility

Tested against OpenEMIS Core 5.13.0 (master, June 2026). 5.7 – 5.12 deployments are also supported — the public REST surface is backwards-compatible.

Capability flag — POCOR-9660 multi-id GET

openemis_get accepts params.ids = "1,2,3" for batch lookups. Core 5.10+ carries POCOR-9660 (?id=1,2,3 support in CrudApiController), so the handler collapses the batch into a single round-trip by default. Pointing at an older Core (5.7 – 5.9) that lacks the native operator? Force the legacy parallel fan-out:

OPENEMIS_CORE_IN_OPERATOR=off

For composite-PK or view resources — where ids does not apply — use _conditions=<field>:IN(1,2,3) instead; it filters any field by a value list and works regardless of this flag.

Architecture

Agent (Claude / Cursor / Codex / …)
        │ MCP stdio
openemis-mcp  ←  6 read tools + 26 read playbooks + 14 redirect stubs
        │ HTTPS + Bearer JWT
OpenEMIS Core API  /api/v5/{resource}   (3,361 endpoints across 678 resources)

Domain-scoped discovery keeps conversations small — openemis_discover("attendance") returns the 20–30 endpoints relevant to attendance, not all 3,361.

🖥️ Server / HTTP mode (install once on Oracle, connect from anywhere including ChatGPT) is available in [openemis-mcp-pro](https://github.com/tixuz/openemis-mcp-pro).

Docs

• Resource Reference — all 678 resources with method availability (Core 5.13.0)
• Playbooks — 17 view playbooks in 5 languages + 9 newer English-only playbooks (translations follow)
• GLOSSARY.md — key terms: OpenEMIS, MCP, attendance, student risks, and more
• FAQ.md — common questions about school management with OpenEMIS MCP
• ACKNOWLEDGEMENTS.md — the AI team that built this

Licence

MIT © 2026 Khindol Madraimov

Not affiliated with OpenEMIS or its maintainers. Third-party bridge to the public Core API. Credentials stay on your machine.