ibu-mcp: Instructions file for Claude Code

CLAUDE.md

ibu-mcp CLAUDE.md is an instructions file for Claude Code from Haris0059/ibu-mcp. It costs 583 tokens per session, scanned A, original, MIT.

Instructions for a program that exposes student-portal data through MCP tools. MCP is a standard way for AI assistants to call outside tools; this server communicates through a machine-readable input and output stream.

In plain words
What is it for?
Run, build, and start the server, add student-portal tools, and keep tool registration and logging compatible with MCP.
Why use it?
They prevent ordinary log messages from breaking that stream and define consistent names and structures for the available tools.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is Haris0059/ibu-mcp's own configuration. It tells Claude Code how to work on ibu-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ibu-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Haris0059/ibu-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Haris0059/ibu-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Haris0059/ibu-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ibu-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/haris0059/ibu-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/haris0059/ibu-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/haris0059/ibu-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/haris0059/ibu-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ibu-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/haris0059/ibu-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/haris0059/ibu-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 583 This file is loaded in full into every session.
When invoked 583 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00583 $0.00583
Opus 5 $0.00292 $0.00292
Sonnet 5 $0.00117 $0.00117
Haiku 4.5 $0.00058 $0.00058

Measured 9d ago against content hash 233338dfb3a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ibu-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this is

A stdio MCP server (@modelcontextprotocol/sdk) exposing IBU student-portal data as tools. Entry: src/index.ts. Tool modules live in src/tools/*.ts. HTTP client and auth in src/client.ts and src/auth.ts.

Commands

  • npm run dev — run via tsx (no build step)
  • npm run buildtsc to dist/
  • npm start — run built server from dist/index.js

There is no test framework and no linter configured.

Stdio MCP — do not write to stdout

The server uses StdioServerTransport. stdout is the MCP protocol channel. Any stray console.log, process.stdout.write, or printed banner will corrupt the JSON-RPC stream and break the client. Use console.error (stderr) for all logging/debug output.

Tool naming and registration

  • All MCP tool names use the ibu_<verb>_<noun> prefix (e.g., ibu_get_grades, ibu_mark_notification_read).
  • Tools are defined as entries in a domain-grouped array in src/tools/<domain>.ts with name, description, inputSchema (JSON Schema with properties/required), and handler.
  • Register the array in src/index.ts via registerTools(...). The registrar in src/index.ts converts the JSON Schema shape into zod and wires error handling — match the existing shape so the conversion keeps working (string properties, optional enum, description).

Error handling convention

src/client.ts maps known HTTP statuses to user-facing messages (401 = expired JWT, 402 = unpaid fees, 403 = locked account, 301 = mandatory survey, 500 = upstream IBU issue). When adding tools, let ibufetch() raise — don't swallow these.

Gotcha: Sporadic 5xx responses from rest.ibu.edu.ba are most commonly caused by unpaid financials on the account being queried, not by a code bug. Don't add retries or "fix" 5xx handling without checking that first.

Auth tokens

IBU_ACCESS_TOKEN and IBU_USER_JWT come from the user's browser session (DevTools → Network on rest.ibu.edu.ba). The JWT expires when the session ends — a 401 means the user needs to re-copy the header, not a code change.

Read the full file on GitHub · 40 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 40 lines · 583 tokens per session scan A 233338dfb3a9

Subscribe to this mod's changes

ibu-mcp CLAUDE.md is an instructions file published in the GitHub repository Haris0059/ibu-mcp (2 stars, last pushed 3mo ago), licensed MIT. It adds 583 tokens to every session, about $0.0029 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens