yargi-mcp: Instructions file for Claude Code

CLAUDE.md

yargi-mcp CLAUDE.md is an instructions file for Claude Code from saidsurucu/yargi-mcp. It costs 23,161 tokens per session, scanned A, original, MIT.

Project instructions for a FastMCP server that provides programmatic access to Turkish legal databases through the Model Context Protocol. It connects coding agents to searches across several Turkish legal institutions.

In plain words
What is it for?
Use them when installing, configuring, developing, or deploying the server and its legal research tools.
Why use it?
They explain the server's setup, installation, authentication, and available legal-database integrations so development and deployment follow the project rules.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; positional $N argument; mentions Claude Code.

This is saidsurucu/yargi-mcp's own configuration. It tells Claude Code how to work on yargi-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 yargi-mcp configures →

About the project

Yargı MCP is a Model Context Protocol server that lets language-model applications search and retrieve documents from Turkish legal databases, including court and regulatory sources. It is used by MCP clients such as Claude Desktop and other supported applications to access Turkish legislation and case-law materials.

saidsurucu/yargi-mcp · 1,112 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to saidsurucu/yargi-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/saidsurucu/yargi-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/saidsurucu/yargi-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 yargi-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/saidsurucu/yargi-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/saidsurucu/yargi-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/saidsurucu/yargi-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/saidsurucu/yargi-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 yargi-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/saidsurucu/yargi-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/saidsurucu/yargi-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23,161 This file is loaded in full into every session.
When invoked 23,161 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.23161 $0.23161
Opus 5 $0.11581 $0.11581
Sonnet 5 $0.04632 $0.04632
Haiku 4.5 $0.02316 $0.02316

Measured 11d ago against content hash 2b9a79814fdd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

yargi-mcp CLAUDE.md scanned grade A with 1 finding 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 11d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -X POST https://api.yargimcp.com/mcp/ \
Origin

Copies of this mod

1 near-identical copy found in the catalogue:

CLAUDE.md · 2,209 lines

How it starts

The opening of the file, as written. The whole thing — 2,209 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.

Project Overview

This is a FastMCP server that provides programmatic access to Turkish legal databases through the Model Context Protocol (MCP). It integrates with 11 different Turkish legal institutions' databases including Yargıtay (Court of Cassation), Danıştay (Council of State), Constitutional Court, Competition Authority, Court of Accounts (Sayıştay), KVKK (Personal Data Protection Authority), BDDK (Banking Regulation and Supervision Agency), BTK (Information and Communication Technologies Authority), and others.

🎯 HIGHLY OPTIMIZED: This MCP server has been extensively optimized for token efficiency, achieving a 56.8% reduction in MCP overhead (from 14,061 to 6,073 tokens) while maintaining full functionality.

✅ PRODUCTION READY: Fully deployed on Fly.io with OAuth 2.0 authentication, Bearer JWT token support, and Claude AI integration. Server successfully handles 21 Turkish legal database tools with cross-origin authentication.

Key Commands

Installation and Setup

PyPI Installation (Recommended)
# Install from PyPI (no Git required)
pip install yargi-mcp

# Run the MCP server (stdio mode for Claude Desktop/5ire)
yargi-mcp

# Or use uvx for isolated execution
uvx yargi-mcp
Development Installation
# Install dependencies
uv sync

# Run the MCP server (stdio mode for Claude Desktop/5ire)
uv run mcp_server_main.py

# Or run via the entry point
yargi-mcp

# Run as web service (ASGI) with OAuth support
uv sync --extra saas    # Install OAuth dependencies (Clerk + Stripe)
cp .env.example .env    # Configure OAuth settings
uvicorn asgi_app:app --host 0.0.0.0 --port 8000

Development Commands

# IMPORTANT: Always use 'uv run' for Python files in this project

# Run tests (if any exist)
uv run -m pytest

# Run specific test file
uv run test_kik_client.py

# Debug specific modules
uv run debug_rekabet_arama.py

# Test individual components
uv run -c "import module; module.function()"

# ASGI Development
python run_asgi.py --reload --log-level debug  # Auto-reload for development
uvicorn fastapi_app:app --reload                # FastAPI with interactive docs
uvicorn starlette_app:app --reload             # Starlette with authentication

# Note: debug_*, test_*, mcp_overhead_*, and *.txt files are in .gitignore for temporary testing

# Testing with FastMCP Client
uv run test_core_tools_quick.py         # Quick test of all core tools (10 tests)
uv run simple_test.py                   # Simple individual tool test
uv run measure_mcp_directly.py          # Measure MCP token overhead

# Test KVKK module (uses fallback token if BRAVE_API_TOKEN not set)
python test_kvkv_module.py              # Test KVKK search and document retrieval

# Test KİK v2 comprehensive functionality
uv run test_kik_v2_comprehensive.py     # Test all three KİK v2 decision types (uyusmazlik, duzenleyici, mahkeme)

# MCP Optimization Testing
uv run test_core_tools_quick.py         # Verify all tools work after optimization

Read the full file on GitHub · 2,209 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. 11d ago First seen · 2,209 lines · 23,161 tokens per session scan A 2b9a79814fdd

Subscribe to this mod's changes

yargi-mcp CLAUDE.md is an instructions file published in the GitHub repository saidsurucu/yargi-mcp (1,112 stars, last pushed 4d ago), licensed MIT. It adds 23,161 tokens to every session, about $0.1158 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 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