Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@rekabet-karar-mcp search for recent antitrust decisions about monopolization"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Yargı MCP'nin ABD muadili: ABD federal içtihadında rekabet/antitröst kararlarını resmi ve açık veritabanından (CourtListener, Free Law Project) arayan bir MCP sunucusu. Rekabet hukuku tezi için ABD kararlarının doğrulanmış künyesini ve tam metnini getirir. (AB tarafı — CURIA/EUR-Lex — ikinci sürümde eklenecek.)
us_karar_ara — ABD federal içtihadında İngilizce tam metin arama. Dava adı,
mahkeme, tarih (dateFiled), atıf (citation), docket ve opinion_id döndürür.
us_karar_getir — opinion_id ile bir görüşün tam metnini + künyesini getirir.
Dipnottaki birebir doğrulama pasajları bu metinden alınır.
Künye, dava adı, tarih ve alıntılar API'den gelen ham veridir; sunucu bunları uydurmaz.
Related MCP server: legal-mcp
Node.js 22.18+ / 24 (.ts dosyasını derlemeden çalıştırmak için). Kurulu sürüm: v24.
CourtListener ücretsiz API token'ı (tam metin getirme için zorunlu; arama token'sız da çalışır ama düşük hız limitiyle).
cd C:\Users\acer\Desktop\rekabet-karar-mcp
npm installhttps://www.courtlistener.com/ adresinde ücretsiz hesap oluştur.
Profil → Profile → API bölümünden bir API token üret.
Token'ı mcp-config-ornek.json içindeki COURTLISTENER_TOKEN alanına yapıştır.
Not: Hesap açma ve şifre girme işlemlerini yalnızca kullanıcı yapar; sunucu token'ı ortam değişkeninden (env) okur, kod içinde token saklanmaz.
# token'sız (yalnızca arama çalışır)
node server.ts --selftest "consumer welfare Sherman Act"
# token ile (arama + tam metin)
$env:COURTLISTENER_TOKEN = "SENIN_TOKENIN"
node server.ts --selftest "predatory pricing recoupment"mcp-config-ornek.json içindeki mcpServers bloğunu Claude'un MCP yapılandırmasına
ekle, token'ı gir, oturumu yeniden başlat. Sonraki oturumda us_karar_ara ve
us_karar_getir araçları — Yargı MCP gibi — hazır gelir.
CourtListener REST API v4 (https://www.courtlistener.com/api/rest/v4/) — Free Law Project.
ABD federal ictihadinda (CourtListener) tam metin arama yapar; rekabet/antitrost kararlarini bulmak icin. Sorgu Ingilizce anahtar kelimelerle verilir (or. 'consumer welfare Sherman Act', 'predatory pricing recoupment'). Dava adi, mahkeme, tarih, atif (citation) ve opinion_id doner. Kunye uydurulmaz; ham API verisidir.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Sonuc sayisi (varsayilan 10) | |
| sorgu | Yes | Ingilizce tam metin arama sorgusu | |
| mahkeme | No | Opsiyonel court id filtresi: scotus, ca9, cand vb. | |
| siralama | No | Siralama; varsayilan ilgi (relevance) | |
| tarih_bitis | No | YYYY-MM-DD; bu tarihten once (filed_before) | |
| tarih_baslangic | No | YYYY-MM-DD; bu tarihten sonra karara verilenler (filed_after) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the transparency burden. It explicitly notes 'Kunye uydurulmaz; ham API verisidir' (does not fabricate metadata; raw API data), which is a meaningful behavioral disclosure. It also clarifies it returns specific fields (case name, court, date, citation, opinion_id) without describing every edge case.
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 three sentences, front-loaded with the core function, and contains no redundant phrases. Every sentence adds value: what it does, query format examples, and data authenticity note.
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?
For a search tool with no output schema and no annotations, the description covers purpose, query language, return fields, and data trustworthiness. It doesn't explicitly mention optional filters like court/date, but those are fully described in the input schema, so the description is sufficiently complete for agent use.
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 100% with all six parameters documented. The description adds example queries and output fields but does not elaborate on parameter formats or nuances beyond the schema. Thus it meets the baseline without significantly enhancing parameter understanding.
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 it performs full-text search in US federal case law (CourtListener) specifically for competition/antitrust decisions, using a specific verb and resource. It explicitly distinguishes this as a search tool from the likely retrieval-oriented sibling tool by describing its search scope and output.
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 usage context: user should supply English keywords and examples are given ('consumer welfare Sherman Act'). It doesn't explicitly state when not to use this tool or mention the sibling alternative, but the search vs. retrieval distinction is implied strongly enough.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Bir gorusun (opinion) tam metnini ve kunyesini getirir. opinion_id, us_karar_ara sonucundaki opinion_id'dir. Dipnot dogrulama blogu icin birebir pasajlar bu metinden alinir.
| Name | Required | Description | Default |
|---|---|---|---|
| opinion_id | Yes | us_karar_ara sonucundaki opinion_id | |
| maks_karakter | No | Donen metin uzunlugu ust siniri (varsayilan 18000) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. The phrase 'tam metnini' (full text) contradicts the maks_karakter parameter which caps returned length, meaning the text may be truncated. It also fails to mention permissions, error cases, or return format, and the truncation behavior is especially relevant for the verbatim-passage guarantee.
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 extremely concise: two sentences convey purpose, ID provenance, and a key use case. No redundant words, and it is front-loaded with the core purpose.
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?
For a low-complexity tool with no output schema, the description explains the basic flow (search then retrieve) and return content type. However, it does not mention that the length may be capped by maks_karakter or describe the output structure, leaving notable gaps for an agent.
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 coverage is 100% and the schema already describes both parameters. The tool description adds no extra meaning beyond what the schema provides, and the 'full text' wording conflicts with the length-limit parameter. Baseline 3 is appropriate.
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 verb ('getirir'), the resource ('bir gorusun tam metnini ve kunyesini'), and specifies that opinion_id comes from the us_karar_ara result. This distinguishes it from the sibling search tool.
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 tells the agent that the tool should be used after a search (opinion_id is from us_karar_ara) and states a specific use case (footnote verification). However, it does not explicitly say when not to use it or name alternatives beyond the implicit search workflow.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
The search tool and retrieval tool have clearly distinct functions: one queries by keywords and returns metadata, the other takes an opinion_id and returns the full text. There is no overlap or ambiguity between them.
Both tools follow a consistent verb-noun pattern: 'us_karar_ara' (search) and 'us_karar_getir' (get), sharing the 'us_karar_' prefix. This makes the toolset's structure predictable and easy to learn.
With only two tools, the server feels thin but is not inappropriate for its narrow purpose. The calibration suggests 1-2 tools are borderline, so this score reflects the minimalism while acknowledging the clear scope.
The server covers the essential search-and-retrieve workflow for US antitrust decisions. There are minor gaps such as lack of filtering options, but the core lifecycle (find a case, fetch its text) is complete for the stated purpose.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Search US court opinions, federal dockets, judges, citations, and oral arguments via CourtListener.
MCP for CourtListener: US federal and state opinions, dockets, judges, plus eCFR regulations.
Search U.S. case law, fetch opinions, and ask matter-aware legal questions over your documents.
Resolve, search and verify legal citations against the official sources, with provenance.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/cankilercioglu99-sudo/rekabet-karar-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
