e-Gov Law

Provides fast access to e-Gov law data via MCP with intelligent search, alias handling, and batch capabilities.
  • python

4

GitHub Stars

python

Language

4 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "ryoooo-e-gov-law-mcp": {
      "command": "uv",
      "args": [
        "run",
        "--directory",
        "/path/to/e-gov-law-mcp",
        "python",
        "run_server.py"
      ],
      "env": {
        "EGOV_API_URL": "https://laws.e-gov.go.jp/api/2",
        "EGOV_API_TOKEN": "<EGOV_API_TOKEN>"
      }
    }
  }
}

You can run and use the e-Gov Law MCP Server v2 to search and retrieve Japanese legal texts and related content with fast, secure, and scalable MCP tooling. This server combines intelligent law lookup, high performance caching, and enterprise-ready security to help you build compliant legal search and analysis workflows.

How to use

You interact with the MCP server through a client that can call the available tools. Use the find_law_article tool to query specific provisions, the batch_find_articles tool for bulk searches, and other tools to retrieve full law content or search results with filters, highlighting, and pagination. The system is designed to handle complex article patterns, abbreviations, and multi-part references, returning structured results you can display or analyze in your application.

How to install

Prerequisites you need before installing include the Python runtime and the MCP client tooling environment. You also require a command-line interface capable of starting and managing the MCP server workflow.

# Prerequisites
# Install the MCP client wrapper (example helper may be uv-based)
# Install Python runtime if not present
# Ensure you have network access to fetch dependencies

Install and run steps you should follow exactly as shown here to start the server locally.

# Quick start for the MCP server
# 1) Clone the MCP server repository
# 2) Change into the directory
# 3) Synchronize dependencies
uv sync
# 4) Optionally enable performance monitoring
uv add psutil

Additional sections

Configuration and runtime are designed to be flexible. You can customize the MCP behavior using environment variables and external configuration files. A practical way to wire up Claude Desktop or another MCP client is to point it at the local MCP process via a standard I/O channel. The following example shows how you can run the local server through the MCP runtime and connect via a client.

{
  "mcpServers": {
    "e_gov_law": {
      "command": "uv",
      "args": [
        "run",
        "--directory",
        "/path/to/e-gov-law-mcp",
        "python",
        "run_server.py"
      ]
    }
  }
}

Claude Desktop configuration is supported to manage how you start and monitor the MCP server locally. You can place the following settings in your Claude Desktop config to run the server from a local directory.

{
  "mcpServers": {
    "e-gov-law": {
      "command": "uv",
      "args": [
        "run",
        "--directory",
        "/path/to/e-gov-law-mcp",
        "python",
        "run_server.py"
      ]
    }
  }
}

Available tools

find_law_article

Search for a specific article by law name and article number with support for complex patterns and numbering formats.

search_laws

Perform a law search with filtering and pagination to locate relevant statutes.

search_laws_by_keyword

Full-text keyword search with highlighting for matching terms in laws.

get_law_content

Retrieve the full content of a law article, with size limits and multiple formats (XML/JSON).

batch_find_articles

Execute up to 200 article lookups in a single batch, with performance statistics included.

prefetch_common_laws

Preload frequently accessed laws into the cache to reduce latency.

get_cache_stats

Provide real-time cache statistics and health monitoring.

clear_cache

Manage and clear cache at a granular level to recover memory.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational