add bedesten module

README.md

@@ -9,9 +9,14 @@ Bu proje, çeşitli Türk hukuk kaynaklarına (Yargıtay, Danıştay, Emsal Kara
 🎯 **Temel Özellikler**
 
 * Çeşitli Türk hukuk veritabanlarına programatik erişim için standart bir MCP arayüzü.
+* **Kapsamlı Mahkeme Daire/Kurul Filtreleme:** 79 farklı daire/kurul filtreleme seçeneği
+* **Dual/Triple API Desteği:** Her mahkeme için birden fazla API kaynağı ile maksimum kapsama
 * Aşağıdaki kurumların kararlarını arama ve getirme yeteneği:
-    * **Yargıtay:** Detaylı kriterlerle karar arama ve karar metinlerini Markdown formatında getirme.
+    * **Yargıtay:** Detaylı kriterlerle karar arama ve karar metinlerini Markdown formatında getirme. **Dual API** (Ana + Bedesten) + **52 Daire/Kurul Filtreleme** (Hukuk/Ceza Daireleri, Genel Kurullar)
-    * **Danıştay:** Anahtar kelime bazlı ve detaylı kriterlerle karar arama; karar metinlerini Markdown formatında getirme.
+    * **Danıştay:** Anahtar kelime bazlı ve detaylı kriterlerle karar arama; karar metinlerini Markdown formatında getirme. **Triple API** (Keyword + Detailed + Bedesten) + **27 Daire/Kurul Filtreleme** (İdari Daireler, Vergi/İdare Kurulları, Askeri Yüksek İdare Mahkemesi)
+    * **Yerel Hukuk Mahkemeleri:** Bedesten API ile yerel hukuk mahkemesi kararlarına erişim
+    * **İstinaf Hukuk Mahkemeleri:** Bedesten API ile istinaf mahkemesi kararlarına erişim
+    * **Kanun Yararına Bozma (KYB):** Bedesten API ile olağanüstü kanun yoluna erişim
     * **Emsal (UYAP):** Detaylı kriterlerle emsal karar arama ve karar metinlerini Markdown formatında getirme.
     * **Uyuşmazlık Mahkemesi:** Form tabanlı kriterlerle karar arama ve karar metinlerini (URL ile erişilen) Markdown formatında getirme.
     * **Anayasa Mahkemesi (Norm Denetimi):** Kapsamlı kriterlerle norm denetimi kararlarını arama; uzun karar metinlerini (5.000 karakterlik) sayfalanmış Markdown formatında getirme.
@@ -75,15 +80,33 @@ Bu bölüm, Yargı MCP aracını 5ire gibi Claude Desktop dışındaki MCP istem
 
 Bu FastMCP sunucusu aşağıdaki temel araçları sunar:
 
+### **Yargıtay Araçları (Dual API + 52 Daire Filtreleme)**
+* **Ana API:**
+    * `search_yargitay_detailed(arananKelime, birimYrgKurulDaire, ...)`: Yargıtay kararlarını detaylı kriterlerle arar. **52 daire/kurul seçeneği** (Hukuk/Ceza Daireleri 1-23, Genel Kurullar, Başkanlar Kurulu)
+    * `get_yargitay_document_markdown(id: str)`: Belirli bir Yargıtay kararının metnini Markdown formatında getirir.
+* **Bedesten API (Alternatif):**
+    * `search_yargitay_bedesten(phrase, birimAdi, ...)`: Bedesten API ile Yargıtay kararlarını arar. **Aynı 52 daire filtreleme**
+    * `get_yargitay_bedesten_document_markdown(documentId: str)`: Bedesten'den karar metni (HTML/PDF → Markdown)
 
-* **Yargıtay Araçları:**
+### **Danıştay Araçları (Triple API + 27 Daire Filtreleme)**
-    * `search_yargitay_detailed(search_query: YargitayDetailedSearchRequest) -> CompactYargitaySearchResult`: Yargıtay kararlarını detaylı kriterlerle arar.
+* **Ana API'lar:**
-    * `get_yargitay_document_markdown(id: str) -> YargitayDocumentMarkdown`: Belirli bir Yargıtay kararının metnini Markdown formatında getirir.
+    * `search_danistay_by_keyword(andKelimeler, orKelimeler, ...)`: Danıştay kararlarını anahtar kelimelerle arar.
+    * `search_danistay_detailed(daire, esasYil, ...)`: Danıştay kararlarını detaylı kriterlerle arar.
+    * `get_danistay_document_markdown(id: str)`: Belirli bir Danıştay kararının metnini Markdown formatında getirir.
+* **Bedesten API (Alternatif):**
+    * `search_danistay_bedesten(phrase, birimAdi, ...)`: Bedesten API ile Danıştay kararlarını arar. **27 daire/kurul seçeneği** (1-17. Daireler, Vergi/İdare Kurulları, Askeri Mahkemeler)
+    * `get_danistay_bedesten_document_markdown(documentId: str)`: Bedesten'den karar metni
 
-* **Danıştay Araçları:**
+### **Diğer Mahkemeler (Bedesten API)**
-    * `search_danistay_by_keyword(search_query: DanistayKeywordSearchRequest) -> CompactDanistaySearchResult`: Danıştay kararlarını anahtar kelimelerle arar.
+* **Yerel Hukuk Mahkemeleri:**
-    * `search_danistay_detailed(search_query: DanistayDetailedSearchRequest) -> CompactDanistaySearchResult`: Danıştay kararlarını detaylı kriterlerle arar.
+    * `search_yerel_hukuk_bedesten(phrase, pageSize, ...)`: Yerel hukuk mahkemesi kararlarını arar
-    * `get_danistay_document_markdown(id: str) -> DanistayDocumentMarkdown`: Belirli bir Danıştay kararının metnini Markdown formatında getirir.
+    * `get_yerel_hukuk_bedesten_document_markdown(documentId: str)`: Karar metni
+* **İstinaf Hukuk Mahkemeleri:**
+    * `search_istinaf_hukuk_bedesten(phrase, pageSize, ...)`: İstinaf mahkemesi kararlarını arar
+    * `get_istinaf_hukuk_bedesten_document_markdown(documentId: str)`: Karar metni
+* **Kanun Yararına Bozma (KYB):**
+    * `search_kyb_bedesten(phrase, pageSize, ...)`: Olağanüstü kanun yolu kararlarını arar
+    * `get_kyb_bedesten_document_markdown(documentId: str)`: Karar metni
 
 * **Emsal Karar Araçları:**
     * `search_emsal_detailed_decisions(search_query: EmsalSearchRequest) -> CompactEmsalSearchResult`: Emsal (UYAP) kararlarını detaylı kriterlerle arar.
@@ -109,6 +132,27 @@ Bu FastMCP sunucusu aşağıdaki temel araçları sunar:
     * `get_rekabet_kurumu_document(karar_id: str, page_number: Optional[int] = 1) -> RekabetDocument`: Belirli bir Rekabet Kurumu kararını `karar_id` ile alır. Kararın PDF formatındaki orijinalinden istenen sayfayı ayıklar ve Markdown formatında döndürür.
 
 
+---
+
+### **📊 Kapsamlı İstatistikler**
+- **Toplam Mahkeme/Kurum:** 11 farklı hukuki kurum
+- **Toplam MCP Tool:** 30+ arama ve belge getirme aracı  
+- **Daire/Kurul Filtreleme:** 79 farklı seçenek (52 Yargıtay + 27 Danıştay)
+- **API Kaynağı:** Dual/Triple API desteği ile maksimum kapsama
+- **Tam Türk Adalet Sistemi:** Yerel mahkemelerden en yüksek mahkemelere kadar
+
+**🏛️ Desteklenen Mahkeme Hiyerarşisi:**
+```
+Yerel Mahkemeler → İstinaf → Yargıtay/Danıştay → Anayasa Mahkemesi
+     ↓              ↓            ↓                    ↓
+Bedesten API   Bedesten API   Dual/Triple API   Norm+Bireysel API
+```
+
+**⚖️ Kapsamlı Daire Filtreleme:**
+- **Yargıtay:** 52 seçenek (1-23 Hukuk, 1-23 Ceza, Genel Kurullar, Başkanlar Kurulu)
+- **Danıştay:** 27 seçenek (1-17 Daireler, İdare/Vergi Kurulları, Askeri Mahkemeler)
+- **Toplam:** 79 farklı mahkeme dairesi/kurulu
+
 📜 **Lisans**
 
 Bu proje MIT Lisansı altında lisanslanmıştır. Detaylar için `LICENSE` dosyasına bakınız.

bedesten_mcp_module/__init__.py

@@ -0,0 +1 @@
+# bedesten_mcp_module/__init__.py

bedesten_mcp_module/client.py

@@ -0,0 +1,183 @@
+# bedesten_mcp_module/client.py
+
+import httpx
+import base64
+from typing import Optional
+import logging
+from markitdown import MarkItDown
+import tempfile
+import os
+
+from .models import (
+    BedestenSearchRequest, BedestenSearchResponse,
+    BedestenDocumentRequest, BedestenDocumentResponse,
+    BedestenDocumentMarkdown, BedestenDocumentRequestData
+)
+
+logger = logging.getLogger(__name__)
+
+class BedestenApiClient:
+    """
+    API Client for Bedesten (bedesten.adalet.gov.tr) - Alternative legal decision search system.
+    Currently used for Yargıtay decisions, but can be extended for other court types.
+    """
+    BASE_URL = "https://bedesten.adalet.gov.tr"
+    SEARCH_ENDPOINT = "/emsal-karar/searchDocuments"
+    DOCUMENT_ENDPOINT = "/emsal-karar/getDocumentContent"
+    
+    def __init__(self, request_timeout: float = 60.0):
+        self.http_client = httpx.AsyncClient(
+            base_url=self.BASE_URL,
+            headers={
+                "Accept": "*/*",
+                "Accept-Language": "tr-TR,tr;q=0.9,en-US;q=0.8,en;q=0.7",
+                "AdaletApplicationName": "UyapMevzuat",
+                "Content-Type": "application/json; charset=utf-8",
+                "Origin": "https://mevzuat.adalet.gov.tr",
+                "Referer": "https://mevzuat.adalet.gov.tr/",
+                "Sec-Fetch-Dest": "empty",
+                "Sec-Fetch-Mode": "cors",
+                "Sec-Fetch-Site": "same-site",
+                "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/137.0.0.0 Safari/537.36"
+            },
+            timeout=request_timeout
+        )
+    
+    async def search_documents(self, search_request: BedestenSearchRequest) -> BedestenSearchResponse:
+        """
+        Search for documents using Bedesten API.
+        Currently supports: YARGITAYKARARI, DANISTAYKARARI, YERELHUKMAHKARARI, etc.
+        """
+        logger.info(f"BedestenApiClient: Searching documents with phrase: {search_request.data.phrase}")
+        
+        try:
+            response = await self.http_client.post(
+                self.SEARCH_ENDPOINT, 
+                json=search_request.model_dump()
+            )
+            response.raise_for_status()
+            response_json = response.json()
+            
+            # Parse and return the response
+            return BedestenSearchResponse(**response_json)
+            
+        except httpx.RequestError as e:
+            logger.error(f"BedestenApiClient: HTTP request error during search: {e}")
+            raise
+        except Exception as e:
+            logger.error(f"BedestenApiClient: Error processing search response: {e}")
+            raise
+    
+    async def get_document_as_markdown(self, document_id: str) -> BedestenDocumentMarkdown:
+        """
+        Get document content and convert to markdown.
+        Handles both HTML (text/html) and PDF (application/pdf) content types.
+        """
+        logger.info(f"BedestenApiClient: Fetching document for markdown conversion (ID: {document_id})")
+        
+        try:
+            # Prepare request
+            doc_request = BedestenDocumentRequest(
+                data=BedestenDocumentRequestData(documentId=document_id)
+            )
+            
+            # Get document
+            response = await self.http_client.post(
+                self.DOCUMENT_ENDPOINT,
+                json=doc_request.model_dump()
+            )
+            response.raise_for_status()
+            response_json = response.json()
+            doc_response = BedestenDocumentResponse(**response_json)
+            
+            # Decode base64 content
+            content_bytes = base64.b64decode(doc_response.data.content)
+            mime_type = doc_response.data.mimeType
+            
+            logger.info(f"BedestenApiClient: Document mime type: {mime_type}")
+            
+            # Convert to markdown based on mime type
+            if mime_type == "text/html":
+                html_content = content_bytes.decode('utf-8')
+                markdown_content = self._convert_html_to_markdown(html_content)
+            elif mime_type == "application/pdf":
+                markdown_content = self._convert_pdf_to_markdown(content_bytes)
+            else:
+                logger.warning(f"Unsupported mime type: {mime_type}")
+                markdown_content = f"Unsupported content type: {mime_type}. Unable to convert to markdown."
+            
+            return BedestenDocumentMarkdown(
+                documentId=document_id,
+                markdown_content=markdown_content,
+                source_url=f"{self.BASE_URL}/document/{document_id}",
+                mime_type=mime_type
+            )
+            
+        except httpx.RequestError as e:
+            logger.error(f"BedestenApiClient: HTTP error fetching document {document_id}: {e}")
+            raise
+        except Exception as e:
+            logger.error(f"BedestenApiClient: Error processing document {document_id}: {e}")
+            raise
+    
+    def _convert_html_to_markdown(self, html_content: str) -> Optional[str]:
+        """Convert HTML to Markdown using MarkItDown"""
+        if not html_content:
+            return None
+            
+        temp_file_path = None
+        try:
+            md_converter = MarkItDown()
+            
+            # Write HTML to temp file
+            with tempfile.NamedTemporaryFile(mode="w", delete=False, suffix=".html", encoding="utf-8") as tmp:
+                tmp.write(html_content)
+                temp_file_path = tmp.name
+            
+            # Convert
+            result = md_converter.convert(temp_file_path)
+            markdown_content = result.text_content
+            
+            logger.info("Successfully converted HTML to Markdown")
+            return markdown_content
+            
+        except Exception as e:
+            logger.error(f"Error converting HTML to Markdown: {e}")
+            return f"Error converting HTML content: {str(e)}"
+        finally:
+            if temp_file_path and os.path.exists(temp_file_path):
+                os.remove(temp_file_path)
+    
+    def _convert_pdf_to_markdown(self, pdf_bytes: bytes) -> Optional[str]:
+        """Convert PDF to Markdown using MarkItDown"""
+        if not pdf_bytes:
+            return None
+            
+        temp_file_path = None
+        try:
+            # MarkItDown supports PDF with markitdown[pdf]
+            md_converter = MarkItDown()
+            
+            # Write PDF to temp file
+            with tempfile.NamedTemporaryFile(mode="wb", delete=False, suffix=".pdf") as tmp:
+                tmp.write(pdf_bytes)
+                temp_file_path = tmp.name
+            
+            # Convert
+            result = md_converter.convert(temp_file_path)
+            markdown_content = result.text_content
+            
+            logger.info("Successfully converted PDF to Markdown")
+            return markdown_content
+            
+        except Exception as e:
+            logger.error(f"Error converting PDF to Markdown: {e}")
+            return f"Error converting PDF content: {str(e)}. The document may be corrupted or in an unsupported format."
+        finally:
+            if temp_file_path and os.path.exists(temp_file_path):
+                os.remove(temp_file_path)
+    
+    async def close_client_session(self):
+        """Close HTTP client session"""
+        await self.http_client.aclose()
+        logger.info("BedestenApiClient: HTTP client session closed.")

bedesten_mcp_module/models.py

@@ -0,0 +1,115 @@
+# bedesten_mcp_module/models.py
+
+from pydantic import BaseModel, Field
+from typing import List, Optional, Dict, Any, Literal, Union
+
+# Import YargitayBirimEnum for chamber filtering
+from yargitay_mcp_module.models import YargitayBirimEnum
+
+# Danıştay Chamber/Board Options
+DanistayBirimEnum = Literal[
+    "",  # Empty string for "All" chambers
+    # Main Councils
+    "Büyük Gen.Kur.",  # Grand General Assembly
+    "İdare Dava Daireleri Kurulu",  # Administrative Cases Chambers Council
+    "Vergi Dava Daireleri Kurulu",  # Tax Cases Chambers Council
+    "İçtihatları Birleştirme Kurulu",  # Precedents Unification Council
+    "İdari İşler Kurulu",  # Administrative Affairs Council
+    "Başkanlar Kurulu",  # Presidents Council
+    # Chambers
+    "1. Daire", "2. Daire", "3. Daire", "4. Daire", "5. Daire",
+    "6. Daire", "7. Daire", "8. Daire", "9. Daire", "10. Daire",
+    "11. Daire", "12. Daire", "13. Daire", "14. Daire", "15. Daire",
+    "16. Daire", "17. Daire",
+    # Military High Administrative Court
+    "Askeri Yüksek İdare Mahkemesi",
+    "Askeri Yüksek İdare Mahkemesi Daireler Kurulu",
+    "Askeri Yüksek İdare Mahkemesi Başsavcılığı",
+    "Askeri Yüksek İdare Mahkemesi 1. Daire",
+    "Askeri Yüksek İdare Mahkemesi 2. Daire", 
+    "Askeri Yüksek İdare Mahkemesi 3. Daire"
+]
+
+# Search Request Models
+class BedestenSearchData(BaseModel):
+    pageSize: int
+    pageNumber: int  
+    itemTypeList: List[str]
+    phrase: str
+    birimAdi: Optional[Union[YargitayBirimEnum, DanistayBirimEnum]] = Field(None, description="""
+        Chamber/Board filter (optional). Available options depend on itemTypeList:
+        
+        For YARGITAYKARARI (52 options):
+        - None/null for ALL chambers
+        - 'Hukuk Genel Kurulu', '1. Hukuk Dairesi' through '23. Hukuk Dairesi'
+        - 'Ceza Genel Kurulu', '1. Ceza Dairesi' through '23. Ceza Dairesi'  
+        - 'Hukuk Daireleri Başkanlar Kurulu', 'Ceza Daireleri Başkanlar Kurulu'
+        - 'Büyük Genel Kurulu'
+        
+        For DANISTAYKARAR (27 options):
+        - None/null for ALL chambers
+        - 'Büyük Gen.Kur.', 'İdare Dava Daireleri Kurulu', 'Vergi Dava Daireleri Kurulu'
+        - '1. Daire' through '17. Daire'
+        - 'İçtihatları Birleştirme Kurulu', 'İdari İşler Kurulu', 'Başkanlar Kurulu'
+        - Military courts: 'Askeri Yüksek İdare Mahkemesi' variants
+    """)
+    sortFields: List[str] = ["KARAR_TARIHI"]
+    sortDirection: str = "desc"
+
+class BedestenSearchRequest(BaseModel):
+    data: BedestenSearchData
+    applicationName: str = "UyapMevzuat"
+    paging: bool = True
+
+# Search Response Models
+class BedestenItemType(BaseModel):
+    name: str
+    description: str
+
+class BedestenDecisionEntry(BaseModel):
+    documentId: str
+    itemType: BedestenItemType
+    birimId: Optional[str] = None
+    birimAdi: Optional[str]
+    esasNoYil: int
+    esasNoSira: int
+    kararNoYil: int
+    kararNoSira: int
+    kararTuru: Optional[str] = None
+    kararTarihi: str
+    kararTarihiStr: str
+    kesinlesmeDurumu: Optional[str] = None
+    kararNo: str
+    esasNo: str
+
+class BedestenSearchDataResponse(BaseModel):
+    emsalKararList: List[BedestenDecisionEntry]
+    total: int
+    start: int
+
+class BedestenSearchResponse(BaseModel):
+    data: BedestenSearchDataResponse
+    metadata: Dict[str, Any]
+
+# Document Request/Response Models
+class BedestenDocumentRequestData(BaseModel):
+    documentId: str
+
+class BedestenDocumentRequest(BaseModel):
+    data: BedestenDocumentRequestData
+    applicationName: str = "UyapMevzuat"
+
+class BedestenDocumentData(BaseModel):
+    content: str  # Base64 encoded HTML or PDF
+    mimeType: str
+    version: int
+
+class BedestenDocumentResponse(BaseModel):
+    data: BedestenDocumentData
+    metadata: Dict[str, Any]
+
+class BedestenDocumentMarkdown(BaseModel):
+    documentId: str = Field(..., description="The document ID from Bedesten")
+    markdown_content: Optional[str] = Field(None, description="The decision content converted to Markdown")
+    source_url: str = Field(..., description="The source URL of the document")
+    mime_type: Optional[str] = Field(None, description="Original content type (text/html or application/pdf)")

mcp_server_main.py

@@ -36,7 +36,13 @@ from fastmcp import FastMCP
 # --- Module Imports ---
 from yargitay_mcp_module.client import YargitayOfficialApiClient
 from yargitay_mcp_module.models import (
-    YargitayDetailedSearchRequest, YargitayDocumentMarkdown, CompactYargitaySearchResult
+    YargitayDetailedSearchRequest, YargitayDocumentMarkdown, CompactYargitaySearchResult,
+    YargitayBirimEnum
+)
+from bedesten_mcp_module.client import BedestenApiClient
+from bedesten_mcp_module.models import (
+    BedestenSearchRequest, BedestenSearchData,
+    BedestenDocumentMarkdown, DanistayBirimEnum
 )
 from danistay_mcp_module.client import DanistayApiClient
 from danistay_mcp_module.models import (
@@ -97,6 +103,7 @@ anayasa_norm_client_instance = AnayasaMahkemesiApiClient()
 anayasa_bireysel_client_instance = AnayasaBireyselBasvuruApiClient()
 kik_client_instance = KikApiClient()
 rekabet_client_instance = RekabetKurumuApiClient()
+bedesten_client_instance = BedestenApiClient()
 
 
 KARAR_TURU_ADI_TO_GUID_ENUM_MAP = {
@@ -120,9 +127,20 @@ async def search_yargitay_detailed(
     • +"phrase1" +"phrase2" = Multiple required phrases
     • +"required" -"excluded" = Include and exclude
     Examples: arsa payı | "arsa payı" | +"arsa payı" +"bozma sebebi" | bozma*"""),
-    birimYrgKurulDaire: str = Field("", description="Yargitay Board Unit (e.g., 'Hukuk Genel Kurulu')."),
+    birimYrgKurulDaire: YargitayBirimEnum = Field("", description="""
-    birimYrgHukukDaire: str = Field("", description="Yargitay Civil Chamber (e.g., '1. Hukuk Dairesi')."),
+        Yargıtay chamber/board selection. Available options:
-    birimYrgCezaDaire: str = Field("", description="Yargitay Criminal Chamber."),
+        • Empty string ('') for ALL chambers
+        • Hukuk Genel Kurulu (Civil General Assembly)
+        • 1. Hukuk Dairesi through 23. Hukuk Dairesi (Civil Chambers 1-23)
+        • Hukuk Daireleri Başkanlar Kurulu (Civil Chambers Presidents Board)
+        • Ceza Genel Kurulu (Criminal General Assembly)
+        • 1. Ceza Dairesi through 23. Ceza Dairesi (Criminal Chambers 1-23)
+        • Ceza Daireleri Başkanlar Kurulu (Criminal Chambers Presidents Board)
+        • Büyük Genel Kurulu (Grand General Assembly)
+        Total: 49 possible values
+    """),
+    birimYrgHukukDaire: str = Field("", description="Legacy field - use birimYrgKurulDaire instead"),
+    birimYrgCezaDaire: str = Field("", description="Legacy field - use birimYrgKurulDaire instead"),
     esasYil: str = Field("", description="Case year for 'Esas No'."),
     esasIlkSiraNo: str = Field("", description="Starting sequence number for 'Esas No'."),
     esasSonSiraNo: str = Field("", description="Ending sequence number for 'Esas No'."),
@@ -756,6 +774,331 @@ async def get_rekabet_kurumu_document(
         logger.exception(f"Error in tool 'get_rekabet_kurumu_document'. Karar ID: {karar_id}")
         raise 
 
+# --- MCP Tools for Bedesten (Alternative Yargitay Search) ---
+@app.tool()
+async def search_yargitay_bedesten(
+    phrase: str = Field(..., description="Aranacak kavram/kelime"),
+    pageSize: int = Field(10, ge=1, le=100, description="Sayfa başına sonuç sayısı"),
+    pageNumber: int = Field(1, ge=1, description="Sayfa numarası"),
+    birimAdi: Optional[YargitayBirimEnum] = Field(None, description="""
+        Yargıtay chamber/board filter (optional). Available options:
+        • None for ALL chambers  
+        • 'Hukuk Genel Kurulu' (Civil General Assembly)
+        • '1. Hukuk Dairesi' through '23. Hukuk Dairesi' (Civil Chambers 1-23)
+        • 'Hukuk Daireleri Başkanlar Kurulu' (Civil Chambers Presidents Board)
+        • 'Ceza Genel Kurulu' (Criminal General Assembly)
+        • '1. Ceza Dairesi' through '23. Ceza Dairesi' (Criminal Chambers 1-23)  
+        • 'Ceza Daireleri Başkanlar Kurulu' (Criminal Chambers Presidents Board)
+        • 'Büyük Genel Kurulu' (Grand General Assembly)
+        Total: 49 chamber options
+    """)
+) -> dict:
+    """
+    Searches Yargıtay decisions using Bedesten API (alternative source).
+    This complements search_yargitay_detailed for comprehensive coverage.
+    Always use BOTH Yargıtay search tools for complete results.
+    
+    Returns a simplified response with decision list and metadata.
+    """
+    search_data = BedestenSearchData(
+        pageSize=pageSize,
+        pageNumber=pageNumber,
+        itemTypeList=["YARGITAYKARARI"],  # Only Yargıtay decisions
+        phrase=phrase,
+        birimAdi=birimAdi
+    )
+    
+    search_request = BedestenSearchRequest(data=search_data)
+    
+    logger.info(f"Tool 'search_yargitay_bedesten' called: phrase='{phrase}', birimAdi='{birimAdi}', page={pageNumber}")
+    
+    try:
+        response = await bedesten_client_instance.search_documents(search_request)
+        
+        # Return simplified response format
+        return {
+            "decisions": [d.model_dump() for d in response.data.emsalKararList],
+            "total_records": response.data.total,
+            "requested_page": pageNumber,
+            "page_size": pageSize
+        }
+    except Exception as e:
+        logger.exception("Error in tool 'search_yargitay_bedesten'")
+        raise
+
+@app.tool()
+async def get_yargitay_bedesten_document_markdown(
+    documentId: str = Field(..., description="Document ID from Bedesten search results")
+) -> BedestenDocumentMarkdown:
+    """
+    Retrieves a Yargıtay decision document from Bedesten API and converts to Markdown.
+    Supports both HTML and PDF content types.
+    Use documentId from search_yargitay_bedesten results.
+    """
+    logger.info(f"Tool 'get_yargitay_bedesten_document_markdown' called for ID: {documentId}")
+    
+    if not documentId or not documentId.strip():
+        raise ValueError("Document ID must be a non-empty string.")
+    
+    try:
+        return await bedesten_client_instance.get_document_as_markdown(documentId)
+    except Exception as e:
+        logger.exception("Error in tool 'get_yargitay_bedesten_document_markdown'")
+        raise
+
+# --- MCP Tools for Bedesten (Alternative Danıştay Search) ---
+@app.tool()
+async def search_danistay_bedesten(
+    phrase: str = Field(..., description="Aranacak kavram/kelime"),
+    pageSize: int = Field(10, ge=1, le=100, description="Sayfa başına sonuç sayısı"),
+    pageNumber: int = Field(1, ge=1, description="Sayfa numarası"),
+    birimAdi: Optional[DanistayBirimEnum] = Field(None, description="""
+        Danıştay chamber/board filter (optional). Available options:
+        • None for ALL chambers
+        • Main Councils: 'Büyük Gen.Kur.', 'İdare Dava Daireleri Kurulu', 'Vergi Dava Daireleri Kurulu'
+        • Chambers: '1. Daire' through '17. Daire' (17 administrative chambers)
+        • Special Councils: 'İçtihatları Birleştirme Kurulu', 'İdari İşler Kurulu', 'Başkanlar Kurulu'
+        • Military: 'Askeri Yüksek İdare Mahkemesi' and its chambers/councils
+        Total: 27 chamber options
+    """)
+) -> dict:
+    """
+    Searches Danıştay decisions using Bedesten API (alternative source).
+    This complements existing Danıştay search tools (search_danistay_by_keyword, search_danistay_detailed) 
+    for comprehensive coverage. Always use ALL Danıştay search tools for complete results.
+    
+    Returns a simplified response with decision list and metadata.
+    """
+    search_data = BedestenSearchData(
+        pageSize=pageSize,
+        pageNumber=pageNumber,
+        itemTypeList=["DANISTAYKARAR"],  # Only Danıştay decisions
+        phrase=phrase,
+        birimAdi=birimAdi
+    )
+    
+    search_request = BedestenSearchRequest(data=search_data)
+    
+    logger.info(f"Tool 'search_danistay_bedesten' called: phrase='{phrase}', birimAdi='{birimAdi}', page={pageNumber}")
+    
+    try:
+        response = await bedesten_client_instance.search_documents(search_request)
+        
+        # Return simplified response format
+        return {
+            "decisions": [d.model_dump() for d in response.data.emsalKararList],
+            "total_records": response.data.total,
+            "requested_page": pageNumber,
+            "page_size": pageSize
+        }
+    except Exception as e:
+        logger.exception("Error in tool 'search_danistay_bedesten'")
+        raise
+
+@app.tool()
+async def get_danistay_bedesten_document_markdown(
+    documentId: str = Field(..., description="Document ID from Bedesten search results")
+) -> BedestenDocumentMarkdown:
+    """
+    Retrieves a Danıştay decision document from Bedesten API and converts to Markdown.
+    Supports both HTML and PDF content types.
+    Use documentId from search_danistay_bedesten results.
+    """
+    logger.info(f"Tool 'get_danistay_bedesten_document_markdown' called for ID: {documentId}")
+    
+    if not documentId or not documentId.strip():
+        raise ValueError("Document ID must be a non-empty string.")
+    
+    try:
+        return await bedesten_client_instance.get_document_as_markdown(documentId)
+    except Exception as e:
+        logger.exception("Error in tool 'get_danistay_bedesten_document_markdown'")
+        raise
+
+# --- MCP Tools for Bedesten (Yerel Hukuk Mahkemesi Search) ---
+@app.tool()
+async def search_yerel_hukuk_bedesten(
+    phrase: str = Field(..., description="Aranacak kavram/kelime"),
+    pageSize: int = Field(10, ge=1, le=100, description="Sayfa başına sonuç sayısı"),
+    pageNumber: int = Field(1, ge=1, description="Sayfa numarası")
+) -> dict:
+    """
+    Searches Yerel Hukuk Mahkemesi (Local Civil Court) decisions using Bedesten API.
+    This provides access to local court decisions that are not available through other APIs.
+    Currently the only available tool for searching Yerel Hukuk Mahkemesi decisions.
+    
+    Returns a simplified response with decision list and metadata.
+    """
+    search_data = BedestenSearchData(
+        pageSize=pageSize,
+        pageNumber=pageNumber,
+        itemTypeList=["YERELHUKUK"],  # Local Civil Court decisions
+        phrase=phrase
+    )
+    
+    search_request = BedestenSearchRequest(data=search_data)
+    
+    logger.info(f"Tool 'search_yerel_hukuk_bedesten' called: phrase='{phrase}', page={pageNumber}")
+    
+    try:
+        response = await bedesten_client_instance.search_documents(search_request)
+        
+        # Return simplified response format
+        return {
+            "decisions": [d.model_dump() for d in response.data.emsalKararList],
+            "total_records": response.data.total,
+            "requested_page": pageNumber,
+            "page_size": pageSize
+        }
+    except Exception as e:
+        logger.exception("Error in tool 'search_yerel_hukuk_bedesten'")
+        raise
+
+@app.tool()
+async def get_yerel_hukuk_bedesten_document_markdown(
+    documentId: str = Field(..., description="Document ID from Bedesten search results")
+) -> BedestenDocumentMarkdown:
+    """
+    Retrieves a Yerel Hukuk Mahkemesi decision document from Bedesten API and converts to Markdown.
+    Supports both HTML and PDF content types.
+    Use documentId from search_yerel_hukuk_bedesten results.
+    """
+    logger.info(f"Tool 'get_yerel_hukuk_bedesten_document_markdown' called for ID: {documentId}")
+    
+    if not documentId or not documentId.strip():
+        raise ValueError("Document ID must be a non-empty string.")
+    
+    try:
+        return await bedesten_client_instance.get_document_as_markdown(documentId)
+    except Exception as e:
+        logger.exception("Error in tool 'get_yerel_hukuk_bedesten_document_markdown'")
+        raise
+
+# --- MCP Tools for Bedesten (İstinaf Hukuk Mahkemesi Search) ---
+@app.tool()
+async def search_istinaf_hukuk_bedesten(
+    phrase: str = Field(..., description="Aranacak kavram/kelime"),
+    pageSize: int = Field(10, ge=1, le=100, description="Sayfa başına sonuç sayısı"),
+    pageNumber: int = Field(1, ge=1, description="Sayfa numarası")
+) -> dict:
+    """
+    Searches İstinaf Hukuk Mahkemesi (Civil Court of Appeals) decisions using Bedesten API.
+    This provides access to appellate court decisions that are not available through other APIs.
+    Currently the only available tool for searching İstinaf Hukuk Mahkemesi decisions.
+    
+    İstinaf courts are intermediate appellate courts in the Turkish judicial system,
+    handling appeals from local civil courts before cases reach Yargıtay.
+    
+    Returns a simplified response with decision list and metadata.
+    """
+    search_data = BedestenSearchData(
+        pageSize=pageSize,
+        pageNumber=pageNumber,
+        itemTypeList=["ISTINAFHUKUK"],  # Civil Court of Appeals decisions
+        phrase=phrase
+    )
+    
+    search_request = BedestenSearchRequest(data=search_data)
+    
+    logger.info(f"Tool 'search_istinaf_hukuk_bedesten' called: phrase='{phrase}', page={pageNumber}")
+    
+    try:
+        response = await bedesten_client_instance.search_documents(search_request)
+        
+        # Return simplified response format
+        return {
+            "decisions": [d.model_dump() for d in response.data.emsalKararList],
+            "total_records": response.data.total,
+            "requested_page": pageNumber,
+            "page_size": pageSize
+        }
+    except Exception as e:
+        logger.exception("Error in tool 'search_istinaf_hukuk_bedesten'")
+        raise
+
+@app.tool()
+async def get_istinaf_hukuk_bedesten_document_markdown(
+    documentId: str = Field(..., description="Document ID from Bedesten search results")
+) -> BedestenDocumentMarkdown:
+    """
+    Retrieves an İstinaf Hukuk Mahkemesi decision document from Bedesten API and converts to Markdown.
+    Supports both HTML and PDF content types.
+    Use documentId from search_istinaf_hukuk_bedesten results.
+    """
+    logger.info(f"Tool 'get_istinaf_hukuk_bedesten_document_markdown' called for ID: {documentId}")
+    
+    if not documentId or not documentId.strip():
+        raise ValueError("Document ID must be a non-empty string.")
+    
+    try:
+        return await bedesten_client_instance.get_document_as_markdown(documentId)
+    except Exception as e:
+        logger.exception("Error in tool 'get_istinaf_hukuk_bedesten_document_markdown'")
+        raise
+
+# --- MCP Tools for Bedesten (Kanun Yararına Bozma Search) ---
+@app.tool()
+async def search_kyb_bedesten(
+    phrase: str = Field(..., description="Aranacak kavram/kelime"),
+    pageSize: int = Field(10, ge=1, le=100, description="Sayfa başına sonuç sayısı"),
+    pageNumber: int = Field(1, ge=1, description="Sayfa numarası")
+) -> dict:
+    """
+    Searches Kanun Yararına Bozma (KYB - Extraordinary Appeal) decisions using Bedesten API.
+    This provides access to extraordinary appeal decisions that are not available through other APIs.
+    Currently the only available tool for searching KYB decisions.
+    
+    KYB decisions are extraordinary appeals in the Turkish judicial system,
+    where the Public Prosecutor's Office can request review of finalized decisions
+    in favor of the law and defendants.
+    
+    Returns a simplified response with decision list and metadata.
+    """
+    search_data = BedestenSearchData(
+        pageSize=pageSize,
+        pageNumber=pageNumber,
+        itemTypeList=["KYB"],  # Kanun Yararına Bozma decisions
+        phrase=phrase
+    )
+    
+    search_request = BedestenSearchRequest(data=search_data)
+    
+    logger.info(f"Tool 'search_kyb_bedesten' called: phrase='{phrase}', page={pageNumber}")
+    
+    try:
+        response = await bedesten_client_instance.search_documents(search_request)
+        
+        # Return simplified response format
+        return {
+            "decisions": [d.model_dump() for d in response.data.emsalKararList],
+            "total_records": response.data.total,
+            "requested_page": pageNumber,
+            "page_size": pageSize
+        }
+    except Exception as e:
+        logger.exception("Error in tool 'search_kyb_bedesten'")
+        raise
+
+@app.tool()
+async def get_kyb_bedesten_document_markdown(
+    documentId: str = Field(..., description="Document ID from Bedesten search results")
+) -> BedestenDocumentMarkdown:
+    """
+    Retrieves a Kanun Yararına Bozma (KYB) decision document from Bedesten API and converts to Markdown.
+    Supports both HTML and PDF content types.
+    Use documentId from search_kyb_bedesten results.
+    """
+    logger.info(f"Tool 'get_kyb_bedesten_document_markdown' called for ID: {documentId}")
+    
+    if not documentId or not documentId.strip():
+        raise ValueError("Document ID must be a non-empty string.")
+    
+    try:
+        return await bedesten_client_instance.get_document_as_markdown(documentId)
+    except Exception as e:
+        logger.exception("Error in tool 'get_kyb_bedesten_document_markdown'")
+        raise
+
 # --- Application Shutdown Handling ---
 def perform_cleanup():
     logger.info("MCP Server performing cleanup...")
@@ -775,7 +1118,8 @@ def perform_cleanup():
         globals().get('anayasa_norm_client_instance'),
         globals().get('anayasa_bireysel_client_instance'),
         globals().get('kik_client_instance'),
-        globals().get('rekabet_client_instance')
+        globals().get('rekabet_client_instance'),
+        globals().get('bedesten_client_instance')
     ]
     async def close_all_clients_async():
         tasks = []

yargitay_mcp_module/models.py

@@ -1,7 +1,32 @@
 # yargitay_mcp_module/models.py
 
 from pydantic import BaseModel, Field, HttpUrl
-from typing import List, Optional, Dict, Any
+from typing import List, Optional, Dict, Any, Literal
+
+# Yargıtay Chamber/Board Options
+YargitayBirimEnum = Literal[
+    "",  # Empty string for "All" chambers
+    # Hukuk (Civil) Chambers
+    "Hukuk Genel Kurulu",
+    "1. Hukuk Dairesi", "2. Hukuk Dairesi", "3. Hukuk Dairesi", "4. Hukuk Dairesi",
+    "5. Hukuk Dairesi", "6. Hukuk Dairesi", "7. Hukuk Dairesi", "8. Hukuk Dairesi",
+    "9. Hukuk Dairesi", "10. Hukuk Dairesi", "11. Hukuk Dairesi", "12. Hukuk Dairesi",
+    "13. Hukuk Dairesi", "14. Hukuk Dairesi", "15. Hukuk Dairesi", "16. Hukuk Dairesi",
+    "17. Hukuk Dairesi", "18. Hukuk Dairesi", "19. Hukuk Dairesi", "20. Hukuk Dairesi",
+    "21. Hukuk Dairesi", "22. Hukuk Dairesi", "23. Hukuk Dairesi",
+    "Hukuk Daireleri Başkanlar Kurulu",
+    # Ceza (Criminal) Chambers
+    "Ceza Genel Kurulu", 
+    "1. Ceza Dairesi", "2. Ceza Dairesi", "3. Ceza Dairesi", "4. Ceza Dairesi",
+    "5. Ceza Dairesi", "6. Ceza Dairesi", "7. Ceza Dairesi", "8. Ceza Dairesi",
+    "9. Ceza Dairesi", "10. Ceza Dairesi", "11. Ceza Dairesi", "12. Ceza Dairesi",
+    "13. Ceza Dairesi", "14. Ceza Dairesi", "15. Ceza Dairesi", "16. Ceza Dairesi",
+    "17. Ceza Dairesi", "18. Ceza Dairesi", "19. Ceza Dairesi", "20. Ceza Dairesi",
+    "21. Ceza Dairesi", "22. Ceza Dairesi", "23. Ceza Dairesi",
+    "Ceza Daireleri Başkanlar Kurulu",
+    # General Assembly
+    "Büyük Genel Kurulu"
+]
 
 class YargitayDetailedSearchRequest(BaseModel):
     """
@@ -10,11 +35,17 @@ class YargitayDetailedSearchRequest(BaseModel):
     Based on the payload provided by the user.
     """
     arananKelime: Optional[str] = Field("", description="Keyword to search for.")
-    # Department/Board selection. Based on user provided payload.
+    # Department/Board selection - Complete Yargıtay chamber hierarchy
-    # birimYrg* fields seem to be the ones used for filtering.
+    birimYrgKurulDaire: YargitayBirimEnum = Field("", description="""
-    birimYrgKurulDaire: Optional[str] = Field("", description="Yargitay Board Unit (e.g., 'Hukuk Genel Kurulu').")
+        Yargıtay chamber/board selection. Options include:
-    birimYrgHukukDaire: Optional[str] = Field("", description="Yargitay Civil Chamber (e.g., '1. Hukuk Dairesi').")
+        - Empty string ('') for ALL chambers
-    birimYrgCezaDaire: Optional[str] = Field("", description="Yargitay Criminal Chamber.")
+        - Civil: 'Hukuk Genel Kurulu', '1. Hukuk Dairesi' through '23. Hukuk Dairesi', 'Hukuk Daireleri Başkanlar Kurulu'
+        - Criminal: 'Ceza Genel Kurulu', '1. Ceza Dairesi' through '23. Ceza Dairesi', 'Ceza Daireleri Başkanlar Kurulu'
+        - General: 'Büyük Genel Kurulu'
+        Total: 49 possible values (including empty string for all chambers)
+    """)
+    birimYrgHukukDaire: Optional[str] = Field("", description="Legacy field - use birimYrgKurulDaire instead")
+    birimYrgCezaDaire: Optional[str] = Field("", description="Legacy field - use birimYrgKurulDaire instead")
     
     esasYil: Optional[str] = Field("", description="Case year for 'Esas No'.")
     esasIlkSiraNo: Optional[str] = Field("", description="Starting sequence number for 'Esas No'.")