yargi-mcp

Provides a Model Context Protocol (MCP) server for accessing Turkish legal/decision sources (e.g., Yargıtay, Danıştay, Uyuşmazlık Mahkemesi, Anayasa Mahkemesi, KİK, Rekabet Kurumu, Sayıştay, KVKK, BDDK, Sigorta Tahkim) with searchable tools and document retrieval (mostly returned as Markdown, with some pagination/long-text chunking). It can be used remotely via a hosted FastMCP endpoint or run locally via a Python/uv entrypoint.

Evaluated Mar 30, 2026 (21d ago)
Repo ↗ Ai Ml mcp fastmcp legal turkish-law court-decisions retrieval markdown semantic-search
⚙ Agent Friendliness
54
/ 100
Can an agent use this?
🔒 Security
43
/ 100
Is it safe for agents?
⚡ Reliability
28
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
70
Documentation
55
Error Messages
0
Auth Simplicity
85
Rate Limits
10

🔒 Security

TLS Enforcement
90
Auth Strength
30
Scope Granularity
0
Dep. Hygiene
55
Secret Handling
45

Uses HTTPS for the remote MCP URL. However, the README does not document any authentication/authorization for the MCP server, scope model, or rate limiting. OPENROUTER_API_KEY is required for semantic search; the README provides examples of passing it via environment variables, but does not discuss safe storage, logging, or redaction. Dependencies include security-sensitive packages (e.g., cryptography) and LLM-related packages; no vulnerability status is provided here.

⚡ Reliability

Uptime/SLA
0
Version Stability
40
Breaking Changes
50
Error Recovery
20
AF Security Reliability

Best When

You want an MCP tool layer to browse and retrieve Turkish legal decisions programmatically, especially from within an LLM desktop/agent environment that supports MCP.

Avoid When

You require a documented auth model, strict rate-limit semantics, or a guaranteed uptime/SLA; or you cannot provide/store any API keys for optional semantic search.

Use Cases

  • Research assistance for Turkish case law and institutional decisions
  • Automated retrieval and summarization pipelines using MCP-capable LLM clients (e.g., Claude Desktop, 5ire)
  • Querying decisions with court/chamber filters and date ranges
  • Fetching document text converted to Markdown for downstream NLP
  • Optional semantic re-ranking of results using an external embedding/reranking service (OpenRouter API key)

Not For

  • Transactional systems requiring strong guarantees for updates (this is read/search oriented)
  • Use cases needing formal compliance assurances, audit logging, or guaranteed availability (not documented here)
  • Environments that disallow third-party hosted endpoints (remote MCP) or third-party API keys (OpenRouter)

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: Remote MCP via hosted endpoint (no explicit auth described in README) Local MCP server execution (no explicit auth described in README)
OAuth: No Scopes: No

The README does not clearly document authentication/authorization for the MCP endpoints. Optional semantic search uses OPENROUTER_API_KEY, which is an external API key but not described as MCP auth.

Pricing

Free tier: No
Requires CC: No

README mentions Claude Desktop requires a paid subscription, but does not state any pricing for the MCP service itself or workload-based costs. Optional semantic search implies usage costs for OpenRouter.

Agent Metadata

Pagination
some tools mention page_number/sayfalanmış Markdown; otherwise unspecified
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • README does not describe MCP error formats, retry semantics, or timeouts; agent behavior may need defensive handling
  • Optional semantic search tool availability depends on setting OPENROUTER_API_KEY
  • Document chunking/pagination behavior is not consistently specified across all tools in the provided README excerpt

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for yargi-mcp.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered