Server profile

Yargı MCP

Search Turkish court and regulatory decisions from MCP-compatible assistants. Yargı MCP retrieves decision texts as Markdown and offers both local execution and a hosted streamable HTTP endpoint.

Server facts

Yargı MCP

Project

License
MIT

Tech

Runtime / language
pythonPython
Transports
stdio
Remote available
No
Authentication
Not specified

Activity

GitHub stars
1,007
Last commit
Data as of

Tags

  • Court Decisions
  • Document Retrieval
  • Legal Research
  • Python
  • Turkish Law

Overview

Yargı MCP makes Turkish legal sources available to assistants through a FastMCP server. It supports searching decisions and retrieving document text from courts and public bodies, including Yargıtay, Danıştay, the Constitutional Court, and procurement and competition authorities. Additional coverage includes data protection, banking and communications regulators, tax rulings, and insurance arbitration publications. The focus is source discovery and document access within an MCP client rather than a separate legal research interface.

Search capabilities vary by source. The README describes chamber or board selection, date ranges, keyword criteria, and exact-phrase matching for the Bedesten-backed tools. Some courts have more than one API path. Retrieved decisions are converted to Markdown, and several long-document operations return paginated text. This gives an assistant a way to inspect lengthy legal material in smaller portions. The supplied README describes these capabilities but does not enumerate their exact MCP tool identifiers.

Users can run the package locally through uvx or connect to a hosted streamable HTTP endpoint without local installation. The README prominently announces a move to a new remote address; the previous endpoint now returns only a relocation warning tool. It also explains that opening the MCP endpoint in a browser can produce an acceptance-header error without indicating a service outage. Local execution accesses the legal sources directly from the user's machine and does not depend on that remote server.

Install & configure

Requirements

  • Python 3.11 or newer for local execution
  • uv for the local uvx launch
  • An MCP-compatible client
  • Microsoft Visual C++ Redistributable for the documented Windows setup
Documented launch / install command
uvx yargi-mcp

The command is the local stdio option; remote_url is the separate hosted streamable HTTP alternative. The former fastmcp.app endpoint is no longer usable for research. The README's Claude Desktop custom-connector instructions require a paid subscription.

Config file · macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: %APPDATA%\Claude\claude_desktop_config.json

Use Settings → Developer → Edit Config when available. Do not assume a Linux configuration path; check the client documentation for your platform. Remote servers use the app’s connector flow when supported, not the local stdio file shown here. Merge this example with existing settings; do not overwrite unrelated servers.

Claude Desktop configuration
{
  "mcpServers": {
    "yargi-mcp": {
      "command": "uvx",
      "args": [
        "yargi-mcp"
      ],
      "env": {}
    }
  }
}

Read the Claude Desktop setup guide

Config file · Project: .cursor/mcp.json

User: ~/.cursor/mcp.json

The project path is relative to the workspace root. The tilde denotes your user home directory. Use Cursor’s MCP settings to confirm which configuration and scope your installed version is reading. Merge this example with existing settings; do not overwrite unrelated servers.

Cursor configuration
{
  "mcpServers": {
    "yargi-mcp": {
      "command": "uvx",
      "args": [
        "yargi-mcp"
      ],
      "env": {}
    }
  }
}

Read the Cursor setup guide

Config file · Workspace: .vscode/mcp.json

For user scope, use the “MCP: Open User Configuration” command if available. Do not guess a user configuration path across operating systems, profiles, containers, or remote workspaces; check the client documentation. Merge this example with existing settings; do not overwrite unrelated servers.

VS Code configuration
{
  "servers": {
    "yargi-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "yargi-mcp"
      ],
      "env": {}
    }
  }
}

Read the VS Code setup guide

Config file · macOS/Linux: ~/.codeium/windsurf/mcp_config.json

Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json

Open the MCP configuration through Windsurf’s settings when possible to confirm the active file. Paths can differ in managed or future releases; check the client documentation if this location is not present. Merge this example with existing settings; do not overwrite unrelated servers.

Windsurf configuration
{
  "mcpServers": {
    "yargi-mcp": {
      "command": "uvx",
      "args": [
        "yargi-mcp"
      ],
      "env": {}
    }
  }
}

Read the Windsurf setup guide

Config file · Project scope: .mcp.json at the repository root

The project file uses mcpServers. For user scope, use claude mcp add --scope user rather than assuming .mcp.json in your home directory is the user configuration. Check the client documentation for managed settings and storage details. Merge this example with existing settings; do not overwrite unrelated servers.

Claude Code configuration
{
  "mcpServers": {
    "yargi-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "yargi-mcp"
      ],
      "env": {}
    }
  }
}

Read the Claude Code setup guide

Examples are translated from the published configuration. Supply your own credentials and verify requirements in the upstream README. Remote connectors are shown only where a supported configuration format is known.

Tools

No individual tool names were confirmed in the source material. Check the repository for its current tool list.

Names, permissions, and defaults can change. Check the current upstream documentation before granting access.

Use cases

  • Find Turkish appellate decisions by subject and date.
  • Retrieve Constitutional Court decision text in manageable pages.
  • Research regulatory decisions across several public bodies.
  • Access legal sources from a local MCP assistant without using the hosted server.

Strengths

  • Covers multiple Turkish courts and regulators.
  • Converts retrieved decisions into Markdown.
  • Provides both local and hosted connection options.

Limitations

  • Search filters and retrieval behavior differ between sources.
  • Clients configured with the old hosted URL must migrate.
  • Exact tool identifiers are not stated in the supplied README.

Frequently asked questions

The README identifies https://yargimcp.surucu.dev/mcp as the current remote endpoint.

No. The documented uvx launch accesses legal sources directly from the local machine.

The endpoint expects MCP requests with suitable JSON and event-stream acceptance headers, not ordinary webpage browsing.

Several source-specific retrieval operations return Markdown in pages, with 5,000-character sections documented for multiple sources.

Independent listing, not an affiliation or security review. Grant the least access needed and verify the upstream instructions before running code.

Related MCP servers

Firecrawl MCP Server

Search & Web Data

Firecrawl MCP connects AI agents to web search, scraping, crawling, and live browser interaction. It offers hosted access or a local server for collecting structured web context and running research tasks.

Tavily MCP Server

Search & Web Data

Tavily MCP Server connects AI clients to web search, page extraction, site mapping, and crawling. Run it locally with an API key or connect to the hosted service using API-key or OAuth authentication.

AgentQL MCP Server

Search & Web Data

AgentQL MCP Server extracts structured JSON from a web page using a natural-language description of the desired fields. It provides one focused extraction tool for MCP assistants.

Exa MCP Server

Search & Web Data

Exa MCP Server gives AI assistants web search and readable page retrieval, with optional advanced search and agent research tools. It supports hosted connections and a local npm package for research and coding context.

Perplexity API Platform MCP Server

Search & Web Data

The Perplexity API Platform MCP Server gives assistants web search, conversational answers, research, and reasoning tools. It connects to Perplexity’s Search API and Sonar models through local stdio or an HTTP deployment.

ArXiv MCP Server

Search & Web Data

Search arXiv, download papers, and read their contents through an AI assistant. Local storage and research prompts support repeatable literature review and paper analysis.

Bright Data Web MCP

Search & Web Data

Give AI assistants live web search, page extraction, and optional browser automation through Bright Data. Tool groups also provide structured datasets, package information, and AI brand-visibility queries.

DuckDuckGo Search MCP Server

Search & Web Data

Give MCP assistants DuckDuckGo search and webpage text retrieval. It suits research workflows that need regional results, readable page content, and configurable filtering.