Allows OpenAI Codex to search and retrieve current Turkish legislation from the official Mevzuat.gov.tr database, including law search, article extraction, and full text retrieval.
Türk mevzuatının resmî güncel metnini (mevzuat.gov.tr — Cumhurbaşkanlığı Mevzuat Bilgi Sistemi) yapay zekâ araçlarına açan bir MCP sunucusu.
Amaç tek cümle: model bir kanun maddesine atıf yaparken metni hafızasından değil, resmî kaynaktan alsın ve doğrulanabilir biçimde aktarsın. "TBK m.49" denildiğinde, sunucu maddenin yürürlükteki metnini ve doğrulama bağlantısını döndürür.
Hukuki danışmanlık değildir. Bu araç yalnızca resmî metne erişimi kolaylaştırır; yorum, içtihat değerlendirmesi ya da somut olaya uygulama içermez. Nihai metni daima mevzuat.gov.tr üzerinden teyit edin.
Ayrıntı: SORUMLULUK-REDDI.md · PRIVACY.md (veri toplama yok, telemetri yok; tek dış bağlantı mevzuat.gov.tr).
Tool | İşlev |
| Kanun arar; eşleşenleri ve |
| Bir kanunun belirli maddesinin resmî güncel metni + doğrulama kaynağı |
| Bir kanunun resmî güncel tam metni |
| Kayıtlı kanunların dizini (kısaltma, no, ad, kimlik) |
kanun parametresi esnektir: kısaltma (TBK), numara (6098) veya tam kimlik (1.5.6098).
Kayıtta olmayan kanunlar da numara/kimlikle çağrılabilir.
mevzuat_ara'da nerede üç değer alır: Baslik (kanun adında ara — kanunu
bulmak için), Icerik (tam metinde ara — bir kavramın hangi kanunlarda geçtiğini
taramak için), Tumu. Dönen mevzuat_id doğrudan madde_getir'e verilebilir —
böylece numarasını bilmediğin kanunlara da erişebilirsin.
Related MCP server: Mevzuat MCP
mevzuat.gov.tr, her mevzuatın konsolide (güncel) metnini şu desende PDF olarak sunar:
https://www.mevzuat.gov.tr/MevzuatMetin/<Tür>.<Tertip>.<No>.pdfBüyük kanunların tamamı 1.5.<No> (Tür=1 Kanun, Tertip=5) desenindedir — ör. TBK için
1.5.6098. Sunucu bu PDF'i çeker, metne dönüştürür (pypdf), istenen maddeyi regex ile
ayıklar ve süreç boyunca önbellekte tutar. Tamamen yereldir; hiçbir veri toplanmaz.
Arama, sitenin anasayfa/MevzuatDatatable uç noktasına gider (aranan ifade UTF-8 Base64
ile kodlanır). Her sonuç tur.tertip.no taşıdığından, eşleşen kanunun PDF kimliği
(dolayısıyla tam metni ve maddeleri) doğrudan elde edilir.
PyPI'de yayımlıdır; uv
ile ayrı kurulum gerekmeden çalışır.
claude mcp add turk-hukuku-mevzuat -- uvx --from turk-hukuku-mevzuat-mcp turk-hukuku-mevzuat~/.codex/config.toml içine:
[mcp_servers.turk-hukuku-mevzuat]
command = "uvx"
args = ["--from", "turk-hukuku-mevzuat-mcp", "turk-hukuku-mevzuat"]~/.gemini/settings.json içindeki mcpServers altına:
"turk-hukuku-mevzuat": {
"command": "uvx",
"args": ["--from", "turk-hukuku-mevzuat-mcp", "turk-hukuku-mevzuat"]
}pip install turk-hukuku-mevzuat-mcp
# komut: turk-hukuku-mevzuat (ya da: python -m turk_hukuku_mevzuat)Yalnızca kanunlar. Hem arama (MevzuatTur=1) hem metin erişimi kanunlarla sınırlıdır;
yönetmelik/tebliğ gibi diğer mevzuat türleri ve içtihat kapsam dışıdır.
Arama sıralaması garanti değil. mevzuat_ara ilk sonucu en alakalı yapmayabilir;
doğru kanunu ad/no'ya bakarak seçin.
PDF metnine bağımlı. Nadiren satır kırılması/birleşme olabilir; kuşkuda kaynağı açın.
Mülga/değişik maddelerde araç metni döndüremezse uyarı verir — madde uydurmaz.
MIT · © 2026 Aydın Can Polatkan
Veri kaynağı mevzuat.gov.tr'ye aittir; bu proje yalnızca kamuya açık resmî metne erişimi kolaylaştıran bağımsız bir istemcidir.
Bu çalışma, ömrünü Türk yargısına adamış babam Hâkim Vahit Polatkan'ın ebedi anısına ithaf edilmiştir.
Kayıtlı kanunları (kısaltma, no, ad, mevzuat_id) listeler.
Kayıtta olmayan kanunlar da numara/kimlikle çağrılabilir; bu yalnızca yaygın kanunların hızlı dizinidir.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description fully bears the transparency burden. It explains the behavior (lists registered laws with specific fields) and adds a caveat about unregistered laws being callable, which is useful context beyond the tool name.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, no wasted words. The main action is front-loaded, and the secondary sentence adds essential context about coverage. Every sentence earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no parameters, an output schema exists, and the description explains the purpose, fields, and scope (quick index). It is complete for this simple list tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are no parameters, and the schema coverage is 100%. The description adds value by clarifying the output fields (kısaltma, no, ad, mevzuat_id), exceeding the baseline score of 4 for zero-parameter tools.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool lists registered laws with specific fields (kısaltma, no, ad, mevzuat_id), distinguishing it from sibling tools like madde_getir or mevzuat_ara by emphasizing it is a quick index of common laws.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It explains when to use the tool (to list registered laws) and notes that unregistered laws can still be called by number/id, implying this is not exhaustive. However, it does not explicitly state when not to use it or provide direct comparisons with siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Bir kanunun RESMÎ güncel tam metnini getirir (mevzuat.gov.tr).
Büyük kanunlar uzundur; tek madde gerekiyorsa madde_getir tercih edilmeli.
Dönen: {kanun, mevzuat_id, kaynak, uzunluk, metin}.
kanun: kısaltma ("TMK"), numara ("4721") veya tam kimlik ("1.5.4721").
| Name | Required | Description | Default |
|---|---|---|---|
| kanun | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses the source (mevzuat.gov.tr), output structure, and input formats. However, it omits potential behavioral traits like rate limits, authentication, or error handling. Given the simplicity of the tool, this is mostly adequate.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with three short sentences. The first sentence states the primary purpose and source. The second provides usage guidance. The third defines input and output. No unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has one parameter, no output schema, and simple functionality, the description fully covers input format, output structure, and usage alternatives. It is complete for an agent to correctly select and invoke the tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has only one parameter 'kanun' with 0% coverage. The description meaningfully compensates by explaining it accepts abbreviations ('TMK'), numbers ('4721'), or full identifiers ('1.5.4721'), adding essential guidance beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves the official current full text of a law from mevzuat.gov.tr. It specifies the verb 'getirir' and resource 'kanun', and distinguishes from siblings by advising to use 'madde_getir' for single articles.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly tells when to use this tool: for full text of large laws, and when to avoid it: if only a single article is needed, use 'madde_getir' instead. This provides clear guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Bir kanunun belirli maddesinin RESMÎ güncel metnini getirir.
Atıf yapmadan önce bunu çağır: dönen metin mevzuat.gov.tr'nin yürürlükteki
konsolide metnidir; kaynak doğrulama URL'sidir. metin None ise madde
bulunamamıştır (numara yanlış ya da mülga) — uydurma, uyariyı aktar.
kanun: kısaltma ("TBK"), numara ("6098") veya tam kimlik ("1.5.6098").
| Name | Required | Description | Default |
|---|---|---|---|
| kanun | Yes | ||
| madde_no | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It reveals that the tool returns `metin` (consolidated text), `kaynak` (verification URL), and a possible warning. It also describes failure mode (article not found). However, it does not mention authentication, rate limits, or side effects. Lacking annotations, the description is fairly transparent but could be more explicit about being a read-only operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is only two paragraphs. The first sentence states the core purpose. The second paragraph provides usage context. Every sentence adds value, and there is no verbosity or repetition.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and simple parameters, the description covers the return fields (`metin`, `kaynak`, `uyari`) and failure handling. It explains what to do with the output. However, it does not explicitly state the data structure of the return object, which would help an agent parse the response correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. It explains the `kanun` parameter can be an abbreviation ('TBK'), number ('6098'), or full ID ('1.5.6098'). For `madde_no`, it is implied as the article number. While it adds value beyond the schema, it does not specify exact format constraints or validation rules for `kanun`.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves the official current text of a specific article of a law. The verb 'getirir' and resource 'bir kanunun belirli maddesinin RESMÎ güncel metni' are specific. The tool is distinguished from siblings like 'kanun_metni_getir' (law text retrieval) and 'mevzuat_ara' (search).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly says 'Atıf yapmadan önce bunu çağır' (call this before citing), explains returned fields (`metin`, `kaynak`, `uyari`), instructs what to do if `metin` is None, warns not to fabricate, and explains the `kanun` parameter format. This provides clear when-to-use and what-to-expect guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
mevzuat.gov.tr'de KANUN arar; eşleşen kanunları ve kimliklerini döndürür.
Kanunun numarasını bilmiyorsan önce bunu çağır: dönen her sonucun mevzuat_id
değeri doğrudan madde_getir/kanun_metni_getir'e verilebilir.
nerede: "Baslik" (kanun adında ara — kanunu bulmak için), "Icerik" (tam metinde ara — bir kavramın hangi kanunlarda geçtiğini taramak için) ya da "Tumu". adet: en çok kaç sonuç (1-50).
| Name | Required | Description | Default |
|---|---|---|---|
| adet | No | ||
| ifade | Yes | ||
| nerede | No | Baslik |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It describes a read-only search operation and mentions result limiting via 'adet'. However, it does not disclose potential side effects, authentication needs, or return format details beyond the ID and name.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and front-loaded with purpose. It uses a clear structure with explanations and colons. No unnecessary content, but the formatting is slightly informal.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and low schema coverage, the description adequately explains the tool's role, workflow integration with siblings, and parameter meanings. It could provide more detail on return format but is sufficient for the task.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema has 3 parameters with 0% coverage, but description explains 'nerede' options and 'adet' meaning (max result count 1-50). The 'ifade' parameter is implied as the search query but not explicitly described.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool searches for laws (KANUN) on mevzuat.gov.tr and returns matching laws and their IDs. It differentiates from sibling tools (madde_getir, kanun_metni_getir) by explaining that the returned mevzuat_id can be used with them.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear guidance: 'Kanunun numarasını bilmiyorsan önce bunu çağır' (if you don't know the law number, call this first) and explains how to use results. It also describes parameter choices for 'nerede' and 'adet'. However, it does not explicitly state when not to use this tool (e.g., when law number is known).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0bilinen_kanunlarkanun_metni_getirmadde_getirmevzuat_araScored across 4 tools
Her aracın net ve birbirinden ayrık bir amacı var: madde getirme, kanun metni getirme, arama yapma ve bilinen kanunları listeleme. Hiçbir örtüşme yok.
Tüm araç adları fiil+isim (nesne+eylem) yapısında ve Türkçe snake_case olarak tutarlı: madde_getir, kanun_metni_getir, mevzuat_ara, bilinen_kanunlar.
4 araç, mevzuat erişimi için ideal bir kapsam sunuyor. Ne eksik ne fazla; her araç gerekli ve yeterli.
Temel işlemler (ara, listele, tam metin getir, madde getir) mevcut. Salt okunur bir hukuk mevzuatı sunucusu için yeterli; belki alt maddelere veya belirli bölümlere erişim eklenebilirdi ama bu haliyle kullanışlı.
Resolve, search and verify legal citations against the official sources, with provenance.
Case law search, court decisions and súmulas, across indexed public sources (STF, STJ, TST, state co
Semantic search over Polish law and case law, citing the exact in-force article.
Acervo jurídico brasileiro: busca, Markdown, grafo de normas e precedentes, citação verificável.
