rezen-mcp
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
rezen-mcp
An MCP server that lets AI assistants answer questions about school results (classes, scores, rankings, report-card data), with a tested tool surface and a reproducible eval suite.
Status: Phase 0 complete (scaffold). One tool works end to end. See the implementation plan for what's next.
All data in this repository is synthetic. No real students, schools or records are used, ever.
Why this exists
Report-card and results data is a good test bed for MCP tool design: it has real edge cases (missing scores, ties in rankings, strict per-school privacy) and clear right answers, which makes it possible to measure how well an assistant uses the tools instead of guessing.
Related MCP server: College AI Assistant
Quick start
Requires Node 20+ (22 recommended, see .nvmrc) and pnpm (the exact version is pinned in package.json; corepack enable will pick it up).
pnpm install
pnpm check # lint + typecheck + tests + build
pnpm dev # run the server over stdio
pnpm seed # print a summary of the synthetic datasetTo try it with an MCP client over stdio, point the client at the built server:
pnpm build
node dist/index.jsTools
Tool | Status | Purpose |
| Done | List a school's classes with level and student count |
| Planned (Phase 1) | Scores for a class and term |
| Planned (Phase 1) | One student's report-card data |
| Planned (Phase 1) | Class ranking with documented tie handling |
| Planned (Phase 1) | Flag incomplete score entries |
Full definitions live in docs/FEATURE_SPEC.md.
Project layout
src/
data/ domain types, synthetic data generator, repository interface
tools/ one file per MCP tool
server.ts builds the MCP server and registers tools
index.ts stdio entry point
tests/ unit tests and tests through a real MCP client
scripts/ seed script
docs/ spec, plan, decision log, AI workflowHow this project is run
Work is spec-first and phase-based, and AI assistance is used under written rules. Read:
docs/FEATURE_SPEC.md: what we're building and what we're notdocs/IMPLEMENTATION_PLAN.md: phases, tasks, and exit criteriadocs/DECISIONS.md: decision log (ADRs)docs/AI_WORKFLOW.md: how AI is used, and how it is kept honest
License
MIT
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP-native AI evaluation: rubric audits, eval suites, and proof reports for AI/LLM output.
Hosted MCP endpoint with realistic fake data for prototyping agents. 12 tools, no setup.
Trusted multi-domain data for AI: 59 tools, MCP Apps, Skills, 520+ cross-domain benchmarks.
MCP server providing access to the Scorecard API to evaluate and optimize LLM systems.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceProvides tools for querying student academic data such as subjects, marks, performance reports, timetable, exams, fees, events, holidays, and assignments via natural language.-
- FlicenseNot gradedqualityDmaintenanceProvides MCP tools for searching student profiles, viewing marks/attendance, and finding low-attendance students. Enables AI assistants like Gemini to interact with college student data through natural language.-
- FlicenseNot gradedqualityCmaintenanceEnables AI assistants to query a simulated school database for student marks, top rankers, class statistics, enrollment records, awards policy, and school rules via MCP tools, resources, and prompts.-
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to retrieve and work with Moscow Electronic School data, including schedules, homework, grades, rankings, school info, meals, passes, olympiads, and portfolio, via authenticated MCP tools.MIT